Browse the library

7 entries match.

LlamaIndexIntegrationConfig

Ask questions about your own documents with an agent

Index the files in a folder with LlamaIndex and let an OpenAI agent answer questions about them, in Python.

AgentsEmbeddings

Voyage AIPro archiveIntegrationPaste

Find the document that answers a question with Voyage embeddings

Embed a few documents and a question with voyage-4-large in Python, then print the closest document.

EmbeddingsSearch

SupabasePro archiveIntegrationBuild

Give your chatbot memory of your docs with Supabase vector search

Store your documents as gte-small embeddings in Supabase pgvector and find the most relevant passages for any question from Node.

Free tier: 500 MB database, 50,000 MAUsFrom $25/month (Pro)

EmbeddingsSearch

ChromaPro archiveIntegrationPaste

Give your AI a memory on your own disk with Chroma

Store a few notes in a Chroma database folder on your disk and search them by meaning from one Python script. No cloud, no API key.

EmbeddingsSearch

Mistral AIPro archiveSnippetPaste

Generate mistral-embed vectors and compare them in Python

Create 1024-dim embeddings with mistral-embed and score similarity between texts for search or dedupe.

Free tier: No, API needs pay-as-you-goFrom $0.70 per 1M input tokens

EmbeddingsSearch

FirecrawlPro archiveIntegrationPaste

Crawl a website into markdown for RAG with Firecrawl

Crawl a docs site or blog and get clean markdown plus metadata for every page, ready to chunk and embed in your RAG pipeline.

Free tier: YesFrom $16/month

AutomationEmbeddings

PineconePro archiveIntegrationBuild

Semantic search over your own text with Pinecone

Chunk text, embed it with Pinecone's hosted llama-text-embed-v2 model, and query by meaning. No separate embedding provider.

Free tier: YesFrom $20/month

EmbeddingsSearch