Describe the feature
Add LiteLLM as a new chat model provider type alongside OpenAI, Anthropic, and Google. LiteLLM provides a unified completion() API that routes to 100+ LLM providers (AWS Bedrock, Azure, Ollama, Mistral, Cohere, Groq, DeepSeek, etc.) using the same OpenAI-compatible interface. This would let self-hosted Khoj users access any LLM provider without needing individual provider implementations.
Use Case
- Self-hosted users currently limited to OpenAI, Anthropic, and Google. Adding each new provider requires code changes.
- Users hitting issues with OpenAI-compatible proxies. LiteLLM handles provider-specific quirks internally.
- Users wanting to use local models via Ollama, or enterprise models via AWS Bedrock/Azure, without configuring them as OpenAI-compatible endpoints.
Proposed Solution
No response
Additional Information
No response
Link to Discord or Github discussion
No response
Describe the feature
Add LiteLLM as a new chat model provider type alongside OpenAI, Anthropic, and Google. LiteLLM provides a unified completion() API that routes to 100+ LLM providers (AWS Bedrock, Azure, Ollama, Mistral, Cohere, Groq, DeepSeek, etc.) using the same OpenAI-compatible interface. This would let self-hosted Khoj users access any LLM provider without needing individual provider implementations.
Use Case
Proposed Solution
No response
Additional Information
No response
Link to Discord or Github discussion
No response