-
### Summary of your question
When running the bot, it seems to be crashing when trying to generate resume with gemini API, it looks like lib_resume_builder_AIHawk only accepts OpenAI API key
### Que…
-
### The Feature
post https://api.openai.com/v1/images/edits
### Motivation, pitch
Besides post https://api.openai.com/v1/images/generations, it is also possible to do post https://api.openai.com/v1…
-
### The Feature
We should support the new `store`, `metadata`, and `service_tier` parameters on OpenAI requests.
https://platform.openai.com/docs/api-reference/chat/create#chat-create-store
### M…
-
### Feature summary
CLI option to reduce number of requests per minute
### Feature description
Add a CLI option to pass a limit of how much requests per minute Will be done to OpenAI. This will all…
-
### 🐛 Describe the bug
Hi thanks for the library! It seems that the `output.logits` is missing. Looking at code https://github.com/linkedin/Liger-Kernel/blob/6cdc93deee15ab6c843149d6ed660c297c5c2d4a/…
-
### What happened?
I am trying to hit an embedding API via AsyncOpenAI. The following code works:
```python
client = AsyncOpenAI(base_url="http://localhost:7997", api_key="sk-infinity-svc")
…
-
### What Would You Like to See with the Gateway?
https://platform.openai.com/docs/guides/realtime?text-generation-quickstart-example=text
### Context for your Request
_No response_
### Your Twitte…
-
### What happened?
When using the moderation from openai, littlellm seem to send the prefix "openai/" to the openai api
```javascript
const response = await openai.moderations.create({
input:…
-
### What Would You Like to See with the Gateway?
Portkey is an extremely exciting AI gateway！and I want to use Alibaba Cloud's Qwen large model through Dashscope. Moreover, Dashscope is already compa…
-
### What happened?
When using vision language model, I noticed different providers (inference engine) can have un-matched prompt token counts in the usage in streaming v.s. non-streaming request. I'm…