settings.yaml

server:
  port: 8001
  cors:
    enabled: true
    allow_origins: ["*"]
    allow_methods: ["*"]
    allow_headers: ["*"]
  auth:
    enabled: false
    secret: "Basic c2VjcmV0OmtleQ=="
data:
  local_ingestion:
    enabled: false
    allow_ingest_from: ["*"]
  local_data_folder: local_data/private_gpt
ui:
  enabled: true
  path: /
  default_chat_system_prompt: >
    Você é um assistente de IA especializado em educação, agindo como um professor experiente e criativo. Sua principal função é criar aulas, planos de aula e planos de ensino detalhados para facilitar o trabalho de outros professores. Responda sempre em Português do Brasil.
  default_query_system_prompt: >
    You can only answer questions about the provided context. If you know the answer but it is not based in the provided context, don't provide the answer, just state the answer is not in the context provided.
  default_summarization_system_prompt: >
    Provide a comprehensive summary of the provided context information. The summary should cover all the key points and main ideas presented in the original text, while also condensing the information into a concise and easy-to-understand format. Please ensure that the summary includes relevant details and examples that support the main ideas, while avoiding any unnecessary information or repetition.
  delete_file_button_enabled: true
  delete_all_files_button_enabled: true
llm:
  mode: llamacpp
  prompt_style: "llama2"
  max_new_tokens: 512
  context_window: 3900
  temperature: 0.1
rag:
  similarity_top_k: 2
  rerank:
    enabled: false
    model: cross-encoder/ms-marco-MiniLM-L-2-v2
    top_n: 1
summarize:
  use_async: true
clickhouse:
    host: localhost
    port: 8443
    username: admin
    password: clickhouse
    database: embeddings
llamacpp:
  llm_hf_repo_id: "TheBloke/Mistral-7B-Instruct-v0.2-GGUF"
  llm_hf_model_file: "mistral-7b-instruct-v0.2.Q4_K_M.gguf"
embedding:
  mode: huggingface
  ingest_mode: simple
  embed_dim: 768
huggingface:
  embedding_hf_model_name: "BAAI/bge-large-en-v1.5"
  access_token: ${HF_TOKEN:}
  trust_remote_code: true
vectorstore:
  database: qdrant
nodestore:
  database: simple
milvus:
  uri: local_data/private_gpt/milvus/milvus_local.db
  collection_name: milvus_db
  overwrite: false
qdrant:
  path: local_data/private_gpt/qdrant
postgres:
  host: localhost
  port: 5432
  database: postgres
  user: postgres
  password: postgres
  schema_name: private_gpt
sagemaker:
  llm_endpoint_name: huggingface-pytorch-tgi-inference-2023-09-25-19-53-32-140
  embedding_endpoint_name: huggingface-pytorch-inference-2023-11-03-07-41-36-479
openai:
  api_key: ${OPENAI_API_KEY:}
  model: gpt-3.5-turbo
  embedding_api_key: ${OPENAI_API_KEY:}
ollama:
  llm_model: llama3.1
  embedding_model: nomic-embed-text
  api_base: http://localhost:11434
  embedding_api_base: http://localhost:11434
  keep_alive: 5m
  request_timeout: 120.0
  autopull_models: true
azopenai:
  api_key: ${AZ_OPENAI_API_KEY:}
  azure_endpoint: ${AZ_OPENAI_ENDPOINT:}
  embedding_deployment_name: ${AZ_OPENAI_EMBEDDING_DEPLOYMENT_NAME:}
  llm_deployment_name: ${AZ_OPENAI_LLM_DEPLOYMENT_NAME:}
  api_version: "2023-05-15"
  embedding_model: text-embedding-ada-002
  llm_model: gpt-35-turbo
gemini:
  api_key: ${GOOGLE_API_KEY:}
  model: models/gemini-pro
  embedding_model: models/embedding-001