Local Vector DB, from user input, from urls, from files

Показать описание

We will build a local vector db using OpenAI ADA-002 embeddings from user input, from a list of urls and from files in a folder. We will use langchain for text splitting and embedding

Code files are available to download for Patreon members along with 100+ other projects' files:

Search 140+ echohive videos and code download links:

LLM Paper Summaries:

Try the GPT-4 Auto Coder app:

Chat with us on Discord:

GPT-4 web UI:

CHAPTERS:
00:00 intro
00:16 vectordb from user input
01:18 vectordb from urls
02:28 vectordb from files
02:40 code review of tools
05:08 echohive stuff

#openaiapi #vectordb #gpt4 #pythonprojects #langchain

echohive

Рекомендации по теме

Комментарии

Code files are available to download for Patreon members along with 100+ other projects' files:

Search 140+ echohive videos and code download links:

LLM Paper Summaries:

Try the GPT-4 Auto Coder app:

Chat with us on Discord:

GPT-4 web UI:

echohive

This is awesome! So let me get this straight! You can use chat history, external files and website urls, embed them all into the same database and then query that database if needed for the relevant info using cosine similarity? Is there a way to separate the chat history, aka the episodic memory trace, from the text and/or website info, the declarative or semantic memory, and then attach this to a broad tool set, aka the procedural memory, to create a more general agent? Thanks again and look forward to playing with this one!!!🥳🤪🤩🦾

klammer

Next step... add a local LLM for a completely local solution.

nuclear_AI

Is this a local persistant vectorDB or in-memory vectorDB? Do you recommend using a local persistent vectorDB on PC setups?

SuryaNistala-ejjd

Local Vector DB, from user input, from urls, from files

Local Vector DB, from user input, from urls, from files

Vector databases are so hot right now. WTF are they?

Vector Databases simply explained! (Embeddings & Indexes)

How to run a private Chroma Vector Database locally in 5 mins!

OpenAI Embeddings and Vector Databases Crash Course

How Does Rag Work? - Vector Database and LLMs #datascience #naturallanguageprocessing #llm #gpt

How I built an AI Teacher with Vector Databases and ChatGPT

Vector Database Optimization with n8n: Metadata, Text Splitting, & Embeddings

Getting Started with ChromaDB - Lowest Learning Curve Vector Database For Semantic Search

2-Building Multi Agentic AI RAG With Vector Database

How LLMs use Vector Databases

Optimize RAG with AI Agents & Vector Databases

VectorAdmin | The universal GUI for vector databases

Chroma - Vector Database for LLM Applications | OpenAI integration

Vector Search RAG Tutorial – Combine Your Data with LLMs with Advanced Search

Are you doing these things to optimize your Vector Database? #artificialintelligence #n8n

Generate Text Embeddings Locally for Vector Search Databases

Postgres pgvector Extension - Vector Database with PostgreSQL / Langchain Integration

Setting Up Your Qdrant Vector Database

What is Retrieval Augmented Generation (RAG) ? Simplified Explanation

anythingllm create embed vector database with local llm easily

Level Up Your Flutter Skills 🤯

ChromaDB and SQLite

Connect Copilot to your database? #coding #ai #database