Comments (7)
okhat
commented on July 22, 2024
1
Appreciate your input, @stalkermustang ! Yes, we’re working on this.
The effort is led by @santhnm2 and @amirziai
from dspy.
okhat
commented on July 22, 2024
1
They are on the main branch!
from dspy.
okhat
commented on July 22, 2024
It probably doesn’t need a major refactor at the moment.. just appropriate wrappers
from dspy.
stalkermustang
commented on July 22, 2024
@okhat Ok, please let me know if I can help with this integration / any other important staff.
from dspy.
okhat
commented on July 22, 2024
@stalkermustang This particular integration seems under control, but would you like to help revamp our caching system? We're now using joblib but it's pretty basic and unreliable overall. Maybe we should have a redis server or a DB of some kind.
from dspy.
varun-singh-work
commented on July 22, 2024
Hi Team , wanted to check by when do we plan to release the wrappers that would make it easier to use open source or custom/private LLM's ??
from dspy.
varun-singh-work
commented on July 22, 2024
would you be sharing/comitting a sample intro notebook for query HF models/LLMS similar to the one used with ChatGPT(intro.pynb) ??
from dspy.
Related Issues (20)
- Add Community Contributions for Signatures, Prefixes, Postfixes and useful utilities in the release package HOT 2
- clarification on type of dspy.Prediction.context HOT 2
- unable to connect to the host: future-hgx-1 HOT 2
- Crash saving typed predictors with the '... is not JSON serializable' message HOT 2
- Bool output failing when using TypedPredictor HOT 1
- cannot pickle 'socket' object when using ReAct module with HFClientVLLM
- AttributeError: 'HFClientVLLM' object has no attribute 'model'
- LLM output appears cut-off (compared to the output of the same LLM and prompt in Langchain) HOT 4
- Would suggest COPRO ignore "return_outputs" HOT 1
- Implement Exponential Backoff for ThrottlingException in InvokeModel Calls HOT 2
- Error loading program compiled using the Ensemble optimizer HOT 2
- Support for Fireworks API Models with DSPY HOT 1
- Connection error. HOT 4
- Support for vLLM chat completion endpoint HOT 1
- There is a small error in the example in signature-optimizer.mdx.
- Inspect_history only shows the last history regardless of n/skip HOT 2
- Circular import and NameError in Cohere Module HOT 4
- Update weaviate_rm.py with v4 WeaviateClient
- Enhance error handling HOT 4
- DPSy Assistant 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 dspy.