Spaces:

Arif-Badhon
/

Generative_AI_Project

Sleeping

App Files Files Community

Arif commited on Oct 28, 2025

Commit

9a62b2a

1 Parent(s): 704b133

Huggingface upload

Browse files

Files changed (4) hide show

Dockerfile +12 -0
app.py +12 -0
app/static/index.html +70 -0
requirements.txt +519 -0

Dockerfile ADDED Viewed

	@@ -0,0 +1,12 @@

+FROM python:3.10-slim
+WORKDIR /code
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+COPY . .
+EXPOSE 7860
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py ADDED Viewed

	@@ -0,0 +1,12 @@

+from fastapi import FastAPI
+from fastapi.staticfiles import StaticFiles
+from app.main import app as backend_app
+main_app = FastAPI()
+# Backend API at /api
+main_app.mount("/api", backend_app)
+# Frontend served at /
+main_app.mount("/", StaticFiles(directory="static", html=True), name="static")
+app = main_app  # Hugging Face expects this variable

app/static/index.html ADDED Viewed

	@@ -0,0 +1,70 @@

+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <title>RAG Portfolio Project Q&A</title>
+    <meta name="viewport" content="width=device-width, initial-scale=1">
+    <style>
+        body { margin:0; font-family:system-ui,sans-serif; background: #f6f8fc; }
+        .container { max-width: 500px; margin:40px auto; background:#fff; border-radius:18px; padding:36px 28px 30px 28px; box-shadow:0 8px 36px #0001;}
+        h1 { color:#466bb7; font-size:2rem; margin-bottom: 8px;}
+        .subtitle { color: #686868; margin-bottom:20px; font-size:1.05rem;}
+        textarea { width:100%; min-height:70px; font-size:1rem; border-radius:7px; border:1.5px solid #dbeafe; padding:10px;}
+        button { margin:10px 0 0 0; padding:12px 24px; border:none; border-radius:8px; background:#466bb7; color:#fff; font-size:1.08em; font-weight:500; cursor:pointer;}
+        #answer { background:#f3f4fa; border-left:5px solid #466bb7; margin-top:24px; padding:19px; border-radius:8px 7px 7px 8px;}
+        .source { font-size:0.92em; color:#666; margin-top:7px; }
+        #loading { margin:20px 0; color: #466bb7; font-weight: bold;}
+        #error { color: #d00; margin: 12px 0;}
+        footer { margin:32px auto 0; max-width:500px; font-size:0.92em; text-align:center; color:#aaa; }
+        @media (max-width:600px) {.container {padding:18px 5vw 20px 5vw;} }
+    </style>
+</head>
+<body>
+    <div class="container">
+        <h1>RAG Demo: Document Q&A</h1>
+        <div class="subtitle">Ask any question about your uploaded documents.</div>
+        <form id="form">
+            <textarea id="question" placeholder="E.g. What is deep learning?" required maxlength="300"></textarea>
+            <button type="submit">Ask AI</button>
+        </form>
+        <div id="loading" style="display:none;">Thinking...</div>
+        <div id="error"></div>
+        <div id="answer"></div>
+    </div>
+    <footer>
+    <b>Open-source RAG Portfolio Project</b> &nbsp;|&nbsp; <a href="https://github.com/YOUR_USERNAME/rag-portfolio-project" target="_blank">GitHub</a>
+    </footer>
+    <script>
+        // CHANGE THIS to your API endpoint (must be public, e.g., https://your-space-name.hf.space/query or deployed backend URL)
+        const API_URL = "/api/query";
+        const form = document.getElementById("form");
+        form.onsubmit = async (e) => {
+            e.preventDefault();
+            document.getElementById("error").textContent = "";
+            document.getElementById("answer").innerHTML = "";
+            document.getElementById("loading").style.display = "block";
+            const q = document.getElementById("question").value.trim();
+            if (!q) return;
+            let r, data;
+            try {
+                r = await fetch(API_URL, {
+                    method: "POST",
+                    headers: {"Content-Type": "application/json"},
+                    body: JSON.stringify({question: q, top_k: 5}),
+                });
+                data = await r.json();
+                document.getElementById("loading").style.display = "none";
+                if (!r.ok) throw new Error("Server error: " + (data?.detail || r.status));
+            } catch (err) {
+                document.getElementById("loading").style.display = "none";
+                document.getElementById("error").textContent = "Error: " + (err.message || "backend unavailable");
+                return;
+            }
+            document.getElementById("answer").innerHTML =
+                `<b>Answer:</b><br>${data.answer || "No answer."}<br>` +
+                (data.sources && data.sources.length ?
+                  data.sources.map((s,i)=>`<div class="source">Source ${i+1}: ${s.source} (chunk ${s.chunk_index}, relevance: ${Math.round(s.score*100)}%)</div>`).join('') : '');
+        };
+    </script>
+</body>
+</html>

requirements.txt ADDED Viewed

	@@ -0,0 +1,519 @@

+# This file was autogenerated by uv via the following command:
+#    uv pip compile --output-file requirements.txt pyproject.toml
+aiofiles==25.1.0
+    # via unstructured-client
+aiohappyeyeballs==2.6.1
+    # via aiohttp
+aiohttp==3.13.1
+    # via
+    #   fsspec
+    #   instructor
+    #   langchain-community
+aiosignal==1.4.0
+    # via aiohttp
+annotated-doc==0.0.3
+    # via fastapi
+annotated-types==0.7.0
+    # via pydantic
+anyio==4.11.0
+    # via
+    #   httpx
+    #   openai
+    #   starlette
+appdirs==1.4.4
+    # via ragas
+async-timeout==4.0.3
+    # via
+    #   aiohttp
+    #   langchain-classic
+attrs==25.4.0
+    # via aiohttp
+backoff==2.2.1
+    # via unstructured
+beautifulsoup4==4.14.2
+    # via unstructured
+certifi==2025.10.5
+    # via
+    #   httpcore
+    #   httpx
+    #   requests
+cffi==2.0.0
+    # via cryptography
+cfgv==3.4.0
+    # via pre-commit
+charset-normalizer==3.4.4
+    # via
+    #   requests
+    #   unstructured
+click==8.3.0
+    # via
+    #   nltk
+    #   python-oxmsg
+    #   typer
+    #   uvicorn
+cryptography==46.0.3
+    # via unstructured-client
+dataclasses-json==0.6.7
+    # via
+    #   langchain-community
+    #   unstructured
+datasets==4.3.0
+    # via ragas
+dill==0.4.0
+    # via
+    #   datasets
+    #   multiprocess
+diskcache==5.6.3
+    # via
+    #   instructor
+    #   ragas
+distlib==0.4.0
+    # via virtualenv
+distro==1.9.0
+    # via openai
+docstring-parser==0.17.0
+    # via instructor
+emoji==2.15.0
+    # via unstructured
+exceptiongroup==1.3.0
+    # via anyio
+fastapi==0.120.1
+    # via generative-ai-portfolio-project (pyproject.toml)
+filelock==3.20.0
+    # via
+    #   datasets
+    #   huggingface-hub
+    #   torch
+    #   transformers
+    #   virtualenv
+filetype==1.2.0
+    # via unstructured
+frozenlist==1.8.0
+    # via
+    #   aiohttp
+    #   aiosignal
+fsspec==2025.9.0
+    # via
+    #   datasets
+    #   huggingface-hub
+    #   torch
+gitdb==4.0.12
+    # via gitpython
+gitpython==3.1.45
+    # via ragas
+grpcio==1.76.0
+    # via qdrant-client
+h11==0.16.0
+    # via
+    #   httpcore
+    #   uvicorn
+h2==4.3.0
+    # via httpx
+hf-xet==1.2.0
+    # via huggingface-hub
+hpack==4.1.0
+    # via h2
+html5lib==1.1
+    # via unstructured
+httpcore==1.0.9
+    # via
+    #   httpx
+    #   unstructured-client
+httpx==0.28.1
+    # via
+    #   datasets
+    #   langgraph-sdk
+    #   langsmith
+    #   ollama
+    #   openai
+    #   qdrant-client
+    #   unstructured-client
+httpx-sse==0.4.3
+    # via langchain-community
+huggingface-hub==0.36.0
+    # via
+    #   datasets
+    #   sentence-transformers
+    #   tokenizers
+    #   transformers
+hyperframe==6.1.0
+    # via h2
+identify==2.6.15
+    # via pre-commit
+idna==3.11
+    # via
+    #   anyio
+    #   httpx
+    #   requests
+    #   yarl
+instructor==1.12.0
+    # via ragas
+jinja2==3.1.6
+    # via
+    #   instructor
+    #   torch
+jiter==0.10.0
+    # via
+    #   instructor
+    #   openai
+joblib==1.5.2
+    # via
+    #   nltk
+    #   scikit-learn
+jsonpatch==1.33
+    # via langchain-core
+jsonpointer==3.0.0
+    # via jsonpatch
+langchain==1.0.2
+    # via
+    #   generative-ai-portfolio-project (pyproject.toml)
+    #   ragas
+langchain-classic==1.0.0
+    # via langchain-community
+langchain-community==0.4.1
+    # via
+    #   generative-ai-portfolio-project (pyproject.toml)
+    #   ragas
+langchain-core==1.0.1
+    # via
+    #   langchain
+    #   langchain-classic
+    #   langchain-community
+    #   langchain-ollama
+    #   langchain-openai
+    #   langchain-text-splitters
+    #   langgraph
+    #   langgraph-checkpoint
+    #   langgraph-prebuilt
+    #   ragas
+langchain-ollama==1.0.0
+    # via generative-ai-portfolio-project (pyproject.toml)
+langchain-openai==1.0.1
+    # via ragas
+langchain-text-splitters==1.0.0
+    # via
+    #   generative-ai-portfolio-project (pyproject.toml)
+    #   langchain-classic
+langdetect==1.0.9
+    # via unstructured
+langgraph==1.0.1
+    # via langchain
+langgraph-checkpoint==3.0.0
+    # via
+    #   langgraph
+    #   langgraph-prebuilt
+langgraph-prebuilt==1.0.1
+    # via langgraph
+langgraph-sdk==0.2.9
+    # via langgraph
+langsmith==0.4.38
+    # via
+    #   langchain-classic
+    #   langchain-community
+    #   langchain-core
+lxml==6.0.2
+    # via
+    #   python-docx
+    #   unstructured
+markdown-it-py==4.0.0
+    # via rich
+markupsafe==3.0.3
+    # via jinja2
+marshmallow==3.26.1
+    # via dataclasses-json
+mdurl==0.1.2
+    # via markdown-it-py
+mpmath==1.3.0
+    # via sympy
+multidict==6.7.0
+    # via
+    #   aiohttp
+    #   yarl
+multiprocess==0.70.16
+    # via datasets
+mypy-extensions==1.1.0
+    # via typing-inspect
+nest-asyncio==1.6.0
+    # via ragas
+networkx==3.4.2
+    # via
+    #   ragas
+    #   torch
+nltk==3.9.2
+    # via unstructured
+nodeenv==1.9.1
+    # via pre-commit
+numpy==2.2.6
+    # via
+    #   datasets
+    #   langchain-community
+    #   pandas
+    #   qdrant-client
+    #   ragas
+    #   rank-bm25
+    #   scikit-learn
+    #   scikit-network
+    #   scipy
+    #   transformers
+    #   unstructured
+olefile==0.47
+    # via python-oxmsg
+ollama==0.6.0
+    # via langchain-ollama
+openai==1.109.1
+    # via
+    #   instructor
+    #   langchain-openai
+    #   ragas
+orjson==3.11.4
+    # via
+    #   langgraph-sdk
+    #   langsmith
+ormsgpack==1.11.0
+    # via langgraph-checkpoint
+packaging==25.0
+    # via
+    #   datasets
+    #   huggingface-hub
+    #   langchain-core
+    #   langsmith
+    #   marshmallow
+    #   transformers
+pandas==2.3.3
+    # via datasets
+pillow==12.0.0
+    # via
+    #   ragas
+    #   sentence-transformers
+platformdirs==4.5.0
+    # via virtualenv
+portalocker==3.2.0
+    # via qdrant-client
+pre-commit==4.3.0
+    # via instructor
+propcache==0.4.1
+    # via
+    #   aiohttp
+    #   yarl
+protobuf==6.33.0
+    # via qdrant-client
+psutil==7.1.2
+    # via unstructured
+pyarrow==22.0.0
+    # via datasets
+pycparser==2.23
+    # via cffi
+pydantic==2.12.3
+    # via
+    #   fastapi
+    #   instructor
+    #   langchain
+    #   langchain-classic
+    #   langchain-core
+    #   langgraph
+    #   langsmith
+    #   ollama
+    #   openai
+    #   pydantic-settings
+    #   qdrant-client
+    #   ragas
+    #   unstructured-client
+pydantic-core==2.41.4
+    # via
+    #   instructor
+    #   pydantic
+pydantic-settings==2.11.0
+    # via langchain-community
+pygments==2.19.2
+    # via rich
+pypdf==6.1.3
+    # via
+    #   generative-ai-portfolio-project (pyproject.toml)
+    #   unstructured-client
+python-dateutil==2.9.0.post0
+    # via pandas
+python-docx==1.2.0
+    # via generative-ai-portfolio-project (pyproject.toml)
+python-dotenv==1.2.1
+    # via pydantic-settings
+python-iso639==2025.2.18
+    # via unstructured
+python-magic==0.4.27
+    # via unstructured
+python-multipart==0.0.20
+    # via generative-ai-portfolio-project (pyproject.toml)
+python-oxmsg==0.0.2
+    # via unstructured
+pytz==2025.2
+    # via pandas
+pyyaml==6.0.3
+    # via
+    #   datasets
+    #   huggingface-hub
+    #   langchain-classic
+    #   langchain-community
+    #   langchain-core
+    #   pre-commit
+    #   transformers
+qdrant-client==1.15.1
+    # via generative-ai-portfolio-project (pyproject.toml)
+ragas==0.3.7
+    # via generative-ai-portfolio-project (pyproject.toml)
+rank-bm25==0.2.2
+    # via generative-ai-portfolio-project (pyproject.toml)
+rapidfuzz==3.14.1
+    # via unstructured
+regex==2025.10.23
+    # via
+    #   nltk
+    #   tiktoken
+    #   transformers
+requests==2.32.5
+    # via
+    #   generative-ai-portfolio-project (pyproject.toml)
+    #   datasets
+    #   huggingface-hub
+    #   instructor
+    #   langchain-classic
+    #   langchain-community
+    #   langsmith
+    #   requests-toolbelt
+    #   tiktoken
+    #   transformers
+    #   unstructured
+requests-toolbelt==1.0.0
+    # via
+    #   langsmith
+    #   unstructured-client
+rich==14.2.0
+    # via
+    #   instructor
+    #   ragas
+    #   typer
+safetensors==0.6.2
+    # via transformers
+scikit-learn==1.7.2
+    # via sentence-transformers
+scikit-network==0.33.3
+    # via ragas
+scipy==1.15.3
+    # via
+    #   scikit-learn
+    #   scikit-network
+    #   sentence-transformers
+sentence-transformers==5.1.2
+    # via generative-ai-portfolio-project (pyproject.toml)
+shellingham==1.5.4
+    # via typer
+six==1.17.0
+    # via
+    #   html5lib
+    #   langdetect
+    #   python-dateutil
+smmap==5.0.2
+    # via gitdb
+sniffio==1.3.1
+    # via
+    #   anyio
+    #   openai
+soupsieve==2.8
+    # via beautifulsoup4
+sqlalchemy==2.0.44
+    # via
+    #   langchain-classic
+    #   langchain-community
+starlette==0.48.0
+    # via fastapi
+sympy==1.14.0
+    # via torch
+tenacity==9.1.2
+    # via
+    #   instructor
+    #   langchain-community
+    #   langchain-core
+threadpoolctl==3.6.0
+    # via scikit-learn
+tiktoken==0.12.0
+    # via
+    #   langchain-openai
+    #   ragas
+tokenizers==0.22.1
+    # via transformers
+torch==2.9.0
+    # via sentence-transformers
+tqdm==4.67.1
+    # via
+    #   datasets
+    #   huggingface-hub
+    #   nltk
+    #   openai
+    #   ragas
+    #   sentence-transformers
+    #   transformers
+    #   unstructured
+transformers==4.57.1
+    # via sentence-transformers
+typer==0.20.0
+    # via
+    #   instructor
+    #   ragas
+typing-extensions==4.15.0
+    # via
+    #   aiosignal
+    #   anyio
+    #   beautifulsoup4
+    #   cryptography
+    #   exceptiongroup
+    #   fastapi
+    #   grpcio
+    #   huggingface-hub
+    #   langchain-core
+    #   multidict
+    #   openai
+    #   pydantic
+    #   pydantic-core
+    #   pypdf
+    #   python-docx
+    #   python-oxmsg
+    #   sentence-transformers
+    #   sqlalchemy
+    #   starlette
+    #   torch
+    #   typer
+    #   typing-inspect
+    #   typing-inspection
+    #   unstructured
+    #   uvicorn
+    #   virtualenv
+typing-inspect==0.9.0
+    # via dataclasses-json
+typing-inspection==0.4.2
+    # via
+    #   pydantic
+    #   pydantic-settings
+tzdata==2025.2
+    # via pandas
+unstructured==0.18.15
+    # via generative-ai-portfolio-project (pyproject.toml)
+unstructured-client==0.42.3
+    # via unstructured
+urllib3==2.5.0
+    # via
+    #   qdrant-client
+    #   requests
+uvicorn==0.38.0
+    # via generative-ai-portfolio-project (pyproject.toml)
+virtualenv==20.35.3
+    # via pre-commit
+webencodings==0.5.1
+    # via html5lib
+wrapt==2.0.0
+    # via unstructured
+xxhash==3.6.0
+    # via
+    #   datasets
+    #   langgraph
+yarl==1.22.0
+    # via aiohttp
+zstandard==0.25.0
+    # via langsmith