kor
rasa-haystack
kor | rasa-haystack | |
---|---|---|
8 | 1 | |
1,520 | 45 | |
- | - | |
6.9 | 0.0 | |
2 days ago | about 1 year ago | |
Python | Python | |
MIT License | - |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
kor
-
Pydentic in prompt engineering
Check out kor
-
27-Jun-2023
Extract structured data from text using LLMs (https://github.com/eyurtsev/kor)
- Kor: Extract structured data using LLMs
-
Guidance on creating a very lightweight model that does one task very well
Check out https://github.com/eyurtsev/kor
-
A minimal design pattern for LLM-powered microservices with FastAPI & LangChain
You're absolutely correct, and I agree that there's potentially a risk of quality loss. But likewise, since these are all intrinsically linked, it may be possible to leverage strength by combining these tasks. I'm unaware of a paper reviewing the reliability and/or performance of LLMs in this specific scenario. If you find any, do share :) With regards to generating JSON responses - there are simple ways to nudge the model and even validate it, using libraries such as https://github.com/promptslab/Promptify, https://github.com/eyurtsev/kor and https://github.com/ShreyaR/guardrails
-
Information extraction in large documents with LLMs
Currently, I'm experimenting with GPT-3.5-turbo in conjunction with the kor library (langchain for information extraction) to define a prompt template with various examples of what I'm looking for.
-
RasaGPT: First headless LLM chatbot built on top of Rasa, Langchain and FastAPI
yes. there are a few approaches which i intend to take and some helpful resources:
You could implement a Dual LLM Pattern Model https://simonwillison.net/2023/Apr/25/dual-llm-pattern/
You could also leverage a concept like Kor which is a kind of pydantic for LLMs: https://github.com/eyurtsev/kor
in short and as mentioned in the README.md this is absolutely vulnerable to prompt injection. I think this is not a fully solved issue but some interesting community research has been done to help address these things in production
rasa-haystack
-
RasaGPT: First headless LLM chatbot built on top of Rasa, Langchain and FastAPI
Also, with Haystack and a smaller Transformer model to address the long-tail of answers https://github.com/deepset-ai/rasa-haystack (and https://www.deepset.ai/blog/build-smart-conversational-agent...)
What are some alternatives?
Promptify - Prompt Engineering | Prompt Versioning | Use GPT or other prompt based models to get structured output. Join our discord for Prompt-Engineering, LLMs and other latest research
NeMo-Guardrails - NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
motorhead - π§ Motorhead is a memory and information retrieval server for LLMs.
lambdaprompt - Ξ»prompt - A functional programming interface for building AI systems
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
RasaGPT - π¬ RasaGPT is the first headless LLM chatbot platform built on top of Rasa and Langchain. Built w/ Rasa, FastAPI, Langchain, LlamaIndex, SQLModel, pgvector, ngrok, telegram
sketch - AI code-writing assistant that understands data content
rasa - π¬ Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants
shoelace-css - A collection of professionally designed, every day UI components built on Web standards. SHOELACE IS BECOMING WEB AWESOME πππ