🧩 GPT Vector Agent

WIP

This is an experimental playground for interfacing with different LLMs-chains (via LangChain), vectorstores (via Pinecone.io), and autonomous/chained agents.

🥅 Goals:

1. To ideate, and experiment potential use cases for generative AI
2. Provide public documention current understanding and lessons learned

📝 Prompt Design (Great resources)

1. Prompt Engineering by learnprompting.org - an open source introductory course on prompt engineering
2. ChatGPT Prompt Engineering for Developers - Prompt engineering basics straight from OpenAI

🦜 🔗 LangChain

1. Welcome to LangChain - LangChain is a framework for developing applications powered by language models.

• Be data-aware: connect a language model to other sources of data
• Be agentic: Allow a language model to interact with its environment

2. Six Main Components of LangChain:

• 🗃️ Schema (4 items)
• 🗃️ Models (3 items)
• 🗃️ Prompts (4 items)
• 🗃️ Indexes (4 items)
• 🗃️ Memory (1 items)
• 🗃️ Chains (4 items)
• 🗃️ Agents (4 items)

🔢 Vectorstore Databases

Guides

• Pineconeio Quickstart (Coming Soon)

• Redis Quickstart (Coming Soon)

🧪 Experimental Projects

Difficulty	Description
🍼 Beginner	Entry level projects to practice using OpenAI + LangChain
🧑🏾‍💻 Intermediate	Mid-level projects to practice using OpenAI + LangChain + Custom Knowledge base
🧑🏾‍💻 Advanced	Advanced-level projects and custom implementations of OpenAI + LangChain + Embeddings + Vectorstore Databases

HuxleyPDF - PDF Chat bot

• Upload PDF docs, ask questions, receive conversational responses about your data
• Difficulty: Beginner
• Repo: Repo
• Stack: Built in Python, Streamlit (front end), OpenAI (LLM) + Pinecone (vector database)
• Todo: Add connectiom to S3 bucket

🌟 Contributing

As an open-source project in a rapidly developing field, I welcome any contributions, whether it be in the form of updating code, better documentation, or projec to feature.

This repo and series is run by Fred Siika