Move vars to dynamic, add metrics (#1085)

Use pino for logs (#1086)

Support Gemini 1.5 Pro from Vertex AI (#1041)

Add langserve endpoint (#1009)

quick fix error message (#977)

Add support for cohere endpoints (#976)

Implement Cloudflare Workers AI endpoint (#907) (#972)

Google Vertex API support (#950)

Expose sampling controls in assistants (#955) (#959)

Anthropic Endpoint Support (#923)

Fix prompt caching on llama.cpp endpoints (#920)

Make sure preprompt is set on open ai endpoint type (#913)

Fix issue with "continue" feature on llama.cpp endpoints (#898)

Bug Fix: Json Decoder aggessively pulls json (#867)

Allow customising defaultQuery for native Azure OpenAI support (#822)

Conversation trees (#223) (#807)

fix continue button on openai endpoint (#803)

Several QoL contributions (#760)

Continue generation feature (#707)

[JS] use shorthand notation (#711)

Standardize HF_ACCESS_TOKEN -> HF_TOKEN (#610)

Support websearch for openAI chat completion mode (#608)

Add support for passing an API key or any other custom token in the authorization header (#579)

Add ollama endpoint support (#569)

disable cache on tgi endpoint (#567)

Add support for tgi multimodal models (#531)

remove min string size on accessToken

fix: typecheck

Modular backends & support for openAI & AWS endpoints (#541)