Merge pull request #2541 from udit-001/docs/chatlitellm-langfuse

docs(langfuse): add chatlitellm section
This commit is contained in:
Ishaan Jaff
2024-03-15 16:32:01 -07:00
committed by GitHub
2 changed files with 39 additions and 1 deletions
@@ -133,3 +133,6 @@ chat(messages)
```
</TabItem>
</Tabs>
## Use LangChain ChatLiteLLM + Langfuse
Checkout this section [here](../observability/langfuse_integration#use-langchain-chatlitellm--langfuse) for more details on how to integrate Langfuse with ChatLiteLLM.
@@ -132,6 +132,41 @@ print(response)
```
### Use LangChain ChatLiteLLM + Langfuse
Pass `trace_user_id`, `session_id` in model_kwargs
```python
import os
from langchain.chat_models import ChatLiteLLM
from langchain.schema import HumanMessage
import litellm
# from https://cloud.langfuse.com/
os.environ["LANGFUSE_PUBLIC_KEY"] = ""
os.environ["LANGFUSE_SECRET_KEY"] = ""
os.environ['OPENAI_API_KEY']=""
# set langfuse as a callback, litellm will send the data to langfuse
litellm.success_callback = ["langfuse"]
chat = ChatLiteLLM(
model="gpt-3.5-turbo"
model_kwargs={
"metadata": {
"trace_user_id": "user-id2", # set langfuse Trace User ID
"session_id": "session-1" , # set langfuse Session ID
"tags": ["tag1", "tag2"]
}
}
)
messages = [
HumanMessage(
content="what model are you"
)
]
chat(messages)
```
## Troubleshooting & Errors
### Data not getting logged to Langfuse ?
@@ -142,4 +177,4 @@ print(response)
- [Schedule Demo 👋](https://calendly.com/d/4mp-gd3-k5k/berriai-1-1-onboarding-litellm-hosted-version)
- [Community Discord 💭](https://discord.gg/wuPM9dRgDw)
- Our numbers 📞 +1 (770) 8783-106 / +1 (412) 618-6238
- Our emails ✉️ ishaan@berri.ai / krrish@berri.ai
- Our emails ✉️ ishaan@berri.ai / krrish@berri.ai