model: openai:gpt-3.5-turbo # Specify the language model to use temperature: null # Set default temperature parameter top_p: null # Set default top-p parameter save: true # Indicates whether to persist the message save_session: null # Controls the persistence of the session, if null, asking the user highlight: true # Controls syntax highlighting light_theme: false # Activates a light color theme when true. ENV: AICHAT_LIGHT_THEME wrap: no # Controls text wrapping (no, auto, ) wrap_code: false # Enables or disables wrapping of code blocks auto_copy: false # Enables or disables automatic copying the last LLM response to the clipboard keybindings: emacs # Choose keybinding style (emacs, vi) prelude: null # Set a default role or session to start with (role:, session:) # Command that will be used to edit the current line buffer with ctrl+o # if unset fallback to $EDITOR and $VISUAL buffer_editor: null # Compress session when token count reaches or exceeds this threshold (must be at least 1000) compress_threshold: 1000 # 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: ' # Custom REPL prompt, see https://github.com/sigoden/aichat/wiki/Custom-REPL-Prompt left_prompt: '{color.green}{?session {session}{?role /}}{role}{color.cyan}{?session )}{!session >}{color.reset} ' right_prompt: '{color.purple}{?session {?consume_tokens {consume_tokens}({consume_percent}%)}{!consume_tokens {consume_tokens}}}{color.reset}' 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 # The model name # max_input_tokens: 100000 # max_output_tokens: 4096 # supports_vision: true # extra_fields: # Set custom parameters, will merge with the body json # key: value # extra: # proxy: socks5://127.0.0.1:1080 # Specify https/socks5 proxy server. ENV: HTTPS_PROXY/ALL_PROXY # connect_timeout: 10 # Set a timeout in seconds for connect to server # See https://platform.openai.com/docs/quickstart - type: openai api_key: sk-xxx # ENV: {client_name}_API_KEY api_base: https://api.openai.com/v1 # ENV: {client_name}_API_BASE organization_id: org-xxx # Optional # See https://ai.google.dev/docs - type: gemini api_key: xxx # ENV: {client_name}_API_KEY # possible values: BLOCK_NONE, BLOCK_ONLY_HIGH, BLOCK_MEDIUM_AND_ABOVE, BLOCK_LOW_AND_ABOVE block_threshold: BLOCK_NONE # Optional # See https://docs.anthropic.com/claude/reference/getting-started-with-the-api - type: claude api_key: sk-ant-xxx # ENV: {client_name}_API_KEY # See https://docs.mistral.ai/ - type: mistral api_key: xxx # ENV: {client_name}_API_KEY # See https://docs.cohere.com/docs/the-cohere-platform - type: cohere api_key: xxx # ENV: {client_name}_API_KEY # See https://docs.perplexity.ai/docs/getting-started - type: perplexity api_key: pplx-xxx # ENV: {client_name}_API_KEY # See https://console.groq.com/docs/quickstart - type: groq api_key: gsk_xxx # ENV: {client_name}_API_KEY # See https://github.com/jmorganca/ollama - type: ollama api_base: http://localhost:11434 # ENV: {client_name}_API_BASE api_auth: Basic xxx # ENV: {client_name}_API_AUTH chat_endpoint: /api/chat # Optional models: # Required - name: llama3 max_input_tokens: 8192 # 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_name}_API_BASE api_key: xxx # ENV: {client_name}_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_name}_PROJECT_ID location: xxx # ENV: {client_name}_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: # Optional field, possible values: BLOCK_NONE, BLOCK_ONLY_HIGH, BLOCK_MEDIUM_AND_ABOVE, BLOCK_LOW_AND_ABOVE block_threshold: BLOCK_ONLY_HIGH # See https://docs.aws.amazon.com/bedrock/latest/userguide/ - type: bedrock access_key_id: xxx # ENV: {client_name}_ACCESS_KEY_ID secret_access_key: xxx # ENV: {client_name}_SECRET_ACCESS_KEY region: xxx # ENV: {client_name}_REGION # See https://developers.cloudflare.com/workers-ai/ - type: cloudflare account_id: xxx # ENV: {client_name}_ACCOUNT_ID api_key: xxx # ENV: {client_name}_API_KEY # See https://replicate.com/docs - type: replicate api_key: xxx # ENV: {client_name}_API_KEY # See https://cloud.baidu.com/doc/WENXINWORKSHOP/index.html - type: ernie api_key: xxx # ENV: {client_name}_API_KEY secret_key: xxxx # ENV: {client_name}_SECRET_KEY # See https://help.aliyun.com/zh/dashscope/ - type: qianwen api_key: sk-xxx # ENV: {client_name}_API_KEY # See https://platform.moonshot.cn/docs/intro - type: moonshot api_key: sk-xxx # ENV: {client_name}_API_KEY # For any platform compatible with OpenAI's API - type: openai-compatible name: localai api_base: http://localhost:8080/v1 # ENV: {client_name}_API_BASE api_key: sk-xxx # ENV: {client_name}_API_KEY chat_endpoint: /chat/completions # Optional models: # Required - name: llama3 max_input_tokens: 8192 # See https://docs.endpoints.anyscale.com/ - type: openai-compatible name: anyscale api_base: https://api.endpoints.anyscale.com/v1 api_key: xxx models: # https://docs.endpoints.anyscale.com/text-generation/query-a-model#select-a-model - name: meta-llama/Meta-Llama-3-70B-Instruct max_input_tokens: 8192 input_price: 1 output_price: 1 # See https://deepinfra.com/docs - type: openai-compatible name: deepinfra api_base: https://api.deepinfra.com/v1/openai api_key: xxx models: # https://deepinfra.com/models - name: meta-llama/Meta-Llama-3-70B-Instruct max_input_tokens: 8192 input_price: 0.59 output_price: 0.79 # See https://readme.fireworks.ai/docs/quickstart - type: openai-compatible name: fireworks api_base: https://api.fireworks.ai/inference/v1 api_key: xxx models: # https://fireworks.ai/models - name: accounts/fireworks/models/llama-v3-70b-instruct max_input_tokens: 8192 input_price: 0.9 output_price: 0.9 # See https://octo.ai/docs/getting-started/quickstart - type: openai-compatible name: octoai api_base: https://text.octoai.run/v1 api_key: xxx models: # https://octo.ai/docs/getting-started/inference-models - name: meta-llama-3-70b-instruct max_input_tokens: 8192 input_price: 0.86 output_price: 0.86 # See https://docs.together.ai/docs/quickstart - type: openai-compatible name: together api_base: https://api.together.xyz/v1 api_key: xxx models: # https://docs.together.ai/docs/inference-models - name: meta-llama/Llama-3-70b-chat-hf max_input_tokens: 8192 input_price: 0.9 output_price: 0.9