# ---- LLM ---- model: openai:gpt-4o # Specify the LLM to use temperature: null # Set default temperature parameter (0, 1) top_p: null # Set default top-p parameter, with a range of (0, 1) or (0, 2) depending on the model # ---- Behavior ---- stream: true # Controls whether to use the stream-style APIs when querying for completions from LLM clients. save: true # Indicates whether to persist the conversation to messages.md for posterity keybindings: emacs # Choose keybinding style (emacs, vi) editor: null # Specifies the editor used to edit the input buffer or session. (e.g. vim, emacs, nano, hx). Defaults to $EDITOR wrap: no # Controls text wrapping (no, auto, ) wrap_code: false # Enables or disables the wrapping of code blocks # ---- Prelude ---- repl_prelude: null # Set a default session or role for REPL mode to use (e.g. role:, session:, :) cmd_prelude: null # Set a default session or role for CMD mode to use (e.g. role:, session:, :) agent_session: null # Set a session to use when starting an agent (e.g. temp, default) # ---- Appearance ---- highlight: true # Controls syntax highlighting light_theme: false # Activates a light color theme when true. env: LOKI_LIGHT_THEME # ---- Miscellaneous ---- user_agent: null # Set User-Agent HTTP header, use `auto` for loki/ save_shell_history: true # Whether to save shell execution command to the history file sync_models_url: > # URL to sync model changes from https://raw.githubusercontent.com/Dark-Alex-17/loki/refs/heads/main/models.yaml # ---- REPL Prompt ---- # Custom REPL left/right prompts; see the [REPL Prompt Documentation](./docs/REPL-PROMPT.md) for more information left_prompt: '{color.red}{model}){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}' # ---- Vault ---- # See the [Vault documentation](./docs/VAULT.md) for more information on the Loki vault vault_password_file: null # Path to a file containing the password for the Loki vault (cannot be a secret template) # ---- Function Calling ---- # See the [Tools documentation](./docs/function-calling/TOOLS.md) for more details 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,fs_read,fs_glob,fs_grep' enabled_tools: null # Which tools to enable by default. (e.g. 'fs,web_search_loki') visible_tools: # Which tools are visible to be compiled (and are thus able to be defined in 'enabled_tools') # - demo_py.py # - demo_sh.sh # - demo_ts.ts - execute_command.sh # - execute_py_code.py # - execute_sql_code.sh # - fetch_url_via_curl.sh # - fetch_url_via_jina.sh - fs_cat.sh - fs_ls.sh # - fs_read.sh # - fs_glob.sh # - fs_grep.sh # - fs_mkdir.sh # - fs_patch.sh # - fs_write.sh - get_current_time.sh # - get_current_weather.py # - get_current_weather.ts - get_current_weather.sh - query_jira_issues.sh # - search_arxiv.sh # - search_wikipedia.sh # - search_wolframalpha.sh # - send_mail.sh # - send_twilio.sh # - web_search_loki.sh # - web_search_perplexity.sh # - web_search_tavily.sh # ---- MCP Servers ---- # See the [MCP Servers documentation](./docs/MCP-SERVERS.md) for more details mcp_server_support: true # Enables or disables MCP servers (globally). mapping_mcp_servers: # Alias for an MCP server or set of servers git: github,gitmcp enabled_mcp_servers: null # Which MCP servers to enable by default (e.g. 'github,slack,ddg-search') # ---- Session ---- # See the [Session documentation](./docs/SESSIONS.md) for more information save_session: null # Controls the persistence of the session. If true, auto save; if false, don't auto-save save; if null, ask the user what to do compression_threshold: 4000 # Compress the session when the token count reaches or exceeds this threshold summarization_prompt: > # The text prompt used for creating a concise summary of session message 'Summarize the discussion briefly in 200 words or less to use as a prompt for future context.' summary_context_prompt: > # The text prompt used for including the summary of the entire session as context to the model 'This is a summary of the chat history as a recap: ' # ---- RAG ---- # See the [RAG Docs](./docs/RAG.md) for more details. rag_embedding_model: null # Specifies the embedding model used for context retrieval rag_reranker_model: null # Specifies the reranker model used for sorting retrieved documents; Loki uses Reciprocal Rank Fusion by default rag_top_k: 5 # Specifies the number of documents to retrieve for answering queries rag_chunk_size: null # Defines the size of chunks for document processing in characters rag_chunk_overlap: null # Defines the overlap between chunks # Defines the query structure using variables like __CONTEXT__, __SOURCES__, and __INPUT__ to tailor searches to specific needs rag_template: | Answer the query based on the context while respecting the rules. (user query, some textual context and rules, all inside xml tags) __CONTEXT__ __SOURCES__ - If you don't know, just say so. - If you are not sure, ask for clarification. - Answer in the same language as the user query. - If the context appears unreadable or of poor quality, tell the user then answer as best as you can. - If the answer is not in the context but you think you know the answer, explain that to the user then answer with your own knowledge. - Answer directly and without using xml tags. - When using information from the context, cite the relevant source from the section. __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: # : # Note: Use `$1` for input file and `$2` for output file. If `$2` is omitted, use stdout as output. pdf: 'pdftotext $1 -' # Use pdftotext to convert a PDF file to text # (see https://poppler.freedesktop.org for details on how to install pdftotext) docx: 'pandoc --to plain $1' # Use pandoc to convert a .docx file to text # (see https://pandoc.org for details on how to install pandoc) jina: 'curl -fsSL https://r.jina.ai/$1 -H "Authorization: Bearer {{JINA_API_KEY}}' # Use Jina to translate a website into text; # Requires a Jina API key to be added to the Loki vault git: > # Use yek to load a git repository into the knowledgebase (https://github.com/bodo-run/yek) sh -c "yek $1 --json | jq 'map({ path: .filename, contents: .content })'" # ---- Clients ---- # See the [Clients documentation](./docs/clients/CLIENTS.md) for more details 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 # default_chunk_size: 1500 # max_batch_size: 100 # - name: xxxx # Reranker model # type: reranker # patch: # Patch API calls # chat_completions: # API type; Possible values: chat_completions, embeddings, and rerank # : # The regex to match model names, e.g. '.*' 'gpt-4o' 'gpt-4o|gpt-4-.*' # url: '' # Patch request URL # body: # Patch request body # # headers: # Patch request headers # : # extra: # proxy: socks5://127.0.0.1:1080 # Set proxy # connect_timeout: 10 # Set timeout in seconds for connect to api # See https://platform.openai.com/docs/quickstart - type: openai api_base: https://api.openai.com/v1 # Optional api_key: '{{OPENAI_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault organization_id: org-xxx # Optional # For any platform compatible with OpenAI's API - type: openai-compatible name: ollama api_base: http://localhost:11434/v1 api_key: '{{OLLAMA_API_KEY}}' # Optional; You can either hard-code or inject secrets from the Loki vault models: - name: deepseek-r1 max_input_tokens: 131072 - name: llama3.1 max_input_tokens: 128000 supports_function_calling: true - name: llama3.2-vision max_input_tokens: 131072 supports_vision: true - name: nomic-embed-text type: embedding default_chunk_size: 1000 max_batch_size: 50 # See https://ai.google.dev/docs - type: gemini api_base: https://generativelanguage.googleapis.com/v1beta api_key: '{{GEMINI_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault auth: null # When set to 'oauth', Loki will use OAuth instead of an API key # Authenticate with `loki --authenticate` or `.authenticate` in the REPL patch: 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_base: https://api.anthropic.com/v1 # Optional api_key: '{{ANTHROPIC_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault auth: null # When set to 'oauth', Loki will use OAuth instead of an API key # Authenticate with `loki --authenticate` or `.authenticate` in the REPL # See https://docs.mistral.ai/ - type: openai-compatible name: mistral api_base: https://api.mistral.ai/v1 api_key: '{{MISTRAL_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault # See https://docs.x.ai/docs - type: openai-compatible name: xai api_base: https://api.x.ai/v1 api_key: '{{XAI_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault # See https://docs.ai21.com/docs/overview - type: openai-compatible name: ai12 api_base: https://api.ai21.com/studio/v1 api_key: '{{AI21_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault # See https://docs.cohere.com/docs/the-cohere-platform - type: cohere api_base: https://api.cohere.ai/v2 # Optional api_key: '{{COHERE_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault # See https://docs.perplexity.ai/getting-started/overview - type: openai-compatible name: perplexity api_base: https://api.perplexity.ai api_key: '{{PERPLEXITY_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault # See https://console.groq.com/docs/quickstart - type: openai-compatible name: groq api_base: https://api.groq.com/openai/v1 api_key: '{{GROQ_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault # See https://learn.microsoft.com/en-us/azure/ai-services/openai/chatgpt-quickstart - type: azure-openai api_base: https://{RESOURCE}.openai.azure.com api_key: '{{AZURE_OPENAI_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault models: - name: gpt-4o # Model deployment name max_input_tokens: 128000 supports_vision: true supports_function_calling: true # See https://cloud.google.com/vertex-ai - type: vertexai project_id: xxx location: xxx # Specifies an application default credentials (adc) file # Run `gcloud auth application-default login` to initialize the ADC file # see https://cloud.google.com/docs/authentication/external/set-up-adc for more information adc_file: /application_default_credentials.json # Optional patch: chat_completions: 'gemini-.*': 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://docs.aws.amazon.com/bedrock/latest/userguide/ - type: bedrock access_key_id: '{{AWS_ACCESS_KEY_ID}}' # You can either hard-code or inject secrets from the Loki vault secret_access_key: '{{AWS_SECRET_ACCESS_KEY}}' # You can either hard-code or inject secrets from the Loki vault region: xxx session_token: xxx # Optional, only needed for temporary credentials # See https://developers.cloudflare.com/workers-ai/ - type: openai-compatible name: cloudflare api_base: https://api.cloudflare.com/client/v4/accounts/{ACCOUNT_ID}/ai/v1 api_key: '{{CLOUDFLARE_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault # See https://cloud.baidu.com/doc/WENXINWORKSHOP/index.html - type: openai-compatible name: ernie api_base: https://qianfan.baidubce.com/v2 api_key: '{{BAIDU_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault # See https://dashscope.aliyun.com/ - type: openai-compatible name: qianwen api_base: https://dashscope.aliyuncs.com/compatible-mode/v1 api_key: '{{ALIYUN_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault # See https://cloud.tencent.com/product/hunyuan - type: openai-compatible name: hunyuan api_base: https://api.hunyuan.cloud.tencent.com/v1 api_key: '{{TENCENT_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault # See https://platform.moonshot.cn/docs/intro - type: openai-compatible name: moonshot api_base: https://api.moonshot.cn/v1 api_key: '{{MOONSHOT_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault # See https://platform.deepseek.com/api-docs/ - type: openai-compatible name: deepseek api_base: https://api.deepseek.com api_key: '{{DEEPSEEK_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault # See https://open.bigmodel.cn/dev/howuse/introduction - type: openai-compatible name: zhipuai api_base: https://open.bigmodel.cn/api/paas/v4 api_key: '{{ZHIPUAI_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault # See https://platform.minimaxi.com/document/Fast%20access - type: openai-compatible name: minimax api_base: https://api.minimax.chat/v1 api_key: '{{MINIMAX_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault # See https://openrouter.ai/docs#quick-start - type: openai-compatible name: openrouter api_base: https://openrouter.ai/api/v1 api_key: '{{OPENROUTER_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault # See https://github.com/marketplace/models - type: openai-compatible name: github api_base: https://models.inference.ai.azure.com api_key: '{{GITHUB_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault # See https://deepinfra.com/docs - type: openai-compatible name: deepinfra api_base: https://api.deepinfra.com/v1/openai api_key: '{{DEEPINFRA_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault # ----- RAG dedicated ----- # See https://jina.ai - type: openai-compatible name: jina api_base: https://api.jina.ai/v1 api_key: '{{JINA_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault # See https://docs.voyageai.com/docs/introduction - type: openai-compatible name: voyageai api_base: https://api.voyageai.com/v1 api_key: '{{VOYAGEAI_API_KEY}}' # You can either hard-code or inject secrets from the Loki vault