Initial chat-ui deployment without binary files

.gitignore

@@ -0,0 +1,41 @@
+# Node dependencies
+node_modules/
+
+# Environment files
+.env
+.env.local
+.env.*.local
+
+# Build output
+/build
+/.svelte-kit
+
+# IDE settings
+.vscode
+.idea
+
+# Operating System Files
+.DS_Store
+Thumbs.db
+
+# Binary files - avoid storing these in git
+*.ttf
+*.woff
+*.woff2
+*.eot
+*.png
+*.jpg
+*.jpeg
+*.gif
+*.svg
+*.ico
+*.webp
+*.mp3
+*.mp4
+*.webm
+*.pdf
+*.zip
+*.tar
+*.gz
+
+# We'll use CDN fonts instead of local fonts

Dockerfile

@@ -0,0 +1,32 @@
+FROM node:18-alpine AS dependencies
+
+# Install necessary packages for building
+RUN apk add --no-cache git python3 make g++
+
+WORKDIR /app
+COPY package*.json ./
+RUN npm install --legacy-peer-deps
+
+FROM dependencies AS builder
+
+WORKDIR /app
+COPY . .
+RUN npm run build
+
+FROM node:18-alpine AS deploy
+
+WORKDIR /app
+COPY --from=dependencies /app/node_modules ./node_modules
+COPY --from=builder /app/build ./build
+COPY --from=builder /app/static ./static
+COPY . .
+
+# Set environment variables
+ENV NODE_ENV=production
+ENV PORT=3000
+
+# Expose port
+EXPOSE 3000
+
+# Start command
+CMD ["npm", "run", "preview", "--", "--port", "3000", "--host", "0.0.0.0"]

chart/Chart.yaml

@@ -0,0 +1,5 @@
+apiVersion: v2
+name: chat-ui
+version: 0.0.1-latest
+type: application
+icon: https://huggingface.co/front/assets/huggingface_logo-noborder.svg

chart/env/prod.yaml

@@ -0,0 +1,700 @@
+image:
+  repository: huggingface
+  name: chat-ui
+
+nodeSelector:
+  role-huggingchat: "true"
+
+tolerations:
+  - key: "huggingface.co/huggingchat"
+    operator: "Equal"
+    value: "true"
+    effect: "NoSchedule"
+
+serviceAccount:
+  enabled: true
+  create: true
+  name: huggingchat-prod
+
+ingress:
+  path: "/chat"
+  annotations:
+    alb.ingress.kubernetes.io/healthcheck-path: "/healthcheck"
+    alb.ingress.kubernetes.io/listen-ports: "[{\"HTTP\": 80}, {\"HTTPS\": 443}]"
+    alb.ingress.kubernetes.io/group.name: "hub-prod"
+    alb.ingress.kubernetes.io/scheme: "internet-facing"
+    alb.ingress.kubernetes.io/ssl-redirect: "443"
+    alb.ingress.kubernetes.io/tags: "Env=prod,Project=hub,Terraform=true"
+    alb.ingress.kubernetes.io/target-node-labels: "role-hub-utils=true"
+    kubernetes.io/ingress.class: "alb"
+
+envVars:
+  ADDRESS_HEADER: 'X-Forwarded-For'
+  ADMIN_CLI_LOGIN: "false"
+  ALTERNATIVE_REDIRECT_URLS: '["huggingchat://login/callback"]'
+  APP_BASE: "/chat"
+  ALLOW_IFRAME: "false"
+  COMMUNITY_TOOLS: "true"
+  COOKIE_SAMESITE: "lax"
+  COOKIE_SECURE: "true"
+  ENABLE_ASSISTANTS: "true"
+  ENABLE_ASSISTANTS_RAG: "true"
+  ENABLE_CONFIG_MANAGER: "false"
+  METRICS_PORT: 5565
+  LOG_LEVEL: "debug"
+  METRICS_ENABLED: "true"
+  MODELS: >
+    [
+      {
+        "name": "meta-llama/Llama-3.3-70B-Instruct",
+        "id": "meta-llama/Llama-3.3-70B-Instruct",
+        "description": "Ideal for everyday use. A fast and extremely capable model matching closed source models' capabilities. Now with the latest Llama 3.3 weights!",
+        "modelUrl": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct",
+        "websiteUrl": "https://llama.meta.com/",
+        "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/meta-logo.png",
+        "tools": true,
+        "preprompt": "",
+        "parameters": {
+          "stop": ["<|endoftext|>", "<|eot_id|>"],
+          "temperature": 0.6,
+          "max_new_tokens": 1024,
+          "truncate": 7167
+        },
+        "promptExamples": [
+          {
+            "title": "Write an email",
+            "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12)"
+          },
+          {
+            "title": "Code a game",
+            "prompt": "Code a basic snake game in python, give explanations for each step."
+          },
+          {
+            "title": "Recipe help",
+            "prompt": "How do I make a delicious lemon cheesecake?"
+          }
+        ]
+      },
+      {
+        "name": "Qwen/Qwen3-235B-A22B",
+        "description": "Qwen's flagship model featuring optional reasoning. Exceptional performance with benchmarks rivaling R1 and o1.",
+        "modelUrl": "https://huggingface.co/Qwen/Qwen3-235B-A22B",
+        "websiteUrl": "https://qwenlm.github.io/blog/qwen3/",
+        "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/qwen-logo.png",
+        "preprompt": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant.",
+        "reasoning": {
+          "type": "tokens",
+          "beginToken": "<think>",
+          "endToken": "</think>"
+        },
+        "parameters": {
+          "stop": ["<|endoftext|>", "<|im_end|>"],
+          "temperature": 0.6,
+        },
+        "promptExamples": [
+          {
+            "title": "Write an email",
+            "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12) /nothink"
+          },
+          {
+            "title": "Build a website",
+            "prompt": "Generate a snazzy static landing page for a local coffee shop using HTML and CSS. You can use tailwind using <script src='https://cdn.tailwindcss.com'></script>."
+          },
+          {
+            "title": "Larger number",
+            "prompt": "9.11 or 9.9 which number is larger?"
+          },
+        ],
+        "endpoints": [
+          {
+            "type": "openai",
+            "baseURL": "https://internal.api-inference.huggingface.co/models/Qwen/Qwen3-235B-A22B/v1"
+          }
+        ]
+      },
+      {
+        "name": "Qwen/Qwen2.5-72B-Instruct",
+        "description": "The latest Qwen open model with improved role-playing, long text generation and structured data understanding.",
+        "modelUrl": "https://huggingface.co/Qwen/Qwen2.5-72B-Instruct",
+        "websiteUrl": "https://qwenlm.github.io/blog/qwen2.5/",
+        "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/qwen-logo.png",
+        "preprompt": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant.",
+        "parameters": {
+          "stop": ["<|endoftext|>", "<|im_end|>"],
+          "temperature": 0.6,
+          "truncate": 28672,
+          "max_new_tokens": 3072
+        },
+        "tools": true,
+        "promptExamples": [
+          {
+            "title": "Write an email",
+            "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12)"
+          },
+          {
+            "title": "Code a game",
+            "prompt": "Code a basic snake game in python, give explanations for each step."
+          },
+          {
+            "title": "Recipe help",
+            "prompt": "How do I make a delicious lemon cheesecake?"
+          }
+        ]
+      },
+      {
+        "name": "CohereForAI/c4ai-command-r-plus-08-2024",
+        "description": "Cohere's largest language model, optimized for conversational interaction and tool use. Now with the 2024 update!",
+        "modelUrl": "https://huggingface.co/CohereForAI/c4ai-command-r-plus-08-2024",
+        "websiteUrl": "https://docs.cohere.com/docs/command-r-plus",
+        "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/cohere-logo.png",
+        "tools": true,
+        "parameters": {
+          "stop": ["<|END_OF_TURN_TOKEN|>", "<|im_end|>"],
+          "truncate": 28672,
+          "max_new_tokens": 2048,
+          "temperature": 0.3
+        },
+        "promptExamples": [
+          {
+            "title": "Generate image",
+            "prompt": "Generate the portrait of a scientific mouse in its laboratory."
+          },
+          {
+            "title": "Review code",
+            "prompt": "Review this pull request: https://github.com/huggingface/chat-ui/pull/1131/files"
+          },
+          {
+            "title": "Code a game",
+            "prompt": "Code a basic snake game in python, give explanations for each step."
+          }
+        ]
+      },
+      {
+        "name": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
+        "modelUrl": "https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
+        "websiteUrl": "https://deepseek.com/",
+        "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/deepseek-logo.png",
+        "description": "The first reasoning model from DeepSeek, distilled into a 32B dense model. Outperforms o1-mini on multiple benchmarks.",
+        "reasoning": {
+          "type": "tokens",
+          "beginToken": "",
+          "endToken": "</think>"
+        },
+        "promptExamples": [
+          {
+            "title": "Rs in strawberry",
+            "prompt": "how many R in strawberry?"
+          },
+          {
+            "title": "Larger number",
+            "prompt": "9.11 or 9.9 which number is larger?"
+          },
+          {
+            "title": "Measuring 6 liters",
+            "prompt": "I have a 6- and a 12-liter jug. I want to measure exactly 6 liters."
+          }
+        ],
+        "endpoints": [
+          {
+            "type": "openai",
+            "baseURL": "https://internal.api-inference.huggingface.co/models/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/v1"
+          }
+        ]
+      },
+      {
+        "name": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
+        "modelUrl": "https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
+        "websiteUrl": "https://www.nvidia.com/",
+        "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/nvidia-logo.png",
+        "description": "Nvidia's latest Llama fine-tune, topping alignment benchmarks and optimized for instruction following.",
+        "parameters": {
+          "stop": ["<|eot_id|>", "<|im_end|>"],
+          "temperature": 0.5,
+          "truncate": 28672,
+          "max_new_tokens": 2048
+        },
+        "promptExamples": [
+          {
+            "title": "Rs in strawberry",
+            "prompt": "how many R in strawberry?"
+          },
+          {
+            "title": "Larger number",
+            "prompt": "9.11 or 9.9 which number is larger?"
+          },
+          {
+            "title": "Measuring 6 liters",
+            "prompt": "I have a 6- and a 12-liter jug. I want to measure exactly 6 liters."
+          }
+        ],
+        "endpoints": [
+          {
+            "type": "openai",
+            "baseURL": "https://internal.api-inference.huggingface.co/models/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF/v1"
+          }
+        ]
+      },
+      {
+        "name": "Qwen/QwQ-32B",
+        "preprompt": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step.",
+        "modelUrl": "https://huggingface.co/Qwen/QwQ-32B",
+        "websiteUrl": "https://qwenlm.github.io/blog/qwq-32b/",
+        "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/qwen-logo.png",
+        "description": "QwQ is the latest reasoning model released by the Qwen team, approaching the capabilities of R1 in benchmarks.",
+        "reasoning": {
+          "type": "tokens",
+          "beginToken": "",
+          "endToken": "</think>"
+        },
+        "promptExamples": [
+          {
+            "title": "Rs in strawberry",
+            "prompt": "how many R in strawberry?"
+          },
+          {
+            "title": "Larger number",
+            "prompt": "9.11 or 9.9 which number is larger?"
+          },
+          {
+            "title": "Measuring 6 liters",
+            "prompt": "I have a 6- and a 12-liter jug. I want to measure exactly 6 liters."
+          }
+        ],
+        "endpoints": [
+          {
+            "type": "openai",
+            "baseURL": "https://atv7xs1nxxtx2wl0.us-east-1.aws.endpoints.huggingface.cloud/v1"
+          }
+        ]
+      },
+      {
+        "name": "google/gemma-3-27b-it",
+        "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/google-logo.png",
+        "multimodal": true,
+        "description": "Google's latest open model with great multilingual performance, supports image inputs natively.",
+        "websiteUrl": "https://blog.google/technology/developers/gemma-3/",
+        "promptExamples": [
+          {
+            "title": "Write an email",
+            "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12)"
+          },
+          {
+            "title": "Code a game",
+            "prompt": "Code a basic snake game in python, give explanations for each step."
+          },
+          {
+            "title": "Recipe help",
+            "prompt": "How do I make a delicious lemon cheesecake?"
+          }
+        ],
+        "endpoints": [
+          {
+            "type": "openai",
+            "baseURL": "https://wp0d3hn6s3k8jk22.us-east-1.aws.endpoints.huggingface.cloud/v1",
+            "multimodal": {
+              "image": {
+                "maxSizeInMB": 10,
+                "maxWidth": 560,
+                "maxHeight": 560,
+                "supportedMimeTypes": ["image/jpeg"],
+                "preferredMimeType": "image/jpeg"
+              }
+            }
+          }
+        ]
+      },
+      {
+        "name": "mistralai/Mistral-Small-3.1-24B-Instruct-2503",
+        "displayName": "mistralai/Mistral-Small-3.1-24B-Instruct-2503",
+        "description": "A small model with good capabilities in language understanding and commonsense reasoning.",
+        "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/mistral-logo.png",
+        "websiteUrl": "https://mistral.ai/news/mistral-nemo/",
+        "modelUrl": "https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503",
+        "preprompt": "",
+        "promptExamples": [
+          {
+            "title": "Write an email",
+            "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12)"
+          },
+          {
+            "title": "Code a game",
+            "prompt": "Code a basic snake game in python, give explanations for each step."
+          },
+          {
+            "title": "Recipe help",
+            "prompt": "How do I make a delicious lemon cheesecake?"
+          }
+        ],
+
+        "endpoints": [
+          {
+            "type": "openai",
+            "baseURL": "https://hkjfqcryevvq9cie.us-east-1.aws.endpoints.huggingface.cloud/v1"
+          }
+        ]
+      },
+      {
+        "name": "Qwen/Qwen2.5-VL-32B-Instruct",
+        "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/qwen-logo.png",
+        "description": "The latest multimodal model from Qwen! Supports image inputs natively.",
+        "websiteUrl": "https://qwenlm.github.io/blog/qwen2.5-vl/",
+        "modelUrl": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct",
+        "multimodal": true,
+        "promptExamples": [
+          {
+            "title": "Write an email",
+            "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12)"
+          },
+          {
+            "title": "Code a game",
+            "prompt": "Code a basic snake game in python, give explanations for each step."
+          },
+          {
+            "title": "Recipe help",
+            "prompt": "How do I make a delicious lemon cheesecake?"
+          }
+        ],
+        "endpoints": [
+          {
+            "type": "openai",
+            "baseURL": "https://lf91qeosuambouj4.us-east-1.aws.endpoints.huggingface.cloud/v1",
+            "multimodal": {
+              "image": {
+                "maxSizeInMB": 10,
+                "maxWidth": 1024,
+                "maxHeight": 1024,
+                "supportedMimeTypes": ["image/png", "image/jpeg", "image/webp"],
+                "preferredMimeType": "image/webp"
+              }
+            }
+          }
+        ]
+      },
+      {
+        "name": "microsoft/Phi-4",
+        "description": "One of the best small models, super fast for simple tasks.",
+        "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/microsoft-logo.png",
+        "modelUrl": "https://huggingface.co/microsoft/Phi-4",
+        "websiteUrl": "https://techcommunity.microsoft.com/blog/aiplatformblog/introducing-phi-4-microsoft%E2%80%99s-newest-small-language-model-specializing-in-comple/4357090",
+        "preprompt": "",
+        "parameters": {
+          "stop": ["<|end|>", "<|endoftext|>", "<|assistant|>"],
+          "temperature": 0.6,
+          "truncate": 28672,
+          "max_new_tokens": 3072
+        },
+        "promptExamples": [
+          {
+            "title": "Write an email",
+            "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12)"
+          },
+          {
+            "title": "Code a game",
+            "prompt": "Code a basic snake game in python, give explanations for each step."
+          },
+          {
+            "title": "Recipe help",
+            "prompt": "How do I make a delicious lemon cheesecake?"
+          }
+        ],
+        "endpoints": [
+          {
+            "type": "openai",
+            "baseURL": "https://up5ijetg6a2e9zlb.us-east-1.aws.endpoints.huggingface.cloud/v1"
+          }
+        ]
+      },
+      {
+        "name": "NousResearch/Hermes-3-Llama-3.1-8B",
+        "description": "Nous Research's latest Hermes 3 release in 8B size. Follows instruction closely.",
+        "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/nous-logo.png",
+        "websiteUrl": "https://nousresearch.com/",
+        "modelUrl": "https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B",
+        "promptExamples": [
+          {
+            "title": "Write an email",
+            "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12)"
+          },
+          {
+            "title": "Code a game",
+            "prompt": "Code a basic snake game in python, give explanations for each step."
+          },
+          {
+            "title": "Recipe help",
+            "prompt": "How do I make a delicious lemon cheesecake?"
+          }
+        ],
+        "parameters": {
+          "stop": ["<|im_end|>"],
+          "temperature": 0.6,
+          "truncate": 14336,
+          "max_new_tokens": 1536
+        }
+      },
+      {
+        "name": "internal/task",
+        "tokenizer" : "NousResearch/Hermes-3-Llama-3.1-8B",
+        "unlisted": true,
+        "tools" : true,
+        "endpoints": [
+          {
+            "type": "openai",
+            "baseURL": "https://internal.api-inference.huggingface.co/models/NousResearch/Hermes-3-Llama-3.1-8B/v1"
+          }
+        ],
+        "parameters": {
+          "temperature": 0.1,
+          "max_new_tokens": 256
+        },
+      }
+    ]
+
+  NODE_ENV: "prod"
+  NODE_LOG_STRUCTURED_DATA: true
+  OLD_MODELS: >
+    [
+      { "name": "bigcode/starcoder" },
+      { "name": "OpenAssistant/oasst-sft-6-llama-30b-xor" },
+      { "name": "HuggingFaceH4/zephyr-7b-alpha" },
+      { "name": "openchat/openchat_3.5" },
+      { "name": "openchat/openchat-3.5-1210" },
+      { "name": "tiiuae/falcon-180B-chat" },
+      { "name": "codellama/CodeLlama-34b-Instruct-hf" },
+      { "name": "google/gemma-7b-it" },
+      { "name": "meta-llama/Llama-2-70b-chat-hf" },
+      { "name": "codellama/CodeLlama-70b-Instruct-hf" },
+      { "name": "openchat/openchat-3.5-0106" },
+      { "name": "meta-llama/Meta-Llama-3-70B-Instruct" },
+      { "name": "meta-llama/Meta-Llama-3.1-405B-Instruct-FP8" },
+      {
+        "name": "CohereForAI/c4ai-command-r-plus",
+        "transferTo": "CohereForAI/c4ai-command-r-plus-08-2024"
+      },
+      {
+        "name": "01-ai/Yi-1.5-34B-Chat",
+        "transferTo": "CohereForAI/c4ai-command-r-plus-08-2024"
+      },
+      {
+        "name": "mistralai/Mixtral-8x7B-Instruct-v0.1",
+        "transferTo": "mistralai/Mistral-Small-3.1-24B-Instruct-2503"
+      },
+      {
+        "name": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
+        "transferTo": "NousResearch/Hermes-3-Llama-3.1-8B"
+      },
+      {
+        "name": "mistralai/Mistral-7B-Instruct-v0.3",
+        "transferTo": "mistralai/Mistral-Small-3.1-24B-Instruct-2503"
+      },
+      {
+        "name": "microsoft/Phi-3-mini-4k-instruct",
+        "transferTo": "microsoft/Phi-4"
+      },
+      {
+        "name": "meta-llama/Meta-Llama-3.1-70B-Instruct",
+        "transferTo": "meta-llama/Llama-3.3-70B-Instruct"
+      },
+      {
+        "name": "Qwen/QwQ-32B-Preview",
+        "transferTo": "Qwen/QwQ-32B"
+      },
+      {
+        "name": "mistralai/Mistral-Nemo-Instruct-2407",
+        "transferTo": "mistralai/Mistral-Small-3.1-24B-Instruct-2503"
+      },
+      {
+        "name": "microsoft/Phi-3.5-mini-instruct",
+        "transferTo": "microsoft/Phi-4"
+      },
+      {
+        "name": "Qwen/Qwen2.5-Coder-32B-Instruct",
+        "transferTo": "Qwen/QwQ-32B"
+      },
+      {
+        "name": "meta-llama/Llama-3.2-11B-Vision-Instruct",
+        "transferTo" : "Qwen/Qwen2.5-VL-32B-Instruct"
+      }
+    ]
+  PUBLIC_ORIGIN: "https://huggingface.co"
+  PUBLIC_SHARE_PREFIX: "https://hf.co/chat"
+  PUBLIC_ANNOUNCEMENT_BANNERS: >
+    [
+      {
+        "title": "Qwen 3 235B is available!",
+        "linkTitle": "Try it out!",
+        "linkHref": "https://huggingface.co/chat/models/Qwen/Qwen3-235B-A22B"
+      }
+    ]
+  PUBLIC_APP_NAME: "HuggingChat"
+  PUBLIC_APP_ASSETS: "huggingchat"
+  PUBLIC_APP_COLOR: "yellow"
+  PUBLIC_APP_DESCRIPTION: "Making the community's best AI chat models available to everyone."
+  PUBLIC_APP_DISCLAIMER_MESSAGE: "Disclaimer: AI is an area of active research with known problems such as biased generation and misinformation. Do not use this application for high-stakes decisions or advice."
+  PUBLIC_APP_GUEST_MESSAGE: "Sign in with a free Hugging Face account to continue using HuggingChat."
+  PUBLIC_APP_DATA_SHARING: 0
+  PUBLIC_APP_DISCLAIMER: 1
+  PUBLIC_PLAUSIBLE_SCRIPT_URL: "/js/script.js"
+  REQUIRE_FEATURED_ASSISTANTS: "true"
+  TASK_MODEL: "internal/task"
+  TEXT_EMBEDDING_MODELS: >
+    [{
+      "name": "bge-base-en-v1-5-sxa",
+      "displayName": "bge-base-en-v1-5-sxa",
+      "chunkCharLength": 512,
+      "endpoints": [{
+        "type": "tei",
+        "url": "https://huggingchat-tei.hf.space/"
+      }]
+    }]
+  WEBSEARCH_BLOCKLIST: '["youtube.com", "twitter.com"]'
+  XFF_DEPTH: '2'
+  TOOLS: >
+    [
+      {
+        "_id": "000000000000000000000001",
+        "displayName": "Image Generation",
+        "description": "Use this tool to generate images based on a prompt.",
+        "color": "yellow",
+        "icon": "camera",
+        "baseUrl": "black-forest-labs/FLUX.1-schnell",
+        "name": "image_generation",
+        "endpoint": "/infer",
+        "inputs": [
+          {
+            "name": "prompt",
+            "description": "A prompt to generate an image from",
+            "paramType": "required",
+            "type": "str"
+          },
+          { "name": "seed", "paramType": "fixed", "value": "0", "type": "float" },
+          {
+            "name": "randomize_seed",
+            "paramType": "fixed",
+            "value": "true",
+            "type": "bool"
+          },
+          {
+            "name": "width",
+            "description": "numeric value between 256 and 2048",
+            "paramType": "optional",
+            "default": 1024,
+            "type": "float"
+          },
+          {
+            "name": "height",
+            "description": "numeric value between 256 and 2048",
+            "paramType": "optional",
+            "default": 1024,
+            "type": "float"
+          },
+          {
+            "name": "num_inference_steps",
+            "paramType": "fixed",
+            "value": "4",
+            "type": "float"
+          }
+        ],
+        "outputComponent": "image",
+        "outputComponentIdx": 0,
+        "showOutput": true
+      },
+      {
+        "_id": "000000000000000000000002",
+        "displayName": "Document Parser",
+        "description": "Use this tool to parse any document and get its content in markdown format.",
+        "color": "yellow",
+        "icon": "cloud",
+        "baseUrl": "huggingchat/document-parser",
+        "name": "document_parser",
+        "endpoint": "/predict",
+        "inputs": [
+          {
+            "name": "document",
+            "description": "Filename of the document to parse",
+            "paramType": "required",
+            "type": "file",
+            "mimeTypes": 'application/*'
+          },
+          {
+            "name": "filename",
+            "paramType": "fixed",
+            "value": "document.pdf",
+            "type": "str"
+          }
+        ],
+        "outputComponent": "textbox",
+        "outputComponentIdx": 0,
+        "showOutput": false,
+        "isHidden": true
+      },
+      {
+        "_id": "000000000000000000000003",
+        "name": "edit_image",
+        "baseUrl": "multimodalart/cosxl",
+        "endpoint": "/run_edit",
+        "inputs": [
+          {
+            "name": "image",
+            "description": "The image path to be edited",
+            "paramType": "required",
+            "type": "file",
+            "mimeTypes": 'image/*'
+          },
+          {
+            "name": "prompt",
+            "description": "The prompt with which to edit the image",
+            "paramType": "required",
+            "type": "str"
+          },
+          {
+            "name": "negative_prompt",
+            "paramType": "fixed",
+            "value": "",
+            "type": "str"
+          },
+          {
+            "name": "guidance_scale",
+            "paramType": "fixed",
+            "value": 6.5,
+            "type": "float"
+          },
+          {
+            "name": "steps",
+            "paramType": "fixed",
+            "value": 30,
+            "type": "float"
+          }
+        ],
+        "outputComponent": "image",
+        "showOutput": true,
+        "displayName": "Image Editor",
+        "color": "green",
+        "icon": "camera",
+        "description": "This tool lets you edit images",
+        "outputComponentIdx": 0
+      }
+    ]
+  HF_ORG_ADMIN: '644171cfbd0c97265298aa99'
+  HF_ORG_EARLY_ACCESS: '5e67bd5b1009063689407478'
+  HF_API_ROOT: 'https://internal.api-inference.huggingface.co/models'
+infisical:
+  enabled: true
+  env: "prod-us-east-1"
+
+autoscaling:
+  enabled: true
+  minReplicas: 12
+  maxReplicas: 30
+  targetMemoryUtilizationPercentage: "50"
+  targetCPUUtilizationPercentage: "50"
+
+resources:
+  requests:
+    cpu: 2
+    memory: 4Gi
+  limits:
+    cpu: 4
+    memory: 8Gi
+
+monitoring:
+  enabled: true

chart/templates/_helpers.tpl

@@ -0,0 +1,22 @@
+{{- define "name" -}}
+{{- default $.Release.Name | trunc 63 | trimSuffix "-" -}}
+{{- end -}}
+
+{{- define "app.name" -}}
+chat-ui
+{{- end -}}
+
+{{- define "labels.standard" -}}
+release: {{ $.Release.Name | quote }}
+heritage: {{ $.Release.Service | quote }}
+chart: "{{ include "name" . }}"
+app: "{{ include "app.name" . }}"
+{{- end -}}
+
+{{- define "labels.resolver" -}}
+release: {{ $.Release.Name | quote }}
+heritage: {{ $.Release.Service | quote }}
+chart: "{{ include "name" . }}"
+app: "{{ include "app.name" . }}-resolver"
+{{- end -}}
+

chart/templates/config.yaml

@@ -0,0 +1,10 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  labels: {{ include "labels.standard" . | nindent 4 }}
+  name: {{ include "name" . }}
+  namespace: {{ .Release.Namespace }}
+data:
+  {{- range $key, $value := $.Values.envVars }}
+  {{ $key }}: {{ $value | quote }}
+  {{- end }}

chart/templates/deployment.yaml

@@ -0,0 +1,81 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  labels: {{ include "labels.standard" . | nindent 4 }}
+  name: {{ include "name" . }}
+  namespace: {{ .Release.Namespace }}
+  {{- if .Values.infisical.enabled }}
+  annotations:
+    secrets.infisical.com/auto-reload: "true"
+  {{- end }}
+spec:
+  progressDeadlineSeconds: 600
+  {{- if not $.Values.autoscaling.enabled }}
+  replicas: {{ .Values.replicas }}
+  {{- end }}
+  revisionHistoryLimit: 10
+  selector:
+    matchLabels: {{ include "labels.standard" . | nindent 6 }}
+  strategy:
+    rollingUpdate:
+      maxSurge: 25%
+      maxUnavailable: 25%
+    type: RollingUpdate
+  template:
+    metadata:
+      labels: {{ include "labels.standard" . | nindent 8 }}
+      annotations:
+        checksum/config: {{ include (print $.Template.BasePath "/config.yaml") . | sha256sum }}
+        {{- if $.Values.envVars.NODE_LOG_STRUCTURED_DATA }}
+        co.elastic.logs/json.expand_keys: "true"
+        {{- end }}
+    spec:
+      {{- if .Values.serviceAccount.enabled }}
+      serviceAccountName: "{{ .Values.serviceAccount.name | default (include "name" .) }}"
+      {{- end }}
+      containers:
+        - name: chat-ui
+          image: "{{ .Values.image.repository }}/{{ .Values.image.name }}:{{ .Values.image.tag }}"
+          imagePullPolicy: {{ .Values.image.pullPolicy }}
+          readinessProbe:
+            failureThreshold: 30
+            periodSeconds: 10
+            httpGet:
+              path: {{ $.Values.envVars.APP_BASE | default "" }}/healthcheck
+              port: {{ $.Values.envVars.APP_PORT | default 3000 | int }}
+          livenessProbe:
+            failureThreshold: 30
+            periodSeconds: 10
+            httpGet:
+              path: {{ $.Values.envVars.APP_BASE | default "" }}/healthcheck
+              port: {{ $.Values.envVars.APP_PORT | default 3000 | int }}
+          ports:
+            - containerPort: {{ $.Values.envVars.APP_PORT | default 3000 | int }}
+              name: http
+              protocol: TCP
+            {{- if $.Values.monitoring.enabled }}
+            - containerPort: {{ $.Values.envVars.METRICS_PORT | default 5565 | int }}
+              name: metrics
+              protocol: TCP
+            {{- end }}
+          resources: {{ toYaml .Values.resources | nindent 12 }}
+          {{- with $.Values.extraEnv }}
+          env:
+            {{- toYaml . | nindent 14 }}
+          {{- end }}
+          envFrom:
+            - configMapRef:
+                name: {{ include "name" . }}
+          {{- if $.Values.infisical.enabled }}
+            - secretRef:
+                name: {{ include "name" $ }}-secs
+          {{- end }}
+          {{- with $.Values.extraEnvFrom }}
+            {{- toYaml . | nindent 14 }}
+          {{- end }}
+      nodeSelector: {{ toYaml .Values.nodeSelector | nindent 8 }}
+      tolerations: {{ toYaml .Values.tolerations | nindent 8 }}
+      volumes:
+        - name: config
+          configMap:
+            name: {{ include "name" . }}

chart/templates/hpa.yaml

@@ -0,0 +1,45 @@
+{{- if $.Values.autoscaling.enabled }}
+apiVersion: autoscaling/v2
+kind: HorizontalPodAutoscaler
+metadata:
+  labels: {{ include "labels.standard" . | nindent 4 }}
+  name: {{ include "name" . }}
+  namespace: {{ .Release.Namespace }}
+spec:
+  scaleTargetRef:
+    apiVersion: apps/v1
+    kind: Deployment
+    name: {{ include "name" . }}
+  minReplicas: {{ $.Values.autoscaling.minReplicas }}
+  maxReplicas: {{ $.Values.autoscaling.maxReplicas }}
+  metrics:
+    {{- if ne "" $.Values.autoscaling.targetMemoryUtilizationPercentage }}
+    - type: Resource
+      resource:
+        name: memory
+        target:
+          type: Utilization
+          averageUtilization: {{ $.Values.autoscaling.targetMemoryUtilizationPercentage | int }}
+    {{- end }}
+    {{- if ne "" $.Values.autoscaling.targetCPUUtilizationPercentage }}
+    - type: Resource
+      resource:
+        name: cpu
+        target:
+          type: Utilization
+          averageUtilization: {{ $.Values.autoscaling.targetCPUUtilizationPercentage | int }}
+    {{- end }}
+  behavior:
+    scaleDown:
+      stabilizationWindowSeconds: 600
+      policies:
+        - type: Percent
+          value: 10
+          periodSeconds: 60
+    scaleUp:
+      stabilizationWindowSeconds: 0
+      policies:
+        - type: Pods
+          value: 1
+          periodSeconds: 30
+{{- end }}

chart/templates/infisical.yaml

@@ -0,0 +1,24 @@
+{{- if .Values.infisical.enabled }}
+apiVersion: secrets.infisical.com/v1alpha1
+kind: InfisicalSecret
+metadata:
+  name: {{ include "name" $ }}-infisical-secret
+  namespace: {{ $.Release.Namespace }}
+spec:
+  authentication:
+    universalAuth:
+      credentialsRef:
+        secretName: {{ .Values.infisical.operatorSecretName | quote }}
+        secretNamespace: {{ .Values.infisical.operatorSecretNamespace | quote }}
+      secretsScope:
+        envSlug: {{ .Values.infisical.env | quote }}
+        projectSlug: {{ .Values.infisical.project | quote }}
+        secretsPath: /
+  hostAPI: {{ .Values.infisical.url | quote }}
+  managedSecretReference:
+    creationPolicy: Owner
+    secretName: {{ include "name" $ }}-secs
+    secretNamespace: {{ .Release.Namespace | quote }}
+    secretType: Opaque
+  resyncInterval: {{ .Values.infisical.resyncInterval }}
+{{- end }}

chart/templates/ingress.yaml

@@ -0,0 +1,32 @@
+{{- if $.Values.ingress.enabled }}
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  annotations: {{ toYaml .Values.ingress.annotations | nindent 4 }}
+  labels: {{ include "labels.standard" . | nindent 4 }}
+  name: {{ include "name" . }}
+  namespace: {{ .Release.Namespace }}
+spec:
+  {{ if $.Values.ingress.className }}
+  ingressClassName: {{ .Values.ingress.className }}
+  {{ end }}
+  {{- with .Values.ingress.tls }}
+  tls:
+    - hosts:
+        - {{ $.Values.domain | quote }}
+      {{- with .secretName }}
+      secretName: {{ . }}
+      {{- end }}
+  {{- end }}
+  rules:
+    - host: {{ .Values.domain }}
+      http:
+        paths:
+          - backend:
+              service:
+                name: {{ include "name" . }}
+                port:
+                  name: http
+            path: {{ $.Values.ingress.path | default "/" }}
+            pathType: Prefix
+{{- end }}

chart/templates/network-policy.yaml

@@ -0,0 +1,36 @@
+{{- if $.Values.networkPolicy.enabled }}
+apiVersion: networking.k8s.io/v1
+kind: NetworkPolicy
+metadata:
+  name: {{ include "name" . }}
+  namespace: {{ .Release.Namespace }}
+spec:
+  egress:
+    - ports:
+        - port: 53
+          protocol: UDP
+      to:
+        - namespaceSelector:
+            matchLabels:
+              kubernetes.io/metadata.name: kube-system
+          podSelector:
+            matchLabels:
+              k8s-app: kube-dns
+    - to:
+        {{- range $ip := .Values.networkPolicy.allowedBlocks }}
+        - ipBlock:
+            cidr: {{ $ip | quote }}
+        {{- end }}
+    - to:
+        - ipBlock:
+            cidr: 0.0.0.0/0
+            except:
+              - 10.0.0.0/8
+              - 172.16.0.0/12
+              - 192.168.0.0/16
+              - 169.254.169.254/32
+  podSelector:
+    matchLabels: {{ include "labels.standard" . | nindent 6 }}
+  policyTypes:
+    - Egress
+{{- end }}

chart/templates/service-account.yaml

@@ -0,0 +1,13 @@
+{{- if and .Values.serviceAccount.enabled .Values.serviceAccount.create }}
+apiVersion: v1
+kind: ServiceAccount
+automountServiceAccountToken: {{ .Values.serviceAccount.automountServiceAccountToken }}
+metadata:
+  name: "{{ .Values.serviceAccount.name | default (include "name" .) }}"
+  namespace: {{ .Release.Namespace }}
+  labels: {{ include "labels.standard" . | nindent 4 }}
+  {{- with .Values.serviceAccount.annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+{{- end }}

chart/templates/service-monitor.yaml

@@ -0,0 +1,15 @@
+{{- if $.Values.monitoring.enabled }}
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  labels: {{ include "labels.standard" . | nindent 4 }}
+  name: {{ include "name" . }}
+  namespace: {{ .Release.Namespace }}
+spec:
+  selector:
+    matchLabels: {{ include "labels.standard" . | nindent 6 }}
+  endpoints:
+    - port: metrics
+      path: /metrics
+      interval: 15s
+{{- end }}

chart/templates/service.yaml

@@ -0,0 +1,21 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: "{{ include "name" . }}"
+  annotations: {{ toYaml .Values.service.annotations | nindent 4 }}
+  namespace: {{ .Release.Namespace }}
+  labels: {{ include "labels.standard" . | nindent 4 }}
+spec:
+  ports:
+  - name: http
+    port: 80
+    protocol: TCP
+    targetPort: http
+  {{- if $.Values.monitoring.enabled }}
+  - name: metrics
+    port: 5565
+    protocol: TCP
+    targetPort: metrics
+  {{- end }}
+  selector: {{ include "labels.standard" . | nindent 4 }}
+  type: {{.Values.service.type}}

chart/values.yaml

@@ -0,0 +1,67 @@
+image:
+  repository: ghcr.io/huggingface
+  name: chat-ui
+  tag: 0.0.0-latest
+  pullPolicy: IfNotPresent
+
+replicas: 3
+
+domain: huggingface.co
+
+networkPolicy:
+  enabled: false
+  allowedBlocks: []
+
+service:
+  type: NodePort
+  annotations: { }
+
+serviceAccount:
+  enabled: false
+  create: false
+  name: ""
+  automountServiceAccountToken: true
+  annotations: { }
+
+ingress:
+  enabled: true
+  path: "/"
+  annotations: { }
+  # className: "nginx"
+  tls: { }
+    # secretName: XXX
+
+resources:
+  requests:
+    cpu: 2
+    memory: 4Gi
+  limits:
+    cpu: 2
+    memory: 4Gi
+nodeSelector: {}
+tolerations: []
+
+envVars: { }
+
+infisical:
+  enabled: false
+  env: ""
+  project: "huggingchat-v2-a1"
+  url: ""
+  resyncInterval: 60
+  operatorSecretName: "huggingchat-operator-secrets"
+  operatorSecretNamespace: "hub-utils"
+
+# Allow to environment injections on top or instead of infisical
+extraEnvFrom: []
+extraEnv: []
+
+autoscaling:
+  enabled: false
+  minReplicas: 1
+  maxReplicas: 2
+  targetMemoryUtilizationPercentage: ""
+  targetCPUUtilizationPercentage: ""
+
+monitoring:
+  enabled: false

docs/source/_toctree.yml

@@ -0,0 +1,64 @@
+- local: index
+  title: 🤗 Chat UI
+- title: Installation
+  sections:
+    - local: installation/local
+      title: Local
+    - local: installation/spaces
+      title: Spaces
+    - local: installation/docker
+      title: Docker
+    - local: installation/helm
+      title: Helm
+- title: Configuration
+  sections:
+    - local: configuration/overview
+      title: Overview
+    - local: configuration/theming
+      title: Theming
+    - local: configuration/open-id
+      title: OpenID
+    - local: configuration/web-search
+      title: Web Search
+    - local: configuration/metrics
+      title: Metrics
+    - local: configuration/embeddings
+      title: Text Embedding Models
+    - title: Models
+      sections:
+        - local: configuration/models/overview
+          title: Overview
+        - local: configuration/models/multimodal
+          title: Multimodal
+        - local: configuration/models/tools
+          title: Tools
+        - title: Providers
+          sections:
+            - local: configuration/models/providers/anthropic
+              title: Anthropic
+            - local: configuration/models/providers/aws
+              title: AWS
+            - local: configuration/models/providers/cloudflare
+              title: Cloudflare
+            - local: configuration/models/providers/cohere
+              title: Cohere
+            - local: configuration/models/providers/google
+              title: Google
+            - local: configuration/models/providers/langserve
+              title: Langserve
+            - local: configuration/models/providers/llamacpp
+              title: Llama.cpp
+            - local: configuration/models/providers/ollama
+              title: Ollama
+            - local: configuration/models/providers/openai
+              title: OpenAI
+            - local: configuration/models/providers/tgi
+              title: TGI
+    - local: configuration/common-issues
+      title: Common Issues
+- title: Developing
+  sections:
+    - local: developing/architecture
+      title: Architecture
+    - local: developing/copy-huggingchat
+      title: Copy HuggingChat

docs/source/configuration/common-issues.md

@@ -0,0 +1,7 @@
+# Common Issues
+
+## 403：You don't have access to this conversation
+
+Most likely you are running chat-ui over HTTP. The recommended option is to setup something like NGINX to handle HTTPS and proxy the requests to chat-ui. If you really need to run over HTTP you can add `ALLOW_INSECURE_COOKIES=true` to your `.env.local`.
+
+Make sure to set your `PUBLIC_ORIGIN` in your `.env.local` to the correct URL as well.

docs/source/configuration/embeddings.md

@@ -0,0 +1,105 @@
+# Text Embedding Models
+
+By default (for backward compatibility), when `TEXT_EMBEDDING_MODELS` environment variable is not defined, [transformers.js](https://huggingface.co/docs/transformers.js) embedding models will be used for embedding tasks, specifically, the [Xenova/gte-small](https://huggingface.co/Xenova/gte-small) model.
+
+You can customize the embedding model by setting `TEXT_EMBEDDING_MODELS` in your `.env.local` file where the required fields are `name`, `chunkCharLength` and `endpoints`.
+
+Supported text embedding backends are: [`transformers.js`](https://huggingface.co/docs/transformers.js), [`TEI`](https://github.com/huggingface/text-embeddings-inference) and [`OpenAI`](https://platform.openai.com/docs/guides/embeddings). `transformers.js` models run locally as part of `chat-ui`, whereas `TEI` models run in a different environment & accessed through an API endpoint. `openai` models are accessed through the [OpenAI API](https://platform.openai.com/docs/guides/embeddings).
+
+When more than one embedding models are supplied in `.env.local` file, the first will be used by default, and the others will only be used on LLM's which configured `embeddingModel` to the name of the model.
+
+## Transformers.js
+
+The Transformers.js backend uses local CPU for the embedding which can be quite slow. If possible, consider using TEI or OpenAI embeddings instead if you use web search frequently, as performance will improve significantly.
+
+```ini
+TEXT_EMBEDDING_MODELS = `[
+  {
+    "name": "Xenova/gte-small",
+    "displayName": "Xenova/gte-small",
+    "description": "locally running embedding",
+    "chunkCharLength": 512,
+    "endpoints": [
+      { "type": "transformersjs" }
+    ]
+  }
+]`
+```
+
+## Text Embeddings Inference (TEI)
+
+> Text Embeddings Inference (TEI) is a comprehensive toolkit designed for efficient deployment and serving of open source text embeddings models. It enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE, and E5.
+
+Some recommended models at the time of writing (May 2024) are `Snowflake/snowflake-arctic-embed-m` and `BAAI/bge-large-en-v1.5`. You may run TEI locally with GPU support via Docker:
+
+`docker run --gpus all -p 8080:80 -v tei-data:/data --name tei ghcr.io/huggingface/text-embeddings-inference:1.2 --model-id YOUR/HF_MODEL`
+
+You can then hook this up to your Chat UI instance with the following configuration.
+
+```ini
+TEXT_EMBEDDING_MODELS=`[
+  {
+    "name": "YOUR/HF_MODEL",
+    "displayName": "YOUR/HF_MODEL",
+    "preQuery": "Check the model documentation for the preQuery. Not all models have one",
+    "prePassage": "Check the model documentation for the prePassage. Not all models have one",
+    "chunkCharLength": 512,
+    "endpoints": [{
+      "type": "tei",
+      "url": "http://127.0.0.1:8080/"
+    }]
+  }
+]`
+```
+
+Examples for `Snowflake/snowflake-arctic-embed-m` and `BAAI/bge-large-en-v1.5`:
+
+```ini
+TEXT_EMBEDDING_MODELS=`[
+  {
+    "name": "Snowflake/snowflake-arctic-embed-m",
+    "displayName": "Snowflake/snowflake-arctic-embed-m",
+    "preQuery": "Represent this sentence for searching relevant passages: ",
+    "chunkCharLength": 512,
+    "endpoints": [{
+      "type": "tei",
+      "url": "http://127.0.0.1:8080/"
+    }]
+  },{
+    "name": "BAAI/bge-large-en-v1.5",
+    "displayName": "BAAI/bge-large-en-v1.5",
+    "chunkCharLength": 512,
+    "endpoints": [{
+      "type": "tei",
+      "url": "http://127.0.0.1:8080/"
+    }]
+  }
+]`
+```
+
+## OpenAI
+
+It's also possible to host your own OpenAI API compatible embedding models. [`Infinity`](https://github.com/michaelfeil/infinity) is one example. You may run it locally with Docker:
+
+`docker run -it --gpus all -v infinity-data:/app/.cache -p 7997:7997 michaelf34/infinity:latest v2 --model-id nomic-ai/nomic-embed-text-v1 --port 7997`
+
+You can then hook this up to your Chat UI instance with the following configuration.
+
+```ini
+TEXT_EMBEDDING_MODELS=`[
+  {
+    "name": "nomic-ai/nomic-embed-text-v1",
+    "displayName": "nomic-ai/nomic-embed-text-v1",
+    "chunkCharLength": 512,
+    "model": {
+      "name": "nomic-ai/nomic-embed-text-v1"
+    },
+    "endpoints": [
+      {
+        "type": "openai",
+        "url": "https://127.0.0.1:7997/embeddings"
+      }
+    ]
+  }
+]`
+```

docs/source/configuration/metrics.md

@@ -0,0 +1,9 @@
+# Metrics
+
+The server can expose prometheus metrics on port `5565` but is off by default. You may enable the metrics server with `METRICS_ENABLED=true` and change the port with `METRICS_PORT=1234`.
+
+<Tip>
+
+In development with `npm run dev`, the metrics server does not shutdown gracefully due to Sveltekit not providing hooks for restart. It's recommended to disable the metrics server in this case.
+
+</Tip>

docs/source/configuration/models/multimodal.md

@@ -0,0 +1,24 @@
+# Multimodal
+
+We currently support [IDEFICS](https://huggingface.co/blog/idefics) (hosted on [TGI](./providers/tgi)), OpenAI and Anthropic Claude 3 as multimodal models. You can enable it by setting `multimodal: true` in your `MODELS` configuration. For IDEFICS, you must have a [PRO HF Api token](https://huggingface.co/settings/tokens). For OpenAI, see the [OpenAI section](./providers/openai). For Anthropic, see the [Anthropic section](./providers/anthropic).
+
+```ini
+MODELS=`[
+  {
+    "name": "HuggingFaceM4/idefics-80b-instruct",
+    "multimodal" : true,
+    "description": "IDEFICS is the new multimodal model by Hugging Face.",
+    "preprompt": "",
+    "chatPromptTemplate" : "{{#each messages}}{{#ifUser}}User: {{content}}{{/ifUser}}<end_of_utterance>\nAssistant: {{#ifAssistant}}{{content}}\n{{/ifAssistant}}{{/each}}",
+    "parameters": {
+      "temperature": 0.1,
+      "top_p": 0.95,
+      "repetition_penalty": 1.2,
+      "top_k": 12,
+      "truncate": 1000,
+      "max_new_tokens": 1024,
+      "stop": ["<end_of_utterance>", "User:", "\nUser:"]
+    }
+  }
+]`
+```

docs/source/configuration/models/overview.md

@@ -0,0 +1,147 @@
+# Models Overview
+
+You can customize the parameters passed to the model or even use a new model by updating the `MODELS` variable in your `.env.local`. The default one can be found in `.env` and looks like this :
+
+```ini
+MODELS=`[
+  {
+    "name": "mistralai/Mistral-7B-Instruct-v0.2",
+    "displayName": "mistralai/Mistral-7B-Instruct-v0.2",
+    "description": "Mistral 7B is a new Apache 2.0 model, released by Mistral AI that outperforms Llama2 13B in benchmarks.",
+    "websiteUrl": "https://mistral.ai/news/announcing-mistral-7b/",
+    "preprompt": "",
+    "chatPromptTemplate" : "<s>{{#each messages}}{{#ifUser}}[INST] {{#if @first}}{{#if @root.preprompt}}{{@root.preprompt}}\n{{/if}}{{/if}}{{content}} [/INST]{{/ifUser}}{{#ifAssistant}}{{content}}</s>{{/ifAssistant}}{{/each}}",
+    "parameters": {
+      "temperature": 0.3,
+      "top_p": 0.95,
+      "repetition_penalty": 1.2,
+      "top_k": 50,
+      "truncate": 3072,
+      "max_new_tokens": 1024,
+      "stop": ["</s>"]
+    },
+    "promptExamples": [
+      {
+        "title": "Write an email",
+        "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12)"
+      }, {
+        "title": "Code a game",
+        "prompt": "Code a basic snake game in python, give explanations for each step."
+      }, {
+        "title": "Recipe help",
+        "prompt": "How do I make a delicious lemon cheesecake?"
+      }
+    ]
+  }
+]`
+
+```
+
+You can change things like the parameters, or customize the preprompt to better suit your needs. You can also add more models by adding more objects to the array, with different preprompts for example.
+
+## Chat Prompt Template
+
+When querying the model for a chat response, the `chatPromptTemplate` template is used. `messages` is an array of chat messages, it has the format `[{ content: string }, ...]`. To identify if a message is a user message or an assistant message the `ifUser` and `ifAssistant` block helpers can be used.
+
+The following is the default `chatPromptTemplate`, although newlines and indentiation have been added for readability. You can find the prompts used in production for HuggingChat [here](https://github.com/huggingface/chat-ui/blob/main/PROMPTS.md). The templating language used is [Handlebars](https://www.npmjs.com/package/handlebars).
+
+```handlebars
+{{preprompt}}
+{{#each messages}}
+	{{#ifUser}}{{@root.userMessageToken}}{{content}}{{@root.userMessageEndToken}}{{/ifUser}}
+	{{#ifAssistant
+	}}{{@root.assistantMessageToken}}{{content}}{{@root.assistantMessageEndToken}}{{/ifAssistant}}
+{{/each}}
+{{assistantMessageToken}}
+```
+
+## Custom endpoint authorization
+
+### Basic and Bearer
+
+Custom endpoints may require authorization, depending on how you configure them. Authentication will usually be set either with `Basic` or `Bearer`.
+
+For `Basic` we will need to generate a base64 encoding of the username and password.
+
+`echo -n "USER:PASS" | base64`
+
+> VVNFUjpQQVNT
+
+For `Bearer` you can use a token, which can be grabbed from [here](https://huggingface.co/settings/tokens).
+
+You can then add the generated information and the `authorization` parameter to your `.env.local`.
+
+```ini
+"endpoints": [
+  {
+    "url": "https://HOST:PORT",
+    "authorization": "Basic VVNFUjpQQVNT",
+  }
+]
+```
+
+Please note that if `HF_TOKEN` is also set or not empty, it will take precedence.
+
+## Models hosted on multiple custom endpoints
+
+If the model being hosted will be available on multiple servers/instances add the `weight` parameter to your `.env.local`. The `weight` will be used to determine the probability of requesting a particular endpoint.
+
+```ini
+"endpoints": [
+  {
+    "url": "https://HOST:PORT",
+    "weight": 1
+  },
+  {
+    "url": "https://HOST:PORT",
+    "weight": 2
+  }
+  ...
+]
+```
+
+## Client Certificate Authentication (mTLS)
+
+Custom endpoints may require client certificate authentication, depending on how you configure them. To enable mTLS between Chat UI and your custom endpoint, you will need to set the `USE_CLIENT_CERTIFICATE` to `true`, and add the `CERT_PATH` and `KEY_PATH` parameters to your `.env.local`. These parameters should point to the location of the certificate and key files on your local machine. The certificate and key files should be in PEM format. The key file can be encrypted with a passphrase, in which case you will also need to add the `CLIENT_KEY_PASSWORD` parameter to your `.env.local`.
+
+If you're using a certificate signed by a private CA, you will also need to add the `CA_PATH` parameter to your `.env.local`. This parameter should point to the location of the CA certificate file on your local machine.
+
+If you're using a self-signed certificate, e.g. for testing or development purposes, you can set the `REJECT_UNAUTHORIZED` parameter to `false` in your `.env.local`. This will disable certificate validation, and allow Chat UI to connect to your custom endpoint.
+
+## Specific Embedding Model
+
+A model can use any of the embedding models defined under `TEXT_EMBEDDING_MODELS`, (currently used when web searching). By default it will use the first embedding model, but it can be changed with the field `embeddingModel`:
+
+```ini
+TEXT_EMBEDDING_MODELS = `[
+  {
+    "name": "Xenova/gte-small",
+    "chunkCharLength": 512,
+    "endpoints": [
+      {"type": "transformersjs"}
+    ]
+  },
+  {
+    "name": "intfloat/e5-base-v2",
+    "chunkCharLength": 768,
+    "endpoints": [
+      {"type": "tei", "url": "http://127.0.0.1:8080/", "authorization": "Basic VVNFUjpQQVNT"},
+      {"type": "tei", "url": "http://127.0.0.1:8081/"}
+    ]
+  }
+]`
+
+MODELS=`[
+  {
+      "name": "Ollama Mistral",
+      "chatPromptTemplate": "...",
+      "embeddingModel": "intfloat/e5-base-v2"
+      "parameters": {
+        ...
+      },
+      "endpoints": [
+        ...
+      ]
+  }
+]`
+```

docs/source/configuration/models/providers/anthropic.md

@@ -0,0 +1,117 @@
+# Anthropic
+
+| Feature                     | Available |
+| --------------------------- | --------- |
+| [Tools](../tools)           | No        |
+| [Multimodal](../multimodal) | Yes       |
+
+We also support Anthropic models (including multimodal ones via `multmodal: true`) through the official SDK. You may provide your API key via the `ANTHROPIC_API_KEY` env variable, or alternatively, through the `endpoints.apiKey` as per the following example.
+
+```ini
+MODELS=`[
+  {
+      "name": "claude-3-haiku-20240307",
+      "displayName": "Claude 3 Haiku",
+      "description": "Fastest and most compact model for near-instant responsiveness",
+      "multimodal": true,
+      "parameters": {
+        "max_new_tokens": 4096,
+      },
+      "endpoints": [
+        {
+          "type": "anthropic",
+          // optionals
+          "apiKey": "sk-ant-...",
+          "baseURL": "https://api.anthropic.com",
+          "defaultHeaders": {},
+          "defaultQuery": {}
+        }
+      ]
+  },
+  {
+      "name": "claude-3-sonnet-20240229",
+      "displayName": "Claude 3 Sonnet",
+      "description": "Ideal balance of intelligence and speed",
+      "multimodal": true,
+      "parameters": {
+        "max_new_tokens": 4096,
+      },
+      "endpoints": [
+        {
+          "type": "anthropic",
+          // optionals
+          "apiKey": "sk-ant-...",
+          "baseURL": "https://api.anthropic.com",
+          "defaultHeaders": {},
+          "defaultQuery": {}
+        }
+      ]
+  },
+  {
+      "name": "claude-3-opus-20240229",
+      "displayName": "Claude 3 Opus",
+      "description": "Most powerful model for highly complex tasks",
+      "multimodal": true,
+      "parameters": {
+         "max_new_tokens": 4096
+      },
+      "endpoints": [
+        {
+          "type": "anthropic",
+          // optionals
+          "apiKey": "sk-ant-...",
+          "baseURL": "https://api.anthropic.com",
+          "defaultHeaders": {},
+          "defaultQuery": {}
+        }
+      ]
+  }
+]`
+```
+
+## VertexAI
+
+We also support using Anthropic models running on Vertex AI. Authentication is done using Google Application Default Credentials. Project ID can be provided through the `endpoints.projectId` as per the following example:
+
+```ini
+MODELS=`[
+  {
+      "name": "claude-3-haiku@20240307",
+      "displayName": "Claude 3 Haiku",
+      "description": "Fastest, most compact model for near-instant responsiveness",
+      "multimodal": true,
+      "parameters": {
+         "max_new_tokens": 4096
+      },
+      "endpoints": [
+        {
+          "type": "anthropic-vertex",
+          "region": "us-central1",
+          "projectId": "gcp-project-id",
+          // optionals
+          "defaultHeaders": {},
+          "defaultQuery": {}
+        }
+      ]
+  },
+  {
+      "name": "claude-3-sonnet@20240229",
+      "displayName": "Claude 3 Sonnet",
+      "description": "Ideal balance of intelligence and speed",
+      "multimodal": true,
+      "parameters": {
+        "max_new_tokens": 4096,
+      },
+      "endpoints": [
+        {
+          "type": "anthropic-vertex",
+          "region": "us-central1",
+          "projectId": "gcp-project-id",
+          // optionals
+          "defaultHeaders": {},
+          "defaultQuery": {}
+        }
+      ]
+  },
+]`
+```

docs/source/configuration/models/providers/aws.md

@@ -0,0 +1,35 @@
+# Amazon Web Services (AWS)
+
+| Feature                     | Available |
+| --------------------------- | --------- |
+| [Tools](../tools)           | No        |
+| [Multimodal](../multimodal) | No        |
+
+You may specify your Amazon SageMaker instance as an endpoint for Chat UI:
+
+```ini
+MODELS=`[{
+  "name": "your-model",
+  "displayName": "Your Model",
+  "description": "Your description",
+  "parameters": {
+     "max_new_tokens": 4096
+  },
+  "endpoints": [
+    {
+      "type" : "aws",
+      "service" : "sagemaker"
+      "url": "",
+      "accessKey": "",
+      "secretKey" : "",
+      "sessionToken": "",
+      "region": "",
+      "weight": 1
+    }
+  ]
+}]`
+```
+
+You can also set `"service": "lambda"` to use a lambda instance.
+
+You can get the `accessKey` and `secretKey` from your AWS user, under programmatic access.

docs/source/configuration/models/providers/cloudflare.md

@@ -0,0 +1,35 @@
+# Cloudflare
+
+| Feature                     | Available |
+| --------------------------- | --------- |
+| [Tools](../tools)           | No        |
+| [Multimodal](../multimodal) | No        |
+
+You may use Cloudflare Workers AI to run your own models with serverless inference.
+
+You will need to have a Cloudflare account, then get your [account ID](https://developers.cloudflare.com/fundamentals/setup/find-account-and-zone-ids/) as well as your [API token](https://developers.cloudflare.com/workers-ai/get-started/rest-api/#1-get-an-api-token) for Workers AI.
+
+You can either specify them directly in your `.env.local` using the `CLOUDFLARE_ACCOUNT_ID` and `CLOUDFLARE_API_TOKEN` variables, or you can set them directly in the endpoint config.
+
+You can find the list of models available on Cloudflare [here](https://developers.cloudflare.com/workers-ai/models/#text-generation).
+
+```ini
+MODELS=`[
+  {
+    "name" : "nousresearch/hermes-2-pro-mistral-7b",
+    "tokenizer": "nousresearch/hermes-2-pro-mistral-7b",
+    "parameters": {
+      "stop": ["<|im_end|>"]
+    },
+    "endpoints" : [
+      {
+        "type" : "cloudflare"
+        <!-- optionally specify these
+        "accountId": "your-account-id",
+        "authToken": "your-api-token"
+        -->
+      }
+    ]
+  }
+]`
+```

docs/source/configuration/models/providers/cohere.md

@@ -0,0 +1,26 @@
+# Cohere
+
+| Feature                     | Available |
+| --------------------------- | --------- |
+| [Tools](../tools)           | Yes       |
+| [Multimodal](../multimodal) | No        |
+
+You may use Cohere to run their models directly from Chat UI. You will need to have a Cohere account, then get your [API token](https://dashboard.cohere.com/api-keys). You can either specify it directly in your `.env.local` using the `COHERE_API_TOKEN` variable, or you can set it in the endpoint config.
+
+Here is an example of a Cohere model config. You can set which model you want to use by setting the `id` field to the model name.
+
+```ini
+MODELS=`[
+  {
+    "name": "command-r-plus",
+    "displayName": "Command R+",
+    "tools": true,
+    "endpoints": [{
+      "type": "cohere",
+      <!-- optionally specify these, or use COHERE_API_TOKEN
+      "apiKey": "your-api-token"
+      -->
+    }]
+  }
+]`
+```

docs/source/configuration/models/providers/google.md

@@ -0,0 +1,92 @@
+# Google
+
+| Feature                     | Available |
+| --------------------------- | --------- |
+| [Tools](../tools)           | No        |
+| [Multimodal](../multimodal) | No        |
+
+Chat UI can connect to the google Vertex API endpoints ([List of supported models](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models)).
+
+To enable:
+
+1. [Select](https://console.cloud.google.com/project) or [create](https://cloud.google.com/resource-manager/docs/creating-managing-projects#creating_a_project) a Google Cloud project.
+1. [Enable billing for your project](https://cloud.google.com/billing/docs/how-to/modify-project).
+1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com).
+1. [Set up authentication with a service account](https://cloud.google.com/docs/authentication/getting-started)
+   so you can access the API from your local workstation.
+
+The service account credentials file can be imported as an environmental variable:
+
+```ini
+GOOGLE_APPLICATION_CREDENTIALS = clientid.json
+```
+
+Make sure your docker container has access to the file and the variable is correctly set.
+Afterwards Google Vertex endpoints can be configured as following:
+
+```ini
+MODELS=`[
+  {
+    "name": "gemini-1.5-pro",
+    "displayName": "Vertex Gemini Pro 1.5",
+    "endpoints" : [{
+      "type": "vertex",
+      "project": "abc-xyz",
+      "location": "europe-west3",
+      "extraBody": {
+         "model_version": "gemini-1.5-pro-002",
+      },
+      // Optional
+      "safetyThreshold": "BLOCK_MEDIUM_AND_ABOVE",
+      "apiEndpoint": "", // alternative api endpoint url,
+      "tools": [{
+        "googleSearchRetrieval": {
+          "disableAttribution": true
+        }
+      }]
+    }]
+  }
+]`
+```
+
+## GenAI
+
+Or use the Gemini API API provider [from](https://github.com/google-gemini/generative-ai-js#readme):
+
+Make sure that you have an API key from Google Cloud Platform. To get an API key, follow the instructions [here](https://ai.google.dev/gemini-api/docs/api-key).
+
+You can either specify them directly in your `.env.local` using the `GOOGLE_GENAI_API_KEY` variables, or you can set them directly in the endpoint config.
+
+You can find the list of models available [here](https://ai.google.dev/gemini-api/docs/models/gemini), and experimental models available [here](https://ai.google.dev/gemini-api/docs/models/experimental-models).
+
+```ini
+MODELS=`[
+  {
+    "name": "gemini-1.5-flash",
+    "displayName": "Gemini Flash 1.5",
+    "multimodal": true,
+    "endpoints": [
+      {
+        "type": "genai",
+
+        // Optional
+        "apiKey": "abc...xyz"
+        "safetyThreshold": "BLOCK_MEDIUM_AND_ABOVE",
+      }
+    ]
+  },
+  {
+    "name": "gemini-1.5-pro",
+    "displayName": "Gemini Pro 1.5",
+    "multimodal": false,
+    "endpoints": [
+      {
+        "type": "genai",
+
+        // Optional
+        "apiKey": "abc...xyz"
+      }
+    ]
+  }
+]`
+```

docs/source/configuration/models/providers/langserve.md

@@ -0,0 +1,22 @@
+# LangServe
+
+| Feature                     | Available |
+| --------------------------- | --------- |
+| [Tools](../tools)           | No        |
+| [Multimodal](../multimodal) | No        |
+
+LangChain applications that are deployed using LangServe can be called with the following config:
+
+```ini
+MODELS=`[
+  {
+    "name": "summarization-chain",
+    "displayName": "Summarization Chain"
+    "endpoints" : [{
+      "type": "langserve",
+      "url" : "http://127.0.0.1:8100",
+    }]
+  }
+]`
+
+```

docs/source/configuration/models/providers/llamacpp.md

@@ -0,0 +1,49 @@
+# Llama.cpp
+
+| Feature                     | Available |
+| --------------------------- | --------- |
+| [Tools](../tools)           | No        |
+| [Multimodal](../multimodal) | No        |
+
+Chat UI supports the llama.cpp API server directly without the need for an adapter. You can do this using the `llamacpp` endpoint type.
+
+If you want to run Chat UI with llama.cpp, you can do the following, using [microsoft/Phi-3-mini-4k-instruct-gguf](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-gguf) as an example model:
+
+```bash
+# install llama.cpp
+brew install llama.cpp
+# start llama.cpp server
+llama-server --hf-repo microsoft/Phi-3-mini-4k-instruct-gguf --hf-file Phi-3-mini-4k-instruct-q4.gguf -c 4096
+```
+
+_note: you can swap the `hf-repo` and `hf-file` with your fav GGUF on the [Hub](https://huggingface.co/models?library=gguf). For example: `--hf-repo TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF` for [this repo](https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF) & `--hf-file tinyllama-1.1b-chat-v1.0.Q4_0.gguf` for [this file](https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF/blob/main/tinyllama-1.1b-chat-v1.0.Q4_0.gguf)._
+
+A local LLaMA.cpp HTTP Server will start on `http://localhost:8080` (to change the port or any other default options, please find [LLaMA.cpp HTTP Server readme](https://github.com/ggerganov/llama.cpp/tree/master/examples/server)).
+
+Add the following to your `.env.local`:
+
+```ini
+MODELS=`[
+  {
+    "name": "Local microsoft/Phi-3-mini-4k-instruct-gguf",
+    "tokenizer": "microsoft/Phi-3-mini-4k-instruct-gguf",
+    "preprompt": "",
+    "chatPromptTemplate": "<s>{{preprompt}}{{#each messages}}{{#ifUser}}<|user|>\n{{content}}<|end|>\n<|assistant|>\n{{/ifUser}}{{#ifAssistant}}{{content}}<|end|>\n{{/ifAssistant}}{{/each}}",
+    "parameters": {
+      "stop": ["<|end|>", "<|endoftext|>", "<|assistant|>"],
+      "temperature": 0.7,
+      "max_new_tokens": 1024,
+      "truncate": 3071
+    },
+    "endpoints": [{
+      "type" : "llamacpp",
+      "baseURL": "http://localhost:8080"
+    }],
+  },
+]`
+```
+
+<div class="flex justify-center">
+<img class="block dark:hidden" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/chat-ui/llamacpp-light.png" height="auto"/>
+<img class="hidden dark:block" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/chat-ui/llamacpp-dark.png" height="auto"/>
+</div>

docs/source/configuration/models/providers/ollama.md

@@ -0,0 +1,39 @@
+# Ollama
+
+| Feature                     | Available |
+| --------------------------- | --------- |
+| [Tools](../tools)           | No        |
+| [Multimodal](../multimodal) | No        |
+
+We also support the Ollama inference server. Spin up a model with
+
+```bash
+ollama run mistral
+```
+
+Then specify the endpoints like so:
+
+```ini
+MODELS=`[
+  {
+    "name": "Ollama Mistral",
+    "chatPromptTemplate": "<s>{{#each messages}}{{#ifUser}}[INST] {{#if @first}}{{#if @root.preprompt}}{{@root.preprompt}}\n{{/if}}{{/if}} {{content}} [/INST]{{/ifUser}}{{#ifAssistant}}{{content}}</s> {{/ifAssistant}}{{/each}}",
+    "parameters": {
+      "temperature": 0.1,
+      "top_p": 0.95,
+      "repetition_penalty": 1.2,
+      "top_k": 50,
+      "truncate": 3072,
+      "max_new_tokens": 1024,
+      "stop": ["</s>"]
+    },
+    "endpoints": [
+      {
+        "type": "ollama",
+        "url" : "http://127.0.0.1:11434",
+        "ollamaName" : "mistral"
+      }
+    ]
+  }
+]`
+```

docs/source/configuration/models/providers/openai.md

@@ -0,0 +1,181 @@
+# OpenAI
+
+| Feature                     | Available |
+| --------------------------- | --------- |
+| [Tools](../tools)           | No        |
+| [Multimodal](../multimodal) | Yes       |
+
+Chat UI can be used with any API server that supports OpenAI API compatibility, for example [text-generation-webui](https://github.com/oobabooga/text-generation-webui/tree/main/extensions/openai), [LocalAI](https://github.com/go-skynet/LocalAI), [FastChat](https://github.com/lm-sys/FastChat/blob/main/docs/openai_api.md), [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), and [ialacol](https://github.com/chenhunghan/ialacol) and [vllm](https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html).
+
+The following example config makes Chat UI works with [text-generation-webui](https://github.com/oobabooga/text-generation-webui/tree/main/extensions/openai), the `endpoint.baseUrl` is the url of the OpenAI API compatible server, this overrides the baseUrl to be used by OpenAI instance. The `endpoint.completion` determine which endpoint to be used, default is `chat_completions` which uses `/chat/completions`, change to `endpoint.completion` to `completions` to use the `/completions` endpoint.
+
+```ini
+MODELS=`[
+  {
+    "name": "text-generation-webui",
+    "id": "text-generation-webui",
+    "parameters": {
+      "temperature": 0.9,
+      "top_p": 0.95,
+      "repetition_penalty": 1.2,
+      "top_k": 50,
+      "truncate": 1000,
+      "max_new_tokens": 1024,
+      "stop": []
+    },
+    "endpoints": [{
+      "type" : "openai",
+      "baseURL": "http://localhost:8000/v1"
+    }]
+  }
+]`
+
+```
+
+The `openai` type includes official OpenAI models. You can add, for example, GPT4/GPT3.5 as a "openai" model:
+
+```ini
+OPENAI_API_KEY=#your openai api key here
+MODELS=`[{
+  "name": "gpt-4",
+  "displayName": "GPT 4",
+  "endpoints" : [{
+    "type": "openai",
+    "apiKey": "or your openai api key here"
+  }]
+},{
+  "name": "gpt-3.5-turbo",
+  "displayName": "GPT 3.5 Turbo",
+  "endpoints" : [{
+    "type": "openai",
+    "apiKey": "or your openai api key here"
+  }]
+}]`
+```
+
+We also support models in the `o1` family. You need to add a few more options ot the config: Here is an example for `o1-mini`:
+
+```ini
+MODELS=`[
+  {
+      "name": "o1-mini",
+      "description": "ChatGPT o1-mini",
+      "systemRoleSupported": false,
+      "parameters": {
+        "max_new_tokens": 2048,
+      },
+      "endpoints" : [{
+        "type": "openai",
+        "useCompletionTokens": true,
+      }]
+  }
+]
+```
+
+You may also consume any model provider that provides compatible OpenAI API endpoint. For example, you may self-host [Portkey](https://github.com/Portkey-AI/gateway) gateway and experiment with Claude or GPTs offered by Azure OpenAI. Example for Claude from Anthropic:
+
+```ini
+MODELS=`[{
+  "name": "claude-2.1",
+  "displayName": "Claude 2.1",
+  "description": "Anthropic has been founded by former OpenAI researchers...",
+  "parameters": {
+    "temperature": 0.5,
+    "max_new_tokens": 4096,
+  },
+  "endpoints": [
+    {
+      "type": "openai",
+      "baseURL": "https://gateway.example.com/v1",
+      "defaultHeaders": {
+        "x-portkey-config": '{"provider":"anthropic","api_key":"sk-ant-abc...xyz"}'
+      }
+    }
+  ]
+}]`
+```
+
+Example for GPT 4 deployed on Azure OpenAI:
+
+```ini
+MODELS=`[{
+  "id": "gpt-4-1106-preview",
+  "name": "gpt-4-1106-preview",
+  "displayName": "gpt-4-1106-preview",
+  "parameters": {
+    "temperature": 0.5,
+    "max_new_tokens": 4096,
+  },
+  "endpoints": [
+    {
+      "type": "openai",
+      "baseURL": "https://{resource-name}.openai.azure.com/openai/deployments/{deployment-id}",
+      "defaultHeaders": {
+        "api-key": "{api-key}"
+      },
+      "defaultQuery": {
+        "api-version": "2023-05-15"
+      }
+    }
+  ]
+}]`
+```
+
+## DeepInfra
+
+Or try Mistral from [Deepinfra](https://deepinfra.com/mistralai/Mistral-7B-Instruct-v0.1/api?example=openai-http):
+
+> Note, apiKey can either be set custom per endpoint, or globally using `OPENAI_API_KEY` variable.
+
+```ini
+MODELS=`[{
+  "name": "mistral-7b",
+  "displayName": "Mistral 7B",
+  "description": "A 7B dense Transformer, fast-deployed and easily customisable. Small, yet powerful for a variety of use cases. Supports English and code, and a 8k context window.",
+  "parameters": {
+    "temperature": 0.5,
+    "max_new_tokens": 4096,
+  },
+  "endpoints": [
+    {
+      "type": "openai",
+      "baseURL": "https://api.deepinfra.com/v1/openai",
+      "apiKey": "abc...xyz"
+    }
+  ]
+}]`
+```
+
+_Non-streaming endpoints_
+
+For endpoints that don´t support streaming like o1 on Azure, you can pass `streamingSupported: false` in your endpoint config:
+
+```
+MODELS=`[{
+  "id": "o1-preview",
+  "name": "o1-preview",
+  "displayName": "o1-preview",
+  "systemRoleSupported": false,
+  "endpoints": [
+    {
+      "type": "openai",
+      "baseURL": "https://my-deployment.openai.azure.com/openai/deployments/o1-preview",
+      "defaultHeaders": {
+        "api-key": "$SECRET"
+      },
+      "streamingSupported": false,
+    }
+  ]
+}]`
+```
+
+## Other
+
+Some other providers and their `baseURL` for reference.
+
+[Groq](https://groq.com/): https://api.groq.com/openai/v1
+[Fireworks](https://fireworks.ai/): https://api.fireworks.ai/inference/v1
+
+```
+
+```

docs/source/configuration/models/providers/tgi.md

@@ -0,0 +1,66 @@
+# Text Generation Inference (TGI)
+
+| Feature                     | Available |
+| --------------------------- | --------- |
+| [Tools](../tools)           | Yes\*     |
+| [Multimodal](../multimodal) | Yes\*     |
+
+\* Tools are only supported with the Cohere Command R+ model with the Xenova tokenizers. Please see the [Tools](../tools) section.
+
+\* Multimodal is only supported with the IDEFICS model. Please see the [Multimodal](../multimodal) section.
+
+By default, if `endpoints` are left unspecified, Chat UI will look for the model on the hosted Hugging Face inference API using the model name, and use your `HF_TOKEN`. Refer to the [overview](../overview) for more information about model configuration.
+
+```ini
+MODELS=`[
+  {
+    "name": "mistralai/Mistral-7B-Instruct-v0.2",
+    "displayName": "mistralai/Mistral-7B-Instruct-v0.2",
+    "description": "Mistral 7B is a new Apache 2.0 model, released by Mistral AI that outperforms Llama2 13B in benchmarks.",
+    "websiteUrl": "https://mistral.ai/news/announcing-mistral-7b/",
+    "preprompt": "",
+    "chatPromptTemplate" : "<s>{{#each messages}}{{#ifUser}}[INST] {{#if @first}}{{#if @root.preprompt}}{{@root.preprompt}}\n{{/if}}{{/if}}{{content}} [/INST]{{/ifUser}}{{#ifAssistant}}{{content}}</s>{{/ifAssistant}}{{/each}}",
+    "parameters": {
+      "temperature": 0.3,
+      "top_p": 0.95,
+      "repetition_penalty": 1.2,
+      "top_k": 50,
+      "truncate": 3072,
+      "max_new_tokens": 1024,
+      "stop": ["</s>"]
+    },
+    "promptExamples": [
+      {
+        "title": "Write an email",
+        "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12)"
+      }, {
+        "title": "Code a game",
+        "prompt": "Code a basic snake game in python, give explanations for each step."
+      }, {
+        "title": "Recipe help",
+        "prompt": "How do I make a delicious lemon cheesecake?"
+      }
+    ]
+  }
+]`
+```
+
+## Running your own models using a custom endpoint
+
+If you want to, instead of hitting models on the Hugging Face Inference API, you can run your own models locally.
+
+A good option is to hit a [text-generation-inference](https://github.com/huggingface/text-generation-inference) endpoint. This is what is done in the official [Chat UI Spaces Docker template](https://huggingface.co/new-space?template=huggingchat/chat-ui-template) for instance: both this app and a text-generation-inference server run inside the same container.
+
+To do this, you can add your own endpoints to the `MODELS` variable in `.env.local`, by adding an `"endpoints"` key for each model in `MODELS`.
+
+```ini
+MODELS=`[{
+  "name": "your-model-name",
+  "displayName": "Your Model Name",
+  ... other model config
+  "endpoints": [{
+    "type" : "tgi",
+    "url": "https://HOST:PORT",
+  }]
+}]`
+```

docs/source/configuration/models/tools.md

@@ -0,0 +1,62 @@
+# Tools
+
+Tool calling instructs the model to generate an output matching a user-defined schema, which may be parsed for invoking external tools. The model simply chooses the tools and their parameters. Currently, only `TGI` and `Cohere` with `Command R+` are supported.
+
+<div class="flex justify-center">
+<img class="block dark:hidden" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/chat-ui/tools-light.png" height="auto"/>
+<img class="hidden dark:block" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/chat-ui/tools-dark.png" height="auto"/>
+</div>
+
+## TGI Configuration
+
+A custom tokenizer is required for prompting the model for generating tool calls, as well as prompting with the results. The expected format for these tools and the resulting tool calls are hard coded for TGI, so it's likely that only the following configuration will work:
+
+```ini
+MODELS=`[
+  {
+    "name" : "CohereForAI/c4ai-command-r-plus",
+    "displayName": "Command R+",
+    "description": "Command R+ is Cohere's latest LLM and is the first open weight model to beat GPT4 in the Chatbot Arena!",
+    "tools": true,
+    "tokenizer": "Xenova/c4ai-command-r-v01-tokenizer",
+    "modelUrl": "https://huggingface.co/CohereForAI/c4ai-command-r-plus",
+    "websiteUrl": "https://docs.cohere.com/docs/command-r-plus",
+    "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/cohere-logo.png",
+    "parameters": {
+      "stop": ["<|END_OF_TURN_TOKEN|>"],
+      "truncate" : 28672,
+      "max_new_tokens" : 4096,
+      "temperature" : 0.3
+    }
+  }
+]`
+```
+
+## Cohere Configuration
+
+The Cohere provider supports the endpoint native method of tool calling. Refer to the `endpoints/cohere` for implementation details.
+
+```ini
+MODELS=`[
+  {
+    "name": "command-r-plus",
+    "displayName": "Command R+",
+    "description": "Command R+ is Cohere's latest LLM and is the first open weight model to beat GPT4 in the Chatbot Arena!",
+    "tools": true,
+    "websiteUrl": "https://docs.cohere.com/docs/command-r-plus",
+    "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/cohere-logo.png",
+    "endpoints": [{
+      "type": "cohere",
+      "apiKey": "YOUR_API_KEY"
+    }]
+  }
+]`
+```
+
+## Adding Tools
+
+Tool implementations are placed in `src/lib/server/tools`, with helpers available for easy integration with HuggingFace Zero GPU spaces. In the future, there may be an OpenAPI interface for adding tools.
+
+## Adding Support for Additional Models
+
+The TGI implementation uses a custom tokenizer and hard coded schema for supporting tools. The Cohere implementation, on the other hand, uses the native support in the SDK to emit tool calls. This is the recommended way to add support for more models. Please see the `endpoints/cohere` section of the code for implementation details.

docs/source/configuration/open-id.md

@@ -0,0 +1,16 @@
+# OpenID
+
+The login feature is disabled by default and users are attributed a unique ID based on their browser. But if you want to use OpenID to authenticate your users, you can add the following to your `.env.local` file:
+
+```ini
+OPENID_CONFIG=`{
+  PROVIDER_URL: "<your OIDC issuer>",
+  CLIENT_ID: "<your OIDC client ID>",
+  CLIENT_SECRET: "<your OIDC client secret>",
+  SCOPES: "openid profile",
+  TOLERANCE: // optional
+  RESOURCE: // optional
+}`
+```
+
+Redirect URI: `/login/callback`

docs/source/configuration/overview.md

@@ -0,0 +1,10 @@
+# Configuration Overview
+
+Chat UI handles configuration with environment variables. The default config for Chat UI is stored in the `.env` file, which you may use as a reference. You will need to override some values to get Chat UI to run locally. This can be done in `.env.local` or via your environment. The bare minimum configuration to get Chat UI running is:
+
+```ini
+MONGODB_URL=mongodb://localhost:27017
+HF_TOKEN=your_token
+```
+
+The following sections detail various sections of the app you may want to configure.

docs/source/configuration/theming.md

@@ -0,0 +1,18 @@
+# Theming
+
+You can use a few environment variables to customize the look and feel of Chat UI. These are by default:
+
+```ini
+PUBLIC_APP_NAME=ChatUI
+PUBLIC_APP_ASSETS=chatui
+PUBLIC_APP_COLOR=blue
+PUBLIC_APP_DESCRIPTION="Making the community's best AI chat models available to everyone."
+PUBLIC_APP_DATA_SHARING=
+PUBLIC_APP_DISCLAIMER=
+```
+
+- `PUBLIC_APP_NAME` The name used as a title throughout the app.
+- `PUBLIC_APP_ASSETS` Is used to find logos & favicons in `static/$PUBLIC_APP_ASSETS`, current options are `chatui` and `huggingchat`.
+- `PUBLIC_APP_COLOR` Can be any of the [tailwind colors](https://tailwindcss.com/docs/customizing-colors#default-color-palette).
+- `PUBLIC_APP_DATA_SHARING` Can be set to 1 to add a toggle in the user settings that lets your users opt-in to data sharing with models creator.
+- `PUBLIC_APP_DISCLAIMER` If set to 1, we show a disclaimer about generated outputs on login.

docs/source/configuration/web-search.md

@@ -0,0 +1,58 @@
+# Web Search
+
+Chat UI features a powerful Web Search feature. A high level overview of how it works:
+
+1. Generate an appropriate search query from the user prompt using the `TASK_MODEL`
+2. Perform web search via an external provider (i.e. Serper) or via locally scrape Google results
+3. Load each search result into playwright and scrape
+4. Convert scraped HTML to Markdown tree with headings as parents
+5. Create embeddings for each Markdown element
+6. Find the embedings clossest to the user query using a vector similarity search (inner product)
+7. Get the corresponding Markdown elements and their parent, up to 8000 characters
+8. Supply the information as context to the model
+
+<div class="flex justify-center">
+<img class="block dark:hidden" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/chat-ui/websearch-light.png" height="auto"/>
+<img class="hidden dark:block" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/chat-ui/websearch-dark.png" height="auto"/>
+</div>
+
+## Providers
+
+Many providers are supported for the web search, or you can use locally scraped Google results.
+
+### Local
+
+For locally scraped Google results, put `USE_LOCAL_WEBSEARCH=true` in your `.env.local`. Please note that you may hit rate limits as we make no attempt to make the traffic look legitimate. To avoid this, you may choose a provider, such as Serper, used on the official instance.
+
+### SearXNG
+
+> SearXNG is a free internet metasearch engine which aggregates results from various search services and databases. Users are neither tracked nor profiled.
+
+You may enable support via the `SEARXNG_QUERY_URL` where `<query>` will be replaceed with the query keywords. Please see [the official documentation](https://docs.searxng.org/dev/search_api.html) for more information
+
+Example: `https://searxng.yourdomain.com/search?q=<query>&engines=duckduckgo,google&format=json`
+
+### Third Party
+
+Many third party providers are supported as well. The official instance uses Serper.
+
+```ini
+YDC_API_KEY=docs.you.com api key here
+SERPER_API_KEY=serper.dev api key here
+SERPAPI_KEY=serpapi key here
+SERPSTACK_API_KEY=serpstack api key here
+SEARCHAPI_KEY=searchapi api key here
+```
+
+## Block/Allow List
+
+You may block or allow specific websites from the web search results. When using an allow list, only the links in the allowlist will be used. For supported search engines, the links will be blocked from the results directly. Any URL in the results that **partially or fully matches** the entry will be filtered out.
+
+```ini
+WEBSEARCH_BLOCKLIST=`["youtube.com", "https://example.com/foo/bar"]`
+WEBSEARCH_ALLOWLIST=`["stackoverflow.com"]`
+```
+
+## Disabling Javascript
+
+By default, Playwright will execute all Javascript on the page. This can be intensive, requiring up to 6 cores for full performance, on some webpages. You may block scripts from running by settings `WEBSEARCH_JAVASCRIPT=false`. However, this will not block Javascript inlined in the HTML.

docs/source/developing/architecture.md

@@ -0,0 +1,35 @@
+# Architecture
+
+This document discusses the high level overview of the Chat UI codebase. If you're looking to contribute or just want to understand how the codebase works, this is the place for you!
+
+## Overview
+
+Chat UI provides a simple interface connecting LLMs to external information and tools. The project uses [MongoDB](https://www.mongodb.com/) and [SvelteKit](https://kit.svelte.dev/) with [Tailwind](https://tailwindcss.com/).
+
+## Code Map
+
+This section discusses various modules of the codebase briefly. The headings are not paths since the codebase structure may change.
+
+### `routes`
+
+Provides all of the routes rendered with SSR via SvelteKit. The majority of backend and frontend logic can be found here, with some modules being pulled out into `lib` for the client and `lib/server` for the server.
+
+### `textGeneration`
+
+Provides a standard interface for most chat features such as model output, web search, assistants and tools. Outputs `MessageUpdate`s which provide fine-grained updates on the request status such as new tokens and web search results.
+
+### `endpoints`/`embeddingEndpoints`
+
+Provides a common streaming interface for many third party LLM and embedding providers.
+
+### `websearch`
+
+Implements web search querying and RAG. See the [Web Search](../configuration/web-search) section for more information.
+
+### `tools`
+
+Provides a common interface for external tools called by LLMs. See the [Tools](../configuration/models/tools.md) section for more information
+
+### `migrations`
+
+Includes all MongoDB migrations for maintaining backwards compatibility across schema changes. Any changes to the schema must include a migration

docs/source/developing/copy-huggingchat.md

@@ -0,0 +1,71 @@
+# Copy HuggingChat
+
+The config file for HuggingChat is stored in the `chart/env/prod.yaml` file. It is the source of truth for the environment variables used for our CI/CD pipeline. For HuggingChat, as we need to customize the app color, as well as the base path, we build a custom docker image. You can find the workflow here.
+
+<Tip>
+
+If you want to make changes to the model config used in production for HuggingChat, you should do so against `chart/env/prod.yaml`.
+
+</Tip>
+
+### Running a copy of HuggingChat locally
+
+If you want to run an exact copy of HuggingChat locally, you will need to do the following first:
+
+1. Create an [OAuth App on the hub](https://huggingface.co/settings/applications/new) with `openid profile email` permissions. Make sure to set the callback URL to something like `http://localhost:5173/chat/login/callback` which matches the right path for your local instance.
+2. Create a [HF Token](https://huggingface.co/settings/tokens) with your Hugging Face account. You will need a Pro account to be able to access some of the larger models available through HuggingChat.
+3. Create a free account with [serper.dev](https://serper.dev/) (you will get 2500 free search queries)
+4. Run an instance of MongoDB, however you want. (Local or remote)
+
+You can then create a new `.env.SECRET_CONFIG` file with the following content
+
+```ini
+MONGODB_URL=<link to your mongo DB from step 4>
+HF_TOKEN=<your HF token from step 2>
+OPENID_CONFIG=`{
+  PROVIDER_URL: "https://huggingface.co",
+  CLIENT_ID: "<your client ID from step 1>",
+  CLIENT_SECRET: "<your client secret from step 1>",
+}`
+SERPER_API_KEY=<your serper API key from step 3>
+MESSAGES_BEFORE_LOGIN=<can be any numerical value, or set to 0 to require login>
+```
+
+You can then run `npm run updateLocalEnv` in the root of chat-ui. This will create a `.env.local` file which combines the `chart/env/prod.yaml` and the `.env.SECRET_CONFIG` file. You can then run `npm run dev` to start your local instance of HuggingChat.
+
+### Populate database
+
+<Tip warning={true}>
+
+The `MONGODB_URL` used for this script will be fetched from `.env.local`. Make sure it's correct! The command runs directly on the database.
+
+</Tip>
+
+You can populate the database using faker data using the `populate` script:
+
+```bash
+npm run populate <flags here>
+```
+
+At least one flag must be specified, the following flags are available:
+
+- `reset` - resets the database
+- `all` - populates all tables
+- `users` - populates the users table
+- `settings` - populates the settings table for existing users
+- `assistants` - populates the assistants table for existing users
+- `conversations` - populates the conversations table for existing users
+
+For example, you could use it like so:
+
+```bash
+npm run populate reset
+```
+
+to clear out the database. Then login in the app to create your user and run the following command:
+
+```bash
+npm run populate users settings assistants conversations
+```
+
+to populate the database with fake data, including fake conversations and assistants for your user.

docs/source/index.md

@@ -0,0 +1,97 @@
+# 🤗 Chat UI
+
+Open source chat interface with support for tools, web search, multimodal and many API providers. The app uses MongoDB and SvelteKit behind the scenes. Try the live version of the app called [HuggingChat on hf.co/chat](https://huggingface.co/chat) or [setup your own instance](./installation/spaces).
+
+🔧 **[Tools](./configuration/models/tools)**: Function calling with custom tools and support for [Zero GPU spaces](https://huggingface.co/spaces/enzostvs/zero-gpu-spaces)
+
+🔍 **[Web Search](./configuration/web-search)**: Automated web search, scraping and RAG for all models
+
+🐙 **[Multimodal](./configuration/models/multimodal)**: Accepts image file uploads on supported providers
+
+👤 **[OpenID](./configuration/open-id)**: Optionally setup OpenID for user authentication
+
+<div class="flex gap-x-4">
+
+<div>
+Tools
+<div class="flex justify-center">
+<img class="block dark:hidden" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/chat-ui/tools-light.png" height="auto"/>
+<img class="hidden dark:block" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/chat-ui/tools-dark.png" height="auto"/>
+</div>
+</div>
+
+<div>
+Web Search
+<div class="flex justify-center">
+<img class="block dark:hidden" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/chat-ui/websearch-light.png" height="auto"/>
+<img class="hidden dark:block" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/chat-ui/websearch-dark.png" height="auto"/>
+</div>
+</div>
+
+</div>
+
+## Quickstart
+
+You can quickly have a locally running chat-ui & LLM text-generation server thanks to chat-ui's [llama.cpp server support](https://huggingface.co/docs/chat-ui/configuration/models/providers/llamacpp).
+
+**Step 1 (Start llama.cpp server):**
+
+```bash
+# install llama.cpp
+brew install llama.cpp
+# start llama.cpp server (using hf.co/microsoft/Phi-3-mini-4k-instruct-gguf as an example)
+llama-server --hf-repo microsoft/Phi-3-mini-4k-instruct-gguf --hf-file Phi-3-mini-4k-instruct-q4.gguf -c 4096
+```
+
+A local LLaMA.cpp HTTP Server will start on `http://localhost:8080`. Read more [here](https://huggingface.co/docs/chat-ui/configuration/models/providers/llamacpp).
+
+**Step 2 (tell chat-ui to use local llama.cpp server):**
+
+Add the following to your `.env.local`:
+
+```ini
+MODELS=`[
+  {
+    "name": "Local microsoft/Phi-3-mini-4k-instruct-gguf",
+    "tokenizer": "microsoft/Phi-3-mini-4k-instruct-gguf",
+    "preprompt": "",
+    "chatPromptTemplate": "<s>{{preprompt}}{{#each messages}}{{#ifUser}}<|user|>\n{{content}}<|end|>\n<|assistant|>\n{{/ifUser}}{{#ifAssistant}}{{content}}<|end|>\n{{/ifAssistant}}{{/each}}",
+    "parameters": {
+      "stop": ["<|end|>", "<|endoftext|>", "<|assistant|>"],
+      "temperature": 0.7,
+      "max_new_tokens": 1024,
+      "truncate": 3071
+    },
+    "endpoints": [{
+      "type" : "llamacpp",
+      "baseURL": "http://localhost:8080"
+    }],
+  },
+]`
+```
+
+Read more [here](https://huggingface.co/docs/chat-ui/configuration/models/providers/llamacpp).
+
+**Step 3 (make sure you have MongoDb running locally):**
+
+```bash
+docker run -d -p 27017:27017 --name mongo-chatui mongo:latest
+```
+
+Read more [here](https://github.com/huggingface/chat-ui?tab=Readme-ov-file#database).
+
+**Step 4 (start chat-ui):**
+
+```bash
+git clone https://github.com/huggingface/chat-ui
+cd chat-ui
+npm install
+npm run dev -- --open
+```
+
+Read more [here](https://github.com/huggingface/chat-ui?tab=readme-ov-file#launch).
+
+<div class="flex justify-center">
+<img class="block dark:hidden" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/chat-ui/llamacpp-light.png" height="auto"/>
+<img class="hidden dark:block" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/chat-ui/llamacpp-dark.png" height="auto"/>
+</div>

docs/source/installation/docker.md

@@ -0,0 +1,11 @@
+# Running on Docker
+
+Pre-built docker images are provided with and without MongoDB built in. Refer to the [configuration section](../configuration/overview) for env variables that must be provided. We recommend using the `--env-file` option to avoid leaking secrets into your shell history.
+
+```bash
+# Without built-in DB
+docker run -p 3000:3000 --env-file .env.local --name chat-ui ghcr.io/huggingface/chat-ui
+
+# With built-in DB
+docker run -p 3000:3000 --env-file .env.local -v chat-ui:/data --name chat-ui ghcr.io/huggingface/chat-ui-db
+```

docs/source/installation/helm.md

@@ -0,0 +1,35 @@
+# Helm
+
+<Tip warning={true}>
+
+**We highly discourage using the chart**. The Helm chart is a work in progress and should be considered unstable. Breaking changes to the chart may be pushed without migration guides or notice. Contributions welcome!
+
+</Tip>
+
+For installation on Kubernetes, you may use the helm chart in `/chart`. Please note that no chart repository has been setup, so you'll need to clone the repository and install the chart by path. The production values may be found at `chart/env/prod.yaml`.
+
+**Example values.yaml**
+
+```yaml
+replicas: 1
+
+domain: example.com
+
+service:
+  type: ClusterIP
+
+resources:
+  requests:
+    cpu: 100m
+    memory: 2Gi
+  limits:
+    # Recommended to use large limits when web search is enabled
+    cpu: "4"
+    memory: 6Gi
+
+envVars:
+  MONGODB_URL: mongodb://chat-ui-mongo:27017
+  # Ensure that your values.yaml will not leak anywhere
+  # PRs welcome for a chart rework with envFrom support!
+  HF_TOKEN: secret_token
+```

docs/source/installation/local.md

@@ -0,0 +1,34 @@
+# Running Locally
+
+You may start an instance locally for non-production use cases. For production use cases, please see the other installation options.
+
+## Configuration
+
+The default config for Chat UI is stored in the `.env` file. You will need to override some values to get Chat UI to run locally. Start by creating a `.env.local` file in the root of the repository as per the [configuration section](../configuration/overview). The bare minimum config you need to get Chat UI to run locally is the following:
+
+```ini
+MONGODB_URL=<the URL to your MongoDB instance>
+HF_TOKEN=<your access token> # find your token at hf.co/settings/token
+```
+
+## Database
+
+The chat history is stored in a MongoDB instance, and having a DB instance available is needed for Chat UI to work.
+
+You can use a local MongoDB instance. The easiest way is to spin one up using docker with persistence:
+
+```bash
+docker run -d -p 27017:27017 -v mongo-chat-ui:/data --name mongo-chat-ui mongo:latest
+```
+
+In which case the url of your DB will be `MONGODB_URL=mongodb://localhost:27017`.
+
+Alternatively, you can use a [free MongoDB Atlas](https://www.mongodb.com/pricing) instance for this, Chat UI should fit comfortably within their free tier. After which you can set the `MONGODB_URL` variable in `.env.local` to match your instance.
+
+## Starting the server
+
+```bash
+npm ci # install dependencies
+npm run build # build the project
+npm run preview -- --open # start the server with & open your instance at http://localhost:4173
+```

docs/source/installation/spaces.md

@@ -0,0 +1,9 @@
+# Running on Huggingface Spaces
+
+If you don't want to configure, setup, and launch your own Chat UI yourself, you can use this option as a fast deploy alternative.
+
+You can deploy your own customized Chat UI instance with any supported [LLM](https://huggingface.co/models?pipeline_tag=text-generation) of your choice on [Hugging Face Spaces](https://huggingface.co/spaces). To do so, use the chat-ui template [available here](https://huggingface.co/new-space?template=huggingchat/chat-ui-template).
+
+Set `HF_TOKEN` in [Space secrets](https://huggingface.co/docs/hub/spaces-overview#managing-secrets-and-environment-variables) to deploy a model with gated access or a model in a private repository. It's also compatible with [Inference for PROs](https://huggingface.co/blog/inference-pro) curated list of powerful models with higher rate limits. Make sure to create your personal token first in your [User Access Tokens settings](https://huggingface.co/settings/tokens).
+
+Read the full tutorial [here](https://huggingface.co/docs/hub/spaces-sdks-docker-chatui#chatui-on-spaces).

entrypoint.sh

@@ -0,0 +1,19 @@
+ENV_LOCAL_PATH=/app/.env.local
+
+if test -z "${DOTENV_LOCAL}" ; then
+    if ! test -f "${ENV_LOCAL_PATH}" ; then
+        echo "DOTENV_LOCAL was not found in the ENV variables and .env.local is not set using a bind volume. Make sure to set environment variables properly. "
+    fi;
+else
+    echo "DOTENV_LOCAL was found in the ENV variables. Creating .env.local file."
+    cat <<< "$DOTENV_LOCAL" > ${ENV_LOCAL_PATH}
+fi;
+
+if [ "$INCLUDE_DB" = "true" ] ; then
+    echo "Starting local MongoDB instance"
+    nohup mongod &
+fi;
+
+export PUBLIC_VERSION=$(node -p "require('./package.json').version")
+
+dotenv -e /app/.env -c -- node /app/build/index.js -- --host 0.0.0.0 --port 3000

models/add-your-models-here.txt

@@ -0,0 +1 @@
+You can add .gguf files to this folder, and they will be picked up automatically by chat-ui. 

package.json

@@ -0,0 +1,132 @@
+{
+	"name": "chat-ui",
+	"version": "0.9.4",
+	"private": true,
+	"packageManager": "npm@9.5.0",
+	"scripts": {
+		"dev": "vite dev",
+		"build": "vite build",
+		"preview": "vite preview",
+		"check": "svelte-kit sync && svelte-check --tsconfig ./tsconfig.json",
+		"check:watch": "svelte-kit sync && svelte-check --tsconfig ./tsconfig.json --watch",
+		"lint": "prettier --check . && eslint .",
+		"format": "prettier --write .",
+		"test": "vitest",
+		"updateLocalEnv": "vite-node --options.transformMode.ssr='/.*/' scripts/updateLocalEnv.ts",
+		"populate": "vite-node --options.transformMode.ssr='/.*/' scripts/populate.ts",
+		"config": "vite-node --options.transformMode.ssr='/.*/' scripts/config.ts",
+		"prepare": "husky"
+	},
+	"devDependencies": {
+		"@faker-js/faker": "^8.4.1",
+		"@iconify-json/carbon": "^1.1.16",
+		"@iconify-json/eos-icons": "^1.1.6",
+		"@sveltejs/adapter-node": "^5.2.12",
+		"@sveltejs/kit": "^2.20.7",
+		"@sveltejs/vite-plugin-svelte": "^5.0.3",
+		"@tailwindcss/typography": "^0.5.9",
+		"@types/dompurify": "^3.0.5",
+		"@types/express": "^4.17.21",
+		"@types/fs-extra": "^11.0.4",
+		"@types/js-yaml": "^4.0.9",
+		"@types/jsdom": "^21.1.1",
+		"@types/jsonpath": "^0.2.4",
+		"@types/katex": "^0.16.7",
+		"@types/mime-types": "^2.1.4",
+		"@types/minimist": "^1.2.5",
+		"@types/node": "^22.1.0",
+		"@types/parquetjs": "^0.10.3",
+		"@types/sbd": "^1.0.5",
+		"@types/uuid": "^9.0.8",
+		"@typescript-eslint/eslint-plugin": "^6.x",
+		"@typescript-eslint/parser": "^6.x",
+		"dompurify": "^3.2.4",
+		"eslint": "^8.28.0",
+		"eslint-config-prettier": "^8.5.0",
+		"eslint-plugin-svelte": "^2.45.1",
+		"fs-extra": "^11.3.0",
+		"isomorphic-dompurify": "^2.13.0",
+		"js-yaml": "^4.1.0",
+		"minimist": "^1.2.8",
+		"mongodb-memory-server": "^10.1.2",
+		"node-llama-cpp": "^3.6.0",
+		"prettier": "^3.1.0",
+		"prettier-plugin-svelte": "^3.2.6",
+		"prettier-plugin-tailwindcss": "^0.6.11",
+		"prom-client": "^15.1.2",
+		"sade": "^1.8.1",
+		"svelte": "^5.27.0",
+		"svelte-check": "^4.0.0",
+		"svelte-gestures": "^5.1.3",
+		"ts-node": "^10.9.1",
+		"tslib": "^2.4.1",
+		"typescript": "^5.5.0",
+		"unplugin-icons": "^0.16.1",
+		"vite": "^6.2.6",
+		"vite-node": "^3.0.9",
+		"vitest": "^3.0.9"
+	},
+	"type": "module",
+	"dependencies": {
+		"@aws-sdk/credential-providers": "^3.592.0",
+		"@cliqz/adblocker-playwright": "^1.34.0",
+		"@gradio/client": "^1.8.0",
+		"@huggingface/hub": "^0.5.1",
+		"@huggingface/inference": "^2.8.1",
+		"@huggingface/transformers": "^3.1.1",
+		"@iconify-json/bi": "^1.1.21",
+		"@playwright/browser-chromium": "^1.43.1",
+		"@resvg/resvg-js": "^2.6.2",
+		"autoprefixer": "^10.4.14",
+		"aws-sigv4-fetch": "^4.0.1",
+		"aws4": "^1.13.0",
+		"date-fns": "^2.29.3",
+		"dotenv": "^16.5.0",
+		"express": "^4.21.2",
+		"file-type": "^19.4.1",
+		"google-auth-library": "^9.13.0",
+		"handlebars": "^4.7.8",
+		"highlight.js": "^11.7.0",
+		"husky": "^9.0.11",
+		"image-size": "^1.2.1",
+		"ip-address": "^9.0.5",
+		"jose": "^5.3.0",
+		"jsdom": "^22.0.0",
+		"json5": "^2.2.3",
+		"jsonpath": "^1.1.1",
+		"katex": "^0.16.21",
+		"lint-staged": "^15.2.7",
+		"marked": "^12.0.1",
+		"mongodb": "^5.8.0",
+		"nanoid": "^5.0.9",
+		"openid-client": "^5.4.2",
+		"parquetjs": "^0.11.2",
+		"pino": "^9.0.0",
+		"pino-pretty": "^11.0.0",
+		"playwright": "^1.52.0",
+		"postcss": "^8.4.31",
+		"saslprep": "^1.0.3",
+		"satori": "^0.10.11",
+		"satori-html": "^0.3.2",
+		"sbd": "^1.0.19",
+		"serpapi": "^1.1.1",
+		"sharp": "^0.33.4",
+		"tailwind-scrollbar": "^3.0.0",
+		"tailwindcss": "^3.4.0",
+		"uuid": "^10.0.0",
+		"zod": "^3.22.3"
+	},
+	"optionalDependencies": {
+		"@anthropic-ai/sdk": "^0.32.1",
+		"@anthropic-ai/vertex-sdk": "^0.4.1",
+		"@aws-sdk/client-bedrock-runtime": "^3.631.0",
+		"@google-cloud/vertexai": "^1.1.0",
+		"@google/generative-ai": "^0.24.0",
+		"aws4fetch": "^1.0.17",
+		"cohere-ai": "^7.9.0",
+		"openai": "^4.44.0"
+	},
+	"overrides": {
+		"@reflink/reflink": "file:stub/@reflink/reflink"
+	}
+}

scripts/config.ts

@@ -0,0 +1,64 @@
+import sade from "sade";
+
+// @ts-expect-error: vite-node makes the var available but the typescript compiler doesn't see them
+import { config, ready } from "$lib/server/config";
+
+const prog = sade("config");
+await ready;
+prog
+	.command("clear")
+	.describe("Clear all config keys")
+	.action(async () => {
+		console.log("Clearing config...");
+		await clear();
+	});
+
+prog
+	.command("add <key> <value>")
+	.describe("Add a new config key")
+	.action(async (key: string, value: string) => {
+		await add(key, value);
+	});
+
+prog
+	.command("remove <key>")
+	.describe("Remove a config key")
+	.action(async (key: string) => {
+		console.log(`Removing ${key}`);
+		await remove(key);
+		process.exit(0);
+	});
+
+prog
+	.command("help")
+	.describe("Show help information")
+	.action(() => {
+		prog.help();
+		process.exit(0);
+	});
+
+async function clear() {
+	await config.clear();
+	process.exit(0);
+}
+
+async function add(key: string, value: string) {
+	if (!key || !value) {
+		console.error("Key and value are required");
+		process.exit(1);
+	}
+	await config.set(key as keyof typeof config.keysFromEnv, value);
+	process.exit(0);
+}
+
+async function remove(key: string) {
+	if (!key) {
+		console.error("Key is required");
+		process.exit(1);
+	}
+	await config.delete(key as keyof typeof config.keysFromEnv);
+	process.exit(0);
+}
+
+// Parse arguments and handle help automatically
+prog.parse(process.argv);

scripts/populate.ts

@@ -0,0 +1,391 @@
+import readline from "readline";
+import minimist from "minimist";
+
+// @ts-expect-error: vite-node makes the var available but the typescript compiler doesn't see them
+import { env } from "$env/dynamic/private";
+
+import { faker } from "@faker-js/faker";
+import { ObjectId } from "mongodb";
+
+// @ts-expect-error: vite-node makes the var available but the typescript compiler doesn't see them
+import { ready } from "$lib/server/config";
+import { collections } from "$lib/server/database.ts";
+import { models } from "../src/lib/server/models.ts";
+import type { User } from "../src/lib/types/User";
+import type { Assistant } from "../src/lib/types/Assistant";
+import type { Conversation } from "../src/lib/types/Conversation";
+import type { Settings } from "../src/lib/types/Settings";
+import type { CommunityToolDB, ToolLogoColor, ToolLogoIcon } from "../src/lib/types/Tool";
+import { defaultEmbeddingModel } from "../src/lib/server/embeddingModels.ts";
+import { Message } from "../src/lib/types/Message.ts";
+
+import { addChildren } from "../src/lib/utils/tree/addChildren.ts";
+import { generateSearchTokens } from "../src/lib/utils/searchTokens.ts";
+import { ReviewStatus } from "../src/lib/types/Review.ts";
+import fs from "fs";
+import path from "path";
+import { MessageUpdateType } from "../src/lib/types/MessageUpdate.ts";
+import { MessageReasoningUpdateType } from "../src/lib/types/MessageUpdate.ts";
+
+const rl = readline.createInterface({
+	input: process.stdin,
+	output: process.stdout,
+});
+
+await ready;
+
+rl.on("close", function () {
+	process.exit(0);
+});
+
+const samples = fs.readFileSync(path.join(__dirname, "samples.txt"), "utf8").split("\n---\n");
+
+const possibleFlags = ["reset", "all", "users", "settings", "assistants", "conversations", "tools"];
+const argv = minimist(process.argv.slice(2));
+const flags = argv["_"].filter((flag) => possibleFlags.includes(flag));
+
+async function generateMessages(preprompt?: string): Promise<Message[]> {
+	const isLinear = faker.datatype.boolean(0.5);
+	const isInterrupted = faker.datatype.boolean(0.05);
+
+	const messages: Message[] = [];
+
+	messages.push({
+		id: crypto.randomUUID(),
+		from: "system",
+		content: preprompt ?? "",
+		createdAt: faker.date.recent({ days: 30 }),
+		updatedAt: faker.date.recent({ days: 30 }),
+	});
+
+	let isUser = true;
+	let lastId = messages[0].id;
+	if (isLinear) {
+		const convLength = faker.number.int({ min: 1, max: 25 }) * 2; // must always be even
+
+		for (let i = 0; i < convLength; i++) {
+			const hasReasoning = Math.random() < 0.2;
+			lastId = addChildren(
+				{
+					messages,
+					rootMessageId: messages[0].id,
+				},
+				{
+					from: isUser ? "user" : "assistant",
+					content:
+						faker.lorem.sentence({
+							min: 10,
+							max: isUser ? 50 : 200,
+						}) +
+						(!isUser && Math.random() < 0.1
+							? "\n```\n" + faker.helpers.arrayElement(samples) + "\n```\n"
+							: ""),
+					createdAt: faker.date.recent({ days: 30 }),
+					updatedAt: faker.date.recent({ days: 30 }),
+					reasoning: hasReasoning ? faker.lorem.paragraphs(2) : undefined,
+					updates: hasReasoning
+						? [
+								{
+									type: MessageUpdateType.Reasoning,
+									subtype: MessageReasoningUpdateType.Status,
+									uuid: crypto.randomUUID(),
+									status: "thinking",
+								},
+							]
+						: [],
+					interrupted: !isUser && i === convLength - 1 && isInterrupted,
+				},
+				lastId
+			);
+			isUser = !isUser;
+		}
+	} else {
+		const convLength = faker.number.int({ min: 2, max: 200 });
+
+		for (let i = 0; i < convLength; i++) {
+			const hasReasoning = Math.random() < 0.2;
+			addChildren(
+				{
+					messages,
+					rootMessageId: messages[0].id,
+				},
+				{
+					from: isUser ? "user" : "assistant",
+					content:
+						faker.lorem.sentence({
+							min: 10,
+							max: isUser ? 50 : 200,
+						}) +
+						(!isUser && Math.random() < 0.1
+							? "\n```\n" + faker.helpers.arrayElement(samples) + "\n```\n"
+							: ""),
+					reasoning: hasReasoning ? faker.lorem.paragraphs(2) : undefined,
+					updates: hasReasoning
+						? [
+								{
+									type: MessageUpdateType.Reasoning,
+									subtype: MessageReasoningUpdateType.Status,
+									uuid: crypto.randomUUID(),
+									status: "thinking",
+								},
+							]
+						: [],
+					createdAt: faker.date.recent({ days: 30 }),
+					updatedAt: faker.date.recent({ days: 30 }),
+					interrupted: !isUser && i === convLength - 1 && isInterrupted,
+				},
+				faker.helpers.arrayElement([
+					messages[0].id,
+					...messages.filter((m) => m.from === (isUser ? "assistant" : "user")).map((m) => m.id),
+				])
+			);
+
+			isUser = !isUser;
+		}
+	}
+	return messages;
+}
+
+async function seed() {
+	console.log("Seeding...");
+	const modelIds = models.map((model) => model.id);
+
+	if (flags.includes("reset")) {
+		console.log("Starting reset of DB");
+		await collections.users.deleteMany({});
+		await collections.settings.deleteMany({});
+		await collections.assistants.deleteMany({});
+		await collections.conversations.deleteMany({});
+		await collections.tools.deleteMany({});
+		await collections.migrationResults.deleteMany({});
+		await collections.semaphores.deleteMany({});
+		console.log("Reset done");
+	}
+
+	if (flags.includes("users") || flags.includes("all")) {
+		console.log("Creating 100 new users");
+		const newUsers: User[] = Array.from({ length: 100 }, () => ({
+			_id: new ObjectId(),
+			createdAt: faker.date.recent({ days: 30 }),
+			updatedAt: faker.date.recent({ days: 30 }),
+			username: faker.internet.userName(),
+			name: faker.person.fullName(),
+			hfUserId: faker.string.alphanumeric(24),
+			avatarUrl: faker.image.avatar(),
+		}));
+
+		await collections.users.insertMany(newUsers);
+		console.log("Done creating users.");
+	}
+
+	const users = await collections.users.find().toArray();
+	if (flags.includes("settings") || flags.includes("all")) {
+		console.log("Updating settings for all users");
+		users.forEach(async (user) => {
+			const settings: Settings = {
+				userId: user._id,
+				shareConversationsWithModelAuthors: faker.datatype.boolean(0.25),
+				hideEmojiOnSidebar: faker.datatype.boolean(0.25),
+				ethicsModalAcceptedAt: faker.date.recent({ days: 30 }),
+				activeModel: faker.helpers.arrayElement(modelIds),
+				createdAt: faker.date.recent({ days: 30 }),
+				updatedAt: faker.date.recent({ days: 30 }),
+				disableStream: faker.datatype.boolean(0.25),
+				directPaste: faker.datatype.boolean(0.25),
+				customPrompts: {},
+				assistants: [],
+			};
+			await collections.settings.updateOne(
+				{ userId: user._id },
+				{ $set: { ...settings } },
+				{ upsert: true }
+			);
+		});
+		console.log("Done updating settings.");
+	}
+
+	if (flags.includes("assistants") || flags.includes("all")) {
+		console.log("Creating assistants for all users");
+		await Promise.all(
+			users.map(async (user) => {
+				const name = faker.animal.insect();
+				const assistants = faker.helpers.multiple<Assistant>(
+					() => ({
+						_id: new ObjectId(),
+						name,
+						createdById: user._id,
+						createdByName: user.username,
+						createdAt: faker.date.recent({ days: 30 }),
+						updatedAt: faker.date.recent({ days: 30 }),
+						userCount: faker.number.int({ min: 1, max: 100000 }),
+						review: faker.helpers.enumValue(ReviewStatus),
+						modelId: faker.helpers.arrayElement(modelIds),
+						description: faker.lorem.sentence(),
+						preprompt: faker.hacker.phrase(),
+						exampleInputs: faker.helpers.multiple(() => faker.lorem.sentence(), {
+							count: faker.number.int({ min: 0, max: 4 }),
+						}),
+						searchTokens: generateSearchTokens(name),
+						last24HoursCount: faker.number.int({ min: 0, max: 1000 }),
+					}),
+					{ count: faker.number.int({ min: 3, max: 10 }) }
+				);
+				await collections.assistants.insertMany(assistants);
+				await collections.settings.updateOne(
+					{ userId: user._id },
+					{ $set: { assistants: assistants.map((a) => a._id.toString()) } },
+					{ upsert: true }
+				);
+			})
+		);
+		console.log("Done creating assistants.");
+	}
+
+	if (flags.includes("conversations") || flags.includes("all")) {
+		console.log("Creating conversations for all users");
+		await Promise.all(
+			users.map(async (user) => {
+				const conversations = faker.helpers.multiple(
+					async () => {
+						const settings = await collections.settings.findOne<Settings>({ userId: user._id });
+
+						const assistantId =
+							settings?.assistants && settings.assistants.length > 0 && faker.datatype.boolean(0.1)
+								? faker.helpers.arrayElement<ObjectId>(settings.assistants)
+								: undefined;
+
+						const preprompt =
+							(assistantId
+								? await collections.assistants
+										.findOne({ _id: assistantId })
+										.then((assistant: Assistant) => assistant?.preprompt ?? "")
+								: faker.helpers.maybe(() => faker.hacker.phrase(), { probability: 0.5 })) ?? "";
+
+						const messages = await generateMessages(preprompt);
+
+						const conv = {
+							_id: new ObjectId(),
+							userId: user._id,
+							assistantId,
+							preprompt,
+							createdAt: faker.date.recent({ days: 145 }),
+							updatedAt: faker.date.recent({ days: 145 }),
+							model: faker.helpers.arrayElement(modelIds),
+							title: faker.internet.emoji() + " " + faker.hacker.phrase(),
+							embeddingModel: defaultEmbeddingModel.id,
+							messages,
+							rootMessageId: messages[0].id,
+						} satisfies Conversation;
+
+						return conv;
+					},
+					{ count: faker.number.int({ min: 10, max: 200 }) }
+				);
+
+				await collections.conversations.insertMany(await Promise.all(conversations));
+			})
+		);
+		console.log("Done creating conversations.");
+	}
+
+	// generate Community Tools
+	if (flags.includes("tools") || flags.includes("all")) {
+		const tools = await Promise.all(
+			faker.helpers.multiple(
+				() => {
+					const _id = new ObjectId();
+					const displayName = faker.company.catchPhrase();
+					const description = faker.company.catchPhrase();
+					const color = faker.helpers.arrayElement([
+						"purple",
+						"blue",
+						"green",
+						"yellow",
+						"red",
+					]) satisfies ToolLogoColor;
+					const icon = faker.helpers.arrayElement([
+						"wikis",
+						"tools",
+						"camera",
+						"code",
+						"email",
+						"cloud",
+						"terminal",
+						"game",
+						"chat",
+						"speaker",
+						"video",
+					]) satisfies ToolLogoIcon;
+					const baseUrl = faker.helpers.arrayElement([
+						"stabilityai/stable-diffusion-3-medium",
+						"multimodalart/cosxl",
+						"gokaygokay/SD3-Long-Captioner",
+						"xichenhku/MimicBrush",
+					]);
+
+					// keep empty for populate for now
+
+					const user: User = faker.helpers.arrayElement(users);
+					const createdById = user._id;
+					const createdByName = user.username ?? user.name;
+
+					return {
+						type: "community" as const,
+						_id,
+						createdById,
+						createdByName,
+						displayName,
+						name: displayName.toLowerCase().replace(" ", "_"),
+						endpoint: "/test",
+						description,
+						color,
+						icon,
+						baseUrl,
+						inputs: [],
+						outputPath: null,
+						outputType: "str" as const,
+						showOutput: false,
+						useCount: faker.number.int({ min: 0, max: 100000 }),
+						last24HoursUseCount: faker.number.int({ min: 0, max: 1000 }),
+						createdAt: faker.date.recent({ days: 30 }),
+						updatedAt: faker.date.recent({ days: 30 }),
+						searchTokens: generateSearchTokens(displayName),
+						review: faker.helpers.enumValue(ReviewStatus),
+						outputComponent: null,
+						outputComponentIdx: null,
+					};
+				},
+				{ count: faker.number.int({ min: 10, max: 200 }) }
+			)
+		);
+
+		await collections.tools.insertMany(tools satisfies CommunityToolDB[]);
+	}
+}
+
+// run seed
+(async () => {
+	try {
+		rl.question(
+			"You're about to run a seeding script on the following MONGODB_URL: \x1b[31m" +
+				env.MONGODB_URL +
+				"\x1b[0m\n\n With the following flags: \x1b[31m" +
+				flags.join("\x1b[0m , \x1b[31m") +
+				"\x1b[0m\n \n\n Are you sure you want to continue? (yes/no): ",
+			async (confirm) => {
+				if (confirm !== "yes") {
+					console.log("Not 'yes', exiting.");
+					rl.close();
+					process.exit(0);
+				}
+				console.log("Starting seeding...");
+				await seed();
+				console.log("Seeding done.");
+				rl.close();
+			}
+		);
+	} catch (e) {
+		console.error(e);
+		process.exit(1);
+	}
+})();

scripts/samples.txt

@@ -0,0 +1,194 @@
+import { Observable, of, from, interval, throwError } from 'rxjs';
+import { map, filter, catchError, switchMap, take, tap } from 'rxjs/operators';
+
+// Mock function to fetch stock prices (simulates API call)
+const fetchStockPrice = (ticker: string): Observable<number> => {
+    return new Observable<number>((observer) => {
+        const intervalId = setInterval(() => {
+            if (Math.random() < 0.1) { // Simulating an error 10% of the time
+                observer.error(`Error fetching stock price for ${ticker}`);
+            } else {
+                const price = parseFloat((Math.random() * 1000).toFixed(2));
+                observer.next(price);
+            }
+        }, 1000);
+
+        return () => {
+            clearInterval(intervalId);
+            console.log(`Stopped fetching prices for ${ticker}`);
+        };
+    });
+};
+
+// Example usage: Tracking stock price updates
+const stockTicker = 'AAPL';
+const stockPrice$ = fetchStockPrice(stockTicker).pipe(
+    map(price => ({ ticker: stockTicker, price })),  // Transform data
+    filter(data => data.price > 500), // Only keep prices above 500
+    tap(data => console.log(`Price update:`, data)), // Side effect: Logging
+    catchError(err => {
+        console.error(err);
+        return of({ ticker: stockTicker, price: null }); // Fallback observable
+    })
+);
+
+// Subscribe to the stock price updates
+const subscription = stockPrice$.subscribe({
+    next: data => console.log(`Subscriber received:`, data),
+    error: err => console.error(`Subscription error:`, err),
+    complete: () => console.log('Stream complete'),
+});
+
+// Automatically unsubscribe after 10 seconds
+setTimeout(() => {
+    subscription.unsubscribe();
+    console.log('Unsubscribed from stock price updates.');
+}, 10000);
+---
+class EnforceAttrsMeta(type):
+    """
+    Metaclass that enforces the presence of specific attributes in a class
+    and automatically decorates methods with a logging wrapper.
+    """
+    
+    required_attributes = ['name', 'version']
+
+    def __new__(cls, name, bases, class_dict):
+        """
+        Create a new class with enforced attributes and method logging.
+
+        :param name: Name of the class being created.
+        :param bases: Tuple of base classes.
+        :param class_dict: Dictionary of attributes and methods of the class.
+        :return: Newly created class object.
+        """
+        # Ensure required attributes exist
+        for attr in cls.required_attributes:
+            if attr not in class_dict:
+                raise TypeError(f"Class '{name}' is missing required attribute '{attr}'")
+
+        # Wrap all methods in a logging decorator
+        for key, value in class_dict.items():
+            if callable(value):  # Check if it's a method
+                class_dict[key] = cls.log_calls(value)
+
+        return super().__new__(cls, name, bases, class_dict)
+
+    @staticmethod
+    def log_calls(func):
+        """
+        Decorator that logs method calls and arguments.
+
+        :param func: Function to be wrapped.
+        :return: Wrapped function with logging.
+        """
+        def wrapper(*args, **kwargs):
+            print(f"Calling {func.__name__} with args={args} kwargs={kwargs}")
+            result = func(*args, **kwargs)
+            print(f"{func.__name__} returned {result}")
+            return result
+        return wrapper
+
+
+class PluginBase(metaclass=EnforceAttrsMeta):
+    """
+    Base class for plugins that enforces required attributes and logging.
+    """
+    name = "BasePlugin"
+    version = "1.0"
+
+    def run(self, data):
+        """
+        Process the input data.
+
+        :param data: The data to be processed.
+        :return: Processed result.
+        """
+        return f"Processed {data}"
+
+
+class CustomPlugin(PluginBase):
+    """
+    Custom plugin that extends PluginBase and adheres to enforced rules.
+    """
+    name = "CustomPlugin"
+    version = "2.0"
+
+    def run(self, data):
+        """
+        Custom processing logic.
+
+        :param data: The data to process.
+        :return: Modified data.
+        """
+        return f"Custom processing of {data}"
+
+
+# Uncommenting the following class definition will raise a TypeError
+# because 'version' attribute is missing.
+# class InvalidPlugin(PluginBase):
+#     name = "InvalidPlugin"
+
+
+if __name__ == "__main__":
+    # Instantiate and use the plugin
+    plugin = CustomPlugin()
+    print(plugin.run("example data"))
+---
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Click the Box Game</title>
+    <style>
+        body {
+            text-align: center;
+            font-family: Arial, sans-serif;
+        }
+        #game-container {
+            position: relative;
+            width: 300px;
+            height: 300px;
+            margin: 20px auto;
+            border: 2px solid black;
+            overflow: hidden;
+        }
+        #target {
+            width: 50px;
+            height: 50px;
+            background-color: red;
+            position: absolute;
+            cursor: pointer;
+        }
+    </style>
+</head>
+<body>
+    <h1>Click the Box!</h1>
+    <p>Score: <span id="score">0</span></p>
+    <div id="game-container">
+        <div id="target"></div>
+    </div>
+    <script>
+        let score = 0;
+        const target = document.getElementById("target");
+        const scoreDisplay = document.getElementById("score");
+        const container = document.getElementById("game-container");
+        
+        function moveTarget() {
+            const maxX = container.clientWidth - target.clientWidth;
+            const maxY = container.clientHeight - target.clientHeight;
+            target.style.left = Math.random() * maxX + "px";
+            target.style.top = Math.random() * maxY + "px";
+        }
+        
+        target.addEventListener("click", function() {
+            score++;
+            scoreDisplay.textContent = score;
+            moveTarget();
+        });
+        
+        moveTarget();
+    </script>
+</body>
+</html>

scripts/setupTest.ts

@@ -0,0 +1,49 @@
+import { vi, afterAll } from "vitest";
+import dotenv from "dotenv";
+import { resolve } from "path";
+import fs from "fs";
+import { MongoMemoryServer } from "mongodb-memory-server";
+
+let mongoServer: MongoMemoryServer;
+// Load the .env file
+const envPath = resolve(__dirname, "../.env");
+dotenv.config({ path: envPath });
+
+// Read the .env file content
+const envContent = fs.readFileSync(envPath, "utf-8");
+
+// Parse the .env content
+const envVars = dotenv.parse(envContent);
+
+// Separate public and private variables
+const publicEnv = {};
+const privateEnv = {};
+
+for (const [key, value] of Object.entries(envVars)) {
+	if (key.startsWith("PUBLIC_")) {
+		publicEnv[key] = value;
+	} else {
+		privateEnv[key] = value;
+	}
+}
+
+vi.mock("$env/dynamic/public", () => ({
+	env: publicEnv,
+}));
+
+vi.mock("$env/dynamic/private", async () => {
+	mongoServer = await MongoMemoryServer.create();
+
+	return {
+		env: {
+			...privateEnv,
+			MONGODB_URL: mongoServer.getUri(),
+		},
+	};
+});
+
+afterAll(async () => {
+	if (mongoServer) {
+		await mongoServer.stop();
+	}
+});