Ecosyste.ms: Timeline
Browse the timeline of events for every public repo on GitHub. Data updated hourly from GH Archive.
krrishdholakia created a branch on BerriAI/litellm
litellm_redis_otel_tracing - Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
us58 created a comment on an issue on BerriAI/litellm
Sorry I have no idea how to monitor this. If you can explain how to do this, I'm happy to help
krrishdholakia pushed 1 commit to litellm_dev_10_26_2024 BerriAI/litellm
- fix(redis_cache.py): instrument otel logging for sync redis calls ensures complete coverage for all redis cache calls 7301c83
krrishdholakia pushed 1 commit to litellm_dev_10_26_2024 BerriAI/litellm
- test: make testing more robust for custom pricing cbc0778
krrishdholakia pushed 1 commit to litellm_dev_10_26_2024 BerriAI/litellm
- fix(main.py): register custom model pricing with specific key Ensure custom model pricing is registered to the speci... a9c8c06
krrishdholakia created a comment on an issue on BerriAI/litellm
it shouldn't be. is a file descriptor only created for http calls (wondering if a new thread could cause this)
us58 created a comment on an issue on BerriAI/litellm
Found the issue. The Ubuntu default value of 1024 for the number of file descriptors caused this. No more errors after increasing it. I guess litellm internally uses an additional request of som...
vercel[bot] created a comment on a pull request on BerriAI/litellm
[vc]: #SaCG2k1vAGa8y0oQYf0kgmhzGPGY++HI/OvidnzoIko=:eyJpc01vbm9yZXBvIjp0cnVlLCJ0eXBlIjoiZ2l0aHViIiwicHJvamVjdHMiOlt7Im5hbWUiOiJsaXRlbGxtIiwicm9vdERpcmVjdG9yeSI6ImRvY3MvbXktd2Vic2l0ZSIsImluc3BlY3Rvc...
jamesev15 opened a pull request on BerriAI/litellm
Add txt file type in GCS URIs as accepted file type for gemini 1.5
## Title Add txt file type to GCS URIs for Gemini 1.5 models ## Relevant issues Since the version of **google-cloud-aiplatform** is 1.47.0, the txt file is supported in GCS URIs, this code...
beat opened an issue on BerriAI/litellm
[Bug]: Adding a LanFuse Logging: UI is missing LANGFUSE_HOST, so a self-hosted langfuse setup not possible in one step
### What happened? New self-hosted LiteLLM installation (docker) with self-hosted langfuse. Bug 1: In the Logging&Alerts menu / Add Callback, select Langfuse, only LANGFUSE_PUBLIC_KEY and LANGF...
krrishdholakia pushed 1 commit to litellm_dev_10_26_2024 BerriAI/litellm
- docs(exception_mapping.md): add missing exception types Fixes https://github.com/Aider-AI/aider/issues/2120#issuecom... 937ed32
beat created a comment on an issue on BerriAI/litellm
Try updating to latest litellm version of today, it's fixed for me.
krrishdholakia created a branch on BerriAI/litellm
litellm_dev_10_26_2024 - Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
krrishdholakia created a comment on an issue on BerriAI/litellm
this makes sense @asapMaki > model: llama-3.2-3b-instruct # add openai/ prefix to route as OpenAI provider you didn't add the route - `openai/`, litellm has no idea how to route this model
ishaan-jaff pushed 1 commit to litellm_dd_llm_obs BerriAI/litellm
- add datadog_llm_observability ad6af95
