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

Update README.md

Browse source
This commit is contained in:
Ishaan Jaff 2023-08-05 15:10:49 -07:00 • committed by GitHub
parent 478e6659ab
commit 4c07cf423d
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 10 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

12
README.md
View file

@ -51,11 +51,19 @@ Stable version
pip install litellm==0.1.1 pip install litellm==0.1.1
``` ```
Streaming Queries
liteLLM supports streaming the model response back, pass `stream=True` to get a streaming iterator in response.
```
response = completion(model="gpt-3.5-turbo", messages=messages, stream=True)
for chunk in response:
print(chunk['choices'][0]['delta'])
```
# hosted version # hosted version
- [Grab time if you want access 👋](https://calendly.com/d/4mp-gd3-k5k/berriai-1-1-onboarding-litellm-hosted-version) - [Grab time if you want access 👋](https://calendly.com/d/4mp-gd3-k5k/berriai-1-1-onboarding-litellm-hosted-version)
# why did I build this # why did we build this
- **Need for simplicity**: My code started to get extremely complicated managing & translating calls between Azure, OpenAI, Cohere - **Need for simplicity**: Our code started to get extremely complicated managing & translating calls between Azure, OpenAI, Cohere
# Support # Support
Contact us at ishaan@berri.ai / krrish@berri.ai Contact us at ishaan@berri.ai / krrish@berri.ai