aichat/config.example.yaml

# ---- llm ----
model: openai:gpt-4o             # Specify the LLM to use
temperature: null                # Set default temperature parameter
top_p: null                      # Set default top-p parameter, range (0, 1)

# ---- behavior ----
save: true                       # Indicates whether to persist the message
keybindings: emacs               # Choose keybinding style (emacs, vi)
buffer_editor: null              # Command used to edit the current input with ctrl+o, env: EDITOR
wrap: no                         # Controls text wrapping (no, auto, <max-width>)
wrap_code: false                 # Enables or disables wrapping of code blocks

# ---- prelude ----
prelude: null                    # Set a default role or session to start with (e.g. role:<name>, session:<name>)
repl_prelude: null               # Overrides the `prelude` setting specifically for conversations started in REPL
agent_prelude: null              # Set a session to use when starting a agent. (e.g. temp, default)

# ---- session ----
# Controls the persistence of the session. if true, auto save; if false, not save; if null, asking the user
save_session: null
# Compress session when token count reaches or exceeds this threshold
compress_threshold: 4000
# Text prompt used for creating a concise summary of session message
summarize_prompt: 'Summarize the discussion briefly in 200 words or less to use as a prompt for future context.'
# Text prompt used for including the summary of the entire session
summary_prompt: 'This is a summary of the chat history as a recap: '

# ---- function-calling & agent ----
# Visit https://github.com/sigoden/llm-functions for setup instructions
function_calling: true           # Enables or disables function calling (Globally).
mapping_tools:                   # Alias for a tool or toolset
  # fs: 'fs_cat,fs_ls,fs_mkdir,fs_rm,fs_write'
use_tools: null                  # Which tools to use by default
# Per-Agent configuration
agents:
  - name: todo-sh
    model: null
    temperature: null
    top_p: null

# ---- RAG ----
rag_embedding_model: null                   # Specifies the embedding model to use
rag_reranker_model: null                    # Specifies the rerank model to use
rag_top_k: 4                                # Specifies the number of documents to retrieve
rag_chunk_size: null                        # Specifies the chunk size
rag_chunk_overlap: null                     # Specifies the chunk overlap
rag_min_score_vector_search: 0              # Specifies the minimum relevance score for vector-based searching
rag_min_score_keyword_search: 0             # Specifies the minimum relevance score for keyword-based searching
rag_min_score_rerank: 0                     # Specifies the minimum relevance score for reranking
# Defines the query structure using variables like __CONTEXT__ and __INPUT__ to tailor searches to specific needs
rag_template: |
  Use the following context as your learned knowledge, inside <context></context> XML tags.
  <context>
  __CONTEXT__
  </context>

  When answer to user:
  - If you don't know, just say that you don't know.
  - If you don't know when you are not sure, ask for clarification.
  Avoid mentioning that you obtained the information from the context.
  And answer according to the language of the user's question.

  Given the context information, answer the query.
  Query: __INPUT__

# Define document loaders to control how RAG and `.file`/`--file` load files of specific formats.
document_loaders:
  # You can add custom loaders using the following syntax:
  #   <file-extension>: <command-to-load-the-file>
  # Note: Use `$1` for input file and `$2` for output file. If `$2` is omitted, use stdout as output.
  pdf: 'pdftotext $1 -'                         # Load .pdf file, see https://poppler.freedesktop.org
  docx: 'pandoc --to plain $1'                  # Load .docx file
  # xlsx: 'ssconvert $1 $2'                     # Load .xlsx file
  # html: 'pandoc --to plain $1'                # Load .html file
  recursive_url: 'rag-crawler $1 $2'            # Load websites, see https://github.com/sigoden/rag-crawler

# ---- apperence ----
highlight: true                  # Controls syntax highlighting
light_theme: false               # Activates a light color theme when true. env: AICHAT_LIGHT_THEME
# Custom REPL prompt, see https://github.com/sigoden/aichat/wiki/Custom-REPL-Prompt for more details
left_prompt:
  '{color.green}{?session {?agent {agent}>}{session}{?role /}}{!session {?agent {agent}>}}{role}{?rag @{rag}}{color.cyan}{?session )}{!session >}{color.reset} '
right_prompt:
  '{color.purple}{?session {?consume_tokens {consume_tokens}({consume_percent}%)}{!consume_tokens {consume_tokens}}}{color.reset}'

# ---- clients ----
clients:
  # All clients have the following configuration:
  # - type: xxxx
  #   name: xxxx                                      # Only use it to distinguish clients with the same client type. Optional
  #   models:
  #     - name: xxxx                                  # Chat model
  #       max_input_tokens: 100000
  #       supports_vision: true
  #       supports_function_calling: true
  #     - name: xxxx                                  # Embedding model
  #       type: embedding
  #       max_input_tokens: 2048
  #       default_chunk_size: 1500                        
  #       max_batch_size: 100
  #     - name: xxxx                                  # Reranker model
  #       type: reranker 
  #       max_input_tokens: 2048
  #   patches: 
  #     <regex>:                                      # The regex to match model names, e.g. '.*' 'gpt-4o' 'gpt-4o|gpt-4-.*'
  #       chat_completions_body:                      # The JSON to be merged with the chat completions request body.
  #   extra:
  #     proxy: socks5://127.0.0.1:1080                # Set https/socks5 proxy. ENV: HTTPS_PROXY/https_proxy/ALL_PROXY/all_proxy
  #     connect_timeout: 10                           # Set timeout in seconds for connect to api

  # See https://platform.openai.com/docs/quickstart
  - type: openai
    api_key: sk-xxx                                   # ENV: {client}_API_KEY
    api_base: https://api.openai.com/v1               # ENV: {client}_API_BASE
    organization_id: org-xxx                          # Optional

  # For any platform compatible with OpenAI's API
  - type: openai-compatible
    name: local
    api_base: http://localhost:8080/v1                # ENV: {client}_API_BASE
    api_key: xxx                                      # ENV: {client}_API_KEY
    chat_endpoint: /chat/completions                  # Optional
    models:
      - name: llama3
        max_input_tokens: 8192

  # See https://ai.google.dev/docs
  - type: gemini
    api_key: xxx                                      # ENV: {client}_API_KEY
    patches:
      '.*':                                           
        chat_completions_body:
          safetySettings:
            - category: HARM_CATEGORY_HARASSMENT
              threshold: BLOCK_NONE
            - category: HARM_CATEGORY_HATE_SPEECH
              threshold: BLOCK_NONE
            - category: HARM_CATEGORY_SEXUALLY_EXPLICIT
              threshold: BLOCK_NONE
            - category: HARM_CATEGORY_DANGEROUS_CONTENT
              threshold: BLOCK_NONE

  # See https://docs.anthropic.com/claude/reference/getting-started-with-the-api
  - type: claude
    api_key: sk-ant-xxx                               # ENV: {client}_API_KEY

  # See https://docs.mistral.ai/
  - type: openai-compatible
    name: mistral
    api_base: https://api.mistral.ai/v1
    api_key: xxx                                      # ENV: {client}_API_KEY

  # See https://docs.cohere.com/docs/the-cohere-platform
  - type: cohere
    api_key: xxx                                      # ENV: {client}_API_KEY

  # See https://docs.perplexity.ai/docs/getting-started
  - type: openai-compatible
    name: perplexity
    api_base: https://api.perplexity.ai
    api_key: pplx-xxx                                 # ENV: {client}_API_KEY

  # See https://console.groq.com/docs/quickstart
  - type: openai-compatible
    name: groq
    api_base: https://api.groq.com/openai/v1
    api_key: gsk_xxx                                  # ENV: {client}_API_KEY

  # See https://github.com/jmorganca/ollama
  - type: ollama
    api_base: http://localhost:11434                  # ENV: {client}_API_BASE
    api_auth: Basic xxx                               # ENV: {client}_API_AUTH
    models:                                           # Required
      - name: llama3
        max_input_tokens: 8192
      - name: all-minilm:l6-v2
        type: embedding
        max_chunk_size: 1000

  # See https://learn.microsoft.com/en-us/azure/ai-services/openai/chatgpt-quickstart
  - type: azure-openai
    api_base: https://{RESOURCE}.openai.azure.com     # ENV: {client}_API_BASE
    api_key: xxx                                      # ENV: {client}_API_KEY
    models:                                           # Required
      - name: gpt-35-turbo                            # Model deployment name
        max_input_tokens: 8192

  # See https://cloud.google.com/vertex-ai
  - type: vertexai
    project_id: xxx                                   # ENV: {client}_PROJECT_ID
    location: xxx                                     # ENV: {client}_LOCATION
    # Specifies a application-default-credentials (adc) file, Optional field
    # Run `gcloud auth application-default login` to init the adc file
    # see https://cloud.google.com/docs/authentication/external/set-up-adc
    adc_file: <path-to/gcloud/application_default_credentials.json> 
    patches:
      'gemini-.*':
        chat_completions_body:
          safetySettings:
            - category: HARM_CATEGORY_HARASSMENT
              threshold: BLOCK_ONLY_HIGH
            - category: HARM_CATEGORY_HATE_SPEECH
              threshold: BLOCK_ONLY_HIGH
            - category: HARM_CATEGORY_SEXUALLY_EXPLICIT
              threshold: BLOCK_ONLY_HIGH
            - category: HARM_CATEGORY_DANGEROUS_CONTENT
              threshold: BLOCK_ONLY_HIGH

  # See https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/use-claude
  - type: vertexai-claude
    project_id: xxx                                   # ENV: {client}_PROJECT_ID
    location: xxx                                     # ENV: {client}_LOCATION
    # Specifies a application-default-credentials (adc) file, Optional field
    # Run `gcloud auth application-default login` to init the adc file
    # see https://cloud.google.com/docs/authentication/external/set-up-adc
    adc_file: <path-to/gcloud/application_default_credentials.json> 

  # See https://docs.aws.amazon.com/bedrock/latest/userguide/
  - type: bedrock
    access_key_id: xxx                                # ENV: {client}_ACCESS_KEY_ID
    secret_access_key: xxx                            # ENV: {client}_SECRET_ACCESS_KEY
    region: xxx                                       # ENV: {client}_REGION

  # See https://developers.cloudflare.com/workers-ai/
  - type: cloudflare
    account_id: xxx                                   # ENV: {client}_ACCOUNT_ID
    api_key: xxx                                      # ENV: {client}_API_KEY

  # See https://replicate.com/docs
  - type: replicate
    api_key: xxx                                      # ENV: {client}_API_KEY

  # See https://cloud.baidu.com/doc/WENXINWORKSHOP/index.html
  - type: ernie
    api_key: xxx                                      # ENV: {client}_API_KEY
    secret_key: xxxx                                  # ENV: {client}_SECRET_KEY

  # See https://help.aliyun.com/zh/dashscope/
  - type: qianwen
    api_key: sk-xxx                                   # ENV: {client}_API_KEY

  # See https://platform.moonshot.cn/docs/intro
  - type: openai-compatible
    name: moonshot
    api_base: https://api.moonshot.cn/v1
    api_key: sk-xxx                                   # ENV: {client}_API_KEY

  # See https://platform.deepseek.com/api-docs/
  - type: openai-compatible
    name: deepseek
    api_key: sk-xxx                                   # ENV: {client}_API_KEY

  # See https://open.bigmodel.cn/dev/howuse/introduction
  - type: openai-compatible
    name: zhipuai
    api_key: xxx                                      # ENV: {client}_API_KEY

  # See https://platform.lingyiwanwu.com/docs
  - type: openai-compatible
    name: lingyiwanwu
    api_key: xxx                                      # ENV: {client}_API_KEY

  # See https://deepinfra.com/docs
  - type: openai-compatible
    name: deepinfra
    api_base: https://api.deepinfra.com/v1/openai
    api_key: xxx                                      # ENV: {client}_API_KEY

  # See https://readme.fireworks.ai/docs/quickstart
  - type: openai-compatible
    name: fireworks
    api_base: https://api.fireworks.ai/inference/v1
    api_key: xxx                                      # ENV: {client}_API_KEY

  # See https://openrouter.ai/docs#quick-start
  - type: openai-compatible
    name: openrouter
    api_base: https://openrouter.ai/api/v1
    api_key: xxx                                      # ENV: {client}_API_KEY

  # See https://octo.ai/docs/getting-started/quickstart
  - type: openai-compatible
    name: octoai
    api_base: https://text.octoai.run/v1
    api_key: xxx                                      # ENV: {client}_API_KEY

  # See https://docs.together.ai/docs/quickstart
  - type: openai-compatible
    name: together
    api_base: https://api.together.xyz/v1
    api_key: xxx                                      # ENV: {client}_API_KEY

  # See https://jina.ai
  - type: rag-dedicated
    name: jina
    api_base: https://api.jina.ai/v1
    api_key: xxx                                      # ENV: {client}_API_KEY

  # See https://docs.voyageai.com/docs/introduction
  - type: rag-dedicated
    name: voyageai
    api_base: https://api.voyageai.ai/v1
    api_key: xxx                                      # ENV: {client}_API_KEY