-
Your code example seems to imply that.
gvlx updated
4 months ago
-
https://aws.amazon.com/about-aws/whats-new/2023/09/amazon-titan-embeddings-generally-available/
Could this be used for Zep too?
-
I like the look of https://github.com/BerriAI/litellm (which also supports streaming, though currently agent smith is not setup to handle that)
-
I am using the `litellm` client to benchmark a HuggingFace TGI server.
In `token_benchmark_ray.py`, `req_launcher.get_next_ready()` is called periodically to fetch pending **results**, with the `bl…
-
### The Feature
Title says it all
### Motivation, pitch
I want to understand if LiteLLM meets my requirements
### Twitter / LinkedIn details
@aantn https://www.linkedin.com/in/natanyellin
aantn updated
5 months ago
-
### What happened?
The code example in the docs: https://docs.litellm.ai/docs/observability/langsmith_integration
For integrating litellm with langsmith fails as it expects an event loop to be run…
-
### What happened?
## The problem
This does **not** work
```python
import litellm
litellm.api_base = "http://localhost:4000"
litellm.set_verbose = True
text = "Hello there!"
list_text…
-
### Issue
I am receiving the following error when attempting to use my local Llama instance of qwen2.5-coder-32b-instruct. (Ubuntu 24.04) When starting aider and pointing to my ollama instance with…
-
**Describe the bug**
For some reasons, I couldn't get the apikey from openai's official website, so I registered openrouter.ai to get the apikey, but when I used openrouter's key to allow 01, the fol…
-
Hi there! Wondering if robby can setup to work with openapi compatible providers. Being able to setup a base_url for example...