-
I use nested pydantic models in the structured output. ell only keeps track of the first level pydantic model in versioning and tracing.
Example:
class Sub(BaseModel):
fields...
class Main…
-
GPT-4o mini
https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/
Describing Differences in Image Sets with Natural Language (CVPR 2024 Oral)
https://arxiv.org/abs/2312.0297…
-
### Environment
SaaS (https://sentry.io/)
### Steps to Reproduce
I am using latest version of sentry and latest version of OpenAI SDK. But not being able to track tokens. Below is my code
Sentry i…
-
Trying the example of movie reviews:
```
import ell
from pydantic import BaseModel, Field
class MovieReview(BaseModel):
title: str = Field(description="The title of the movie")
ratin…
-
Что бы работал Copilot (bing.com -> chat) надо сохранить оттуда куки, export в json сохранить под именем cookie*.json и регулярно проходить капчу.
Неясная формулировка. Куки сохранил в cookie.json …
-
gpt-4o uses a different tokenizer, we need to update jtokkit version once it is released
-
Results from the new [benchmark](https://github.com/fl4p/fetlib/blob/dev/read_llm_json.py) comparing actual min/typ/max field values:
```
num *EQUAL* *VALUES*:
…
-
**Describe the bug**
I have a remote LLM that is our internal proxy for Azure OpenAI and Google Gemini. I have configured it properly as it does occasionally work. However, I often get an error pop u…
-
**Project description**
Enhanced ChatGPT Clone: Features Anthropic, AWS, OpenAI, Assistants API, Azure, Groq, o1, GPT-4o, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, mess…
-
### 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…