Providers
Point DeepDoc at Anthropic, OpenAI, Gemini, Azure, or a local model.
DeepDoc talks to models through LiteLLM,
so anything LiteLLM supports works. deepdoc init --provider picks sensible
defaults for the common ones.
deepdoc init --provider anthropic
export ANTHROPIC_API_KEY=sk-ant-...llm:
provider: anthropic
model: claude-sonnet-4-20250514
api_key_env: ANTHROPIC_API_KEYAnthropic has no embedding models. If you enable the chatbot, embeddings come
from the local fastembed default or another provider.
deepdoc init --provider openai
export OPENAI_API_KEY=sk-...llm:
provider: openai
model: gpt-4o
api_key_env: OPENAI_API_KEYdeepdoc init --provider gemini
export GEMINI_API_KEY=...llm:
provider: gemini
model: gemini/gemini-2.0-flash
api_key_env: GEMINI_API_KEYKeep the gemini/ prefix
LiteLLM uses it to route to the Gemini API. Without it you may be routed to Vertex AI, which authenticates differently.
deepdoc init --provider azure
export AZURE_API_KEY=...llm:
provider: azure
model: azure/your-deployment-name
api_key_env: AZURE_API_KEY
base_url: "https://your-resource.openai.azure.com"
api_version: "2024-02-01"Azure needs base_url and api_version as well as the key. DeepDoc says so
if either is missing.
deepdoc init --provider ollama
ollama pull llama3.2llm:
provider: ollama
model: ollama/llama3.2No API key, no per-token cost, and nothing leaves your machine. Slower than a hosted model, and quality varies — but for a private repository it is often the right trade.
Any other provider
--provider is not restricted to the list above. Any LiteLLM alias works:
deepdoc init --provider groq
deepdoc config set llm.model "groq/llama-3.3-70b-versatile"
deepdoc config set llm.api_key_env GROQ_API_KEYRate limits
If you hit 429s, lower the concurrency:
llm:
rate_limits:
max_concurrency: 2
requests_per_minute: 30
tokens_per_minute: 100000
adaptive_backoff: trueThese apply to documentation generation. The chatbot's answer model is a separate surface and does not read them.
Switching later
deepdoc config set llm.provider openai
deepdoc config set llm.model gpt-4o
deepdoc config set llm.api_key_env OPENAI_API_KEYChanging the model changes what gets written, so it takes effect on your next
generate or update — not on serve.