phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

(docs) update how to use litellm streaming

Browse source
This commit is contained in:
ishaan-jaff 2023-11-21 11:19:32 -08:00
parent 37187e8e88
commit f29a353796
2 changed files with 64 additions and 64 deletions
Download patch file Download diff file Expand all files Collapse all files

10
README.md
View file

@ -68,13 +68,13 @@ Streaming is supported for all models (Bedrock, Huggingface, TogetherAI, Azure,
```python
from litellm import completion
response = completion(model="gpt-3.5-turbo", messages=messages, stream=True)
for chunk in response:
print(chunk['choices'][0]['delta'])
for part in response:
print(part.choices[0].delta.content or "")
# claude 2
result = completion('claude-2', messages, stream=True)
for chunk in result:
print(chunk['choices'][0]['delta'])
response = completion('claude-2', messages, stream=True)
for part in response:
print(part.choices[0].delta.content or "")
```
# Router - load balancing([Docs](https://docs.litellm.ai/docs/routing))