Comments (2)
Could you share all the code? Particularly where you make any calls to client.chat.completions.create
. From what I understand from your message, everything is working fine. This is the expected behavior of the validation process: if the response does not meet the criteria, you should get a validation error, and that should trigger an exception like the one shown in the output you're sharing.
from instructor.
Thanks for your reply. I used to think it was wrong when meeting Assertion failed. The result is correct!
from instructor.
Related Issues (20)
- Compatibility with open models HOT 4
- Trying to use Mixtral @ Anyscale but it doesn't return a clean JSON after a retry and fails HOT 7
- Library support for Mistral endpoints HOT 1
- Deprecate Mode.FUNCTIONS HOT 1
- support for NexusRaven-V2 function call HOT 1
- `Maybe` should use outer `MaybeBase` for better type checking HOT 2
- Move CLI into extras so default dependency chain doesn't include commonmark (which doesn't support Python 3.12) HOT 4
- Outdated documentation for llm_validator for openai_client parameter HOT 2
- Any examples on how to use the library without having to use the .patch method? HOT 2
- Assistants API Support HOT 11
- LiteLLM + Ollama with MD_JSON mode HOT 3
- enable max_retries with tool choice calls HOT 2
- when i run the auto_dataframe.py sample get the error like this HOT 6
- Multiple Formats for Distillation Finetuning HOT 1
- Pointers to what works well with GPT function/tool calling? HOT 2
- Azure OpenAI compatibility with Instructor HOT 1
- Track Cumulative Token Usage During Any Previous Failed Attempts
- No matching distribution found for instructor HOT 5
- emojis not supported as part of the response? HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from instructor.