update readme
This commit is contained in:
19
README.md
19
README.md
@@ -37,6 +37,25 @@ python fastapi_server/server_openai.py
|
|||||||
```
|
```
|
||||||
see sample usage in `fastapi_server/test_dashscope_client.py` to see how to communicate with `fake_stream_server_dashscopy.py` or `server_dashscope.py` service
|
see sample usage in `fastapi_server/test_dashscope_client.py` to see how to communicate with `fake_stream_server_dashscopy.py` or `server_dashscope.py` service
|
||||||
|
|
||||||
|
### Openai API differences
|
||||||
|
For the python `openai` package it does not handle memory. Ours does, so each call remembers what happens previously. For managing memory, pass in a `thread_id` to manager the conversations
|
||||||
|
```python
|
||||||
|
from openai import OpenAI
|
||||||
|
|
||||||
|
client = OpenAI(
|
||||||
|
base_url=BASE_URL,
|
||||||
|
api_key="test-key" # Dummy key for testing
|
||||||
|
)
|
||||||
|
|
||||||
|
client.chat.completions.create(
|
||||||
|
model="qwen-plus",
|
||||||
|
messages=messages,
|
||||||
|
stream=True,
|
||||||
|
extra_body={"thread_id":2000} # pass in a thread id
|
||||||
|
)
|
||||||
|
```
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
## Runnables
|
## Runnables
|
||||||
everything in scripts:
|
everything in scripts:
|
||||||
|
|||||||
Reference in New Issue
Block a user