-
### Your current environment
docker 0.6.3.post1
8*A100
```
docker pull vllm/vllm-openai:latest
docker stop qwen25_72b ; docker remove qwen25_72b
docker run -d --restart=always \
--runtime…
-
Tried the vanilla sample, and updated my openai uri and key details in .env. However setup.py call failed. Any idea what to change in sample? Perhaps, "sales_data_insights" function description conten…
-
New user here...
**Environment**
windows 11
danswer rev: 23.3.0
docker image
**Question**
Accessing a cloud-based LLM seems straightforward enough, but is it possible to access a local LLM v…
-
Hi @Glitch9Inc thank you for the corrections, the first time I run the assistant works great, second time I get an error:
Parameter name: _unity_self
UnityEngine.Debug:LogError (object…
-
### Checked other resources
- [X] I added a very descriptive title to this issue.
- [X] I searched the LangChain documentation with the integrated search.
- [X] I used the GitHub search to find a sim…
-
### Feature Description
The documentation for OpenAI Assistants (https://sdk.vercel.ai/docs/ai-sdk-ui/openai-assistants) could use a bit more tweaking to account for real-world usage.
In this blo…
-
### Library name and version
Azure.AI.OpenAI v2.1.0-beta.2
### Describe the bug
I have a RAG AI application that occasionally throws an exception when calling the ChatCompletion.GetMessageContext()…
-
Trying to run the augment toolkit on MacOs M3, with ollama (ollama run llama3) on the following config.yaml
PATH:
INPUT: "./raw_text_input"
OUTPUT: "./output"
DEFAULT_PROMPTS: "./prompts" # …
-
**Describe the bug 描述bug**
使用free api请求assistant api的话，会报404
```python
assistant = client.beta.assistants.create(name="my assistant",
instructions="You are a gr…
-
### Feature Description
Add events on the `useAssistant` hook, just like the `useChat` hook.
https://sdk.vercel.ai/docs/api-reference/use-chat
`onResponse`
`onError`
`onFinish`
But most **…