Adrian Cole

[REQUEST]: working tool call configuration with localai

3

### Has this been supported or requested before? - [X] I have checked [the GitHub README](https://github.com/QwenLM/Qwen2.5). - [X] I have checked [the Qwen documentation](https://qwen.readthedocs.io). - [X] I have checked the...

refresh the images in the README

1

I think some things have changed!

Some people put large data in span attributes, so you won't be able to see it even if you change the width. It would be nice to be able to...

refresh span name when trace completes in traces list

1

Right now, the trace list has the first span name to complete, not the first span name to start (root trace) in the list. I can't seem to have this...

Implement LLM spans as defined in opentelemetry semantic conventions 1.27.0

1

This is a tall ask, but there are spans and metrics defined in opentelemetry for LLMs (referring intentionally to 1.27.0 as it is what most vendors implement and main may...

fix: validate provider urls before use

5

This fixes validation, like #133, except for all providers that accept a hostname/base URL variable.

**Describe the bug** When I have instructions that require verification of `.env` files, I see a lot of misses (in openai and gemini) as it uses `ls`, not `ls -a`....

otel.instrumentation.common.peer-service-mapping: support glob

4

### Is your feature request related to a problem? Please describe. Right now, there's a handy feature to map peer service names, given hostname or hostname:port. This is important for...

opentelemetry-instrumentation-vertexai: support StreamGenerateContent

2

### What problem do you want to solve? Right now, if you run use langchain with VertexAI in a chatbot, the initialization will appear like this: ```python return ChatVertexAI( model_name=os.getenv("CHAT_MODEL"),...

Make is easier to select either openai or azure openai, ideally heuristically

2

We currently use spring-specific ways to reduce ambiguity between which llm to use. However, there's a routine issue with OpenAI as often the same app needs to use Azure OpenAI....