config.yaml

provide_settings:
  llm:
    provider: "OpenAI"
    config:
      model: "gpt-4o-mini"  # "gpt-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-chat"  # "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-V3"
##      api_key: "xxxx"  # Uncomment to override the `SILICONFLOW_API_KEY` set in the environment variable
##      base_url: ""

#    provider: "TogetherAI"
#    config:
#      model: "deepseek-ai/DeepSeek-V3"
##      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

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


#    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   

  file_loader:
    provider: "PDFLoader"
    config: {}

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

#    provider: "TextLoader"
#    config: {}

#    provider: "UnstructuredLoader"
#    config: {}

  web_crawler:
    provider: "FireCrawlCrawler"
    config: {}

#    provider: "Crawl4AICrawler"
#    config: {}

#    provider: "JinaCrawler"
#    config: {}

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

query_settings:
  max_iter: 3

load_settings:
  chunk_size: 1500
  chunk_overlap: 100