config.yaml

provide_settings:
  llm:
    provider: "OpenAI"
    config:
      model: "o1-mini"
#      api_key: "sk-xxxx"  # Uncomment to override the `OPENAI_API_KEY` set in the environment variable
#      base_url: ""

#    provider: "DeepSeek"
#    config:
#      model: "deepseek-reasoner"
##      api_key: "sk-xxxx"  # Uncomment to override the `DEEPSEEK_API_KEY` set in the environment variable
##      base_url: ""

#    provider: "SiliconFlow"
#    config:
#      model: "deepseek-ai/DeepSeek-R1"
##      api_key: "xxxx"  # Uncomment to override the `SILICONFLOW_API_KEY` set in the environment variable
##      base_url: ""

#    provider: "PPIO"
#    config:
#      model: "deepseek/deepseek-r1-turbo"
##      api_key: "sk_xxxxxx"  # Uncomment to override the `PPIO_API_KEY` set in the environment variable
##      base_url: ""

#    provider: "Jiekou.AI"
#    config:
#      model: "claude-sonnet-4-5-20250929"
##      api_key: "xxxx"  # Uncomment to override the `JIEKOU_API_KEY` set in the environment variable
##      base_url: ""

#    provider: "TogetherAI"
#    config:
#      model: "deepseek-ai/DeepSeek-R1"
##      api_key: "xxxx"  # Uncomment to override the `TOGETHER_API_KEY` set in the environment variable

#    provider: "AzureOpenAI"
#    config:
#      model: ""
#      api_version: ""
##      azure_endpoint: "xxxx"  # Uncomment to override the `AZURE_OPENAI_ENDPOINT` set in the environment variable
##      api_key: "xxxx"  # Uncomment to override the `AZURE_OPENAI_KEY` set in the environment variable

#    provider: "Ollama"
#    config:
#      model: "qwq"
##      base_url: ""

#    provider: "Novita"
#    config:
#      model: "deepseek/deepseek-v3-0324"
##      api_key: "sk_xxxxxx"  # Uncomment to override the `NOVITA_API_KEY` set in the environment variable

#    provider: "LiteLLM"
#    config:
#      model: "anthropic/claude-sonnet-4-20250514"  # Any LiteLLM-supported model
##      api_key: "sk-xxxx"  # Uncomment to override the `LITELLM_API_KEY` set in the environment variable
##      api_base: "http://localhost:4000"  # Uncomment to use a LiteLLM proxy server

  embedding:
    provider: "OpenAIEmbedding"
    config:
      model: "text-embedding-ada-002"
#      api_key: ""  # Uncomment to override the `OPENAI_API_KEY` set in the environment variable
#      base_url: "" # Uncomment to override the `OPENAI_BASE_URL` set in the environment variable
#      dimension: 1536 # Uncomment to customize the embedding dimension 


#    provider: "MilvusEmbedding"
#    config:
#      model: "default"

#    provider: "VoyageEmbedding"
#    config:
#      model: "voyage-3"
##      api_key: ""  # Uncomment to override the `VOYAGE_API_KEY` set in the environment variable

#    provider: "BedrockEmbedding"
#    config:
#      model: "amazon.titan-embed-text-v2:0"
##      aws_access_key_id: ""  # Uncomment to override the `AWS_ACCESS_KEY_ID` set in the environment variable
##      aws_secret_access_key: ""  # Uncomment to override the `AWS_SECRET_ACCESS_KEY` set in the environment variable
    
#    provider: "SiliconflowEmbedding"
#    config:
#      model: "BAAI/bge-m3"
# .    api_key: ""   # Uncomment to override the `SILICONFLOW_API_KEY` set in the environment variable   

#    provider: "GeminiEmbedding"
#    config:
#      model: "text-embedding-004"
##       api_key: ""  # Uncomment to override the `GEMINI_API_KEY` set in the environment variable
##       dimension: 768 # Uncomment to customize the embedding dimension 

#    provider: "OllamaEmbedding"
#    config:
#      model: "bge-m3"
##       dimension: 1024 # Uncomment to customize the embedding dimension

#    provider: "FastEmbedEmbedding"
#    config:
#      model: "BAAI/bge-small-en-v1.5"

#    provider: "NovitaEmbedding"
#    config:
#      model: "baai/bge-m3"
##      api_key: "sk_xxxxxx"  # Uncomment to override the `NOVITA_API_KEY` set in the environment variable

    # provider: "SentenceTransformerEmbedding"
    # config:
    #   model: "BAAI/bge-large-zh-v1.5"

#    provider: "LiteLLMEmbedding"
#    config:
#      model: "text-embedding-ada-002"  # Any LiteLLM-supported embedding model
##      api_key: "sk-xxxx"  # Uncomment to override the `LITELLM_API_KEY` set in the environment variable
##      api_base: "http://localhost:4000"  # Uncomment to use a LiteLLM proxy server
##      dimension: 1536

  file_loader:
    provider: "PDFLoader"
    config: {}

#    provider: "JsonFileLoader"
#    config:
#      text_key: ""

#    provider: "TextLoader"
#    config: {}

#    provider: "UnstructuredLoader"
#    config: {}

#    provider: "DoclingLoader"
#    config: {}


  web_crawler:
    provider: "FireCrawlCrawler"
    config: {}

    # provider: "Crawl4AICrawler"
    # config: # Uncomment to custom browser configuration for Crawl4AI
    #   browser_config:
    #     headless: false
    #     proxy: "http://127.0.0.1:7890"
    #     chrome_channel: "chrome"
    #     verbose: true
    #     viewport_width: 800
    #     viewport_height: 600
    
    #    provider: "JinaCrawler"
    #    config: {}

    #    provider: "DoclingCrawler"
    #    config: {}

  vector_db:
    provider: "Milvus"
    config:
      default_collection: "deepsearcher"
      uri: "./milvus.db"
      token: "root:Milvus"
      db: "default"

  # vector_db:      
  #   provider: "OracleDB"
  #   config:
  #     default_collection: "deepsearcher"
  #     user: ""
  #     password: ""
  #     dsn: ""
  #     config_dir: ""
  #     wallet_location: ""
  #     wallet_password: ""

  # vector_db:      
  #   provider: "Qdrant"
  #   config:
  #     default_collection: "deepsearcher"
  #     host: "localhost"
  #     port: 6333

query_settings:
  max_iter: 3

load_settings:
  chunk_size: 1500
  chunk_overlap: 100