Comments (2)
Yeah, there's no way to go backwards. We use a lot of the newer features
from instructor.
@jxnl One more question that I am wondering: What would be other key differences of instructor vs e.g. using the langchain pydantic output parser.
The main difference visible to me is the retry capability, which can be maybe added to a langchain approach.
I am wondering e.g. what the additional features of V2 are that you are using. Would V2 also be more powerful to parse more complex nested outputs? Or would it be better at using OS models that do not reliable even return a valid JSON?
In our case, we are still thinking of whether it's easier to use langchain (as it support pydantic V1) or upgrade to pydantic V2 to make use of instructor.
Any quick notes would be much appreciated 🙏 !
from instructor.
Related Issues (20)
- create_partial streaming not behaving as expected HOT 12
- Support Usage Tokens Output in Claude API HOT 3
- `create_iterable` is broken HOT 3
- Doesn't work inside asyncio.gather() HOT 3
- Discord link is broken HOT 2
- Instructor fails to work with OpenRouter when using Anthropic models
- `DeprecationWarning` raised on `import instructor` vs. use of `Mode.FUNCTIONS`
- How to fall back to normal completion when no tool is needed HOT 1
- Error handling broken in `retry.py` under certain circumstances
- ModuleNotFoundError: No module named 'google' HOT 3
- Token usage irregularities
- create & create_with_completion fails on non-BaseModel classes HOT 2
- 'List' response models raise exception when using create_with_completion HOT 2
- Count tokens used in retried requests due to Pydantic validation failures HOT 3
- TOOLS mode fails on retries HOT 6
- Is it possible to get the inputs that Instructor uses? HOT 1
- Failing with Ollama HOT 5
- AnthropicBedrock Tools is already out of beta HOT 1
- "Not the same number of function calls and responses" when using Mistral API
- Anthropic client is buggy 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.