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

docs(stream.md): fix async streaming tutorial

Browse source
This commit is contained in:
Krrish Dholakia 2023-10-09 11:47:49 -07:00
parent c3e4c3e3f0
commit 46bfeddfc7
1 changed files with 4 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

6
docs/my-website/docs/completion/stream.md
View file

@ -38,7 +38,9 @@ We've implemented an `__anext__()` function in the streaming object returned. Th
Here's an example of using it with openai. But this Here's an example of using it with openai. But this
```python ```python
from litellm import completion from litellm import completion
import asyncio import asyncio, os, traceback, time
os.environ["OPENAI_API_KEY"] = "your-api-key"
def logger_fn(model_call_object: dict): def logger_fn(model_call_object: dict):
print(f"LOGGER FUNCTION: {model_call_object}") print(f"LOGGER FUNCTION: {model_call_object}")
@ -60,7 +62,7 @@ async def completion_call():
chunk_time = time.time() chunk_time = time.time()
print(f"time since initial request: {chunk_time - start_time:.5f}") print(f"time since initial request: {chunk_time - start_time:.5f}")
print(chunk["choices"][0]["delta"]) print(chunk["choices"][0]["delta"])
complete_response += chunk["choices"][0]["delta"]["content"] complete_response += chunk["choices"][0]["delta"].get("content", "")
if complete_response == "": if complete_response == "":
raise Exception("Empty response received") raise Exception("Empty response received")
except: except: