Cohere Models Scraper

Google Gemini Models Scraper

automation-lab/google-gemini-models-scraper

Scrapes the Google Gemini API pricing page and returns structured data on all Gemini models including paid tier input/output prices per 1M tokens, context caching pricing, grounding pricing, and available tiers (standard, batch, flex, priority).

AWS Bedrock Models Scraper

automation-lab/aws-bedrock-models-scraper

Scrapes the full AWS Bedrock model catalog from the official AWS documentation. Returns all foundation models available on Amazon Bedrock with provider name, model name, model card URL, and optionally detailed specs from each model card page.

Pinecone Integration

apify/pinecone-integration

This integration transfers data from Apify Actors to a Pinecone and is a good starting point for a question-answering, search, or RAG use case.

Qdrant Integration

apify/qdrant-integration

Transfer data from Apify Actors to a Qdrant vector database.

Weaviate Integration

apify/weaviate-integration

This integration transfers data from Apify Actors to a Weaviate and is a good starting point for a question-answering, search, or RAG use case.

Rag Embedding Generator

labrat011/rag-embedding-generator

Generate vector embeddings from text or chunked datasets using OpenAI or Cohere. Chains with RAG Content Chunker for end-to-end RAG pipelines. Outputs raw vectors ready for any vector database.

RAG Pipeline

labrat011/rag-pipeline

One-click RAG pipeline: chunks text, generates embeddings, and stores vectors in Pinecone or Qdrant. Provide your content and API keys -- the orchestrator handles the rest.

Chroma Integration

apify/chroma-integration

This integration transfers data from Apify Actors to a Chroma and is a good starting point for a question-answering, search, or RAG use case.

PubMed Scraper for RAG: Papers as Chunked JSON

devanshlive/pubmed-rag-extractor

Scrape PubMed citations by search term, MeSH, and article type. Returns RAG-ready JSON with full-text chunks from PMC Open Access (cl100k_base, 512/50) and abstract fallback. Drop-in for LangChain, LlamaIndex, Qdrant, Pinecone, Weaviate, pgvector. Skip GROBID / Pubmed Parser. $0.02 per paper.

bioRxiv + medRxiv Scraper for RAG

devanshlive/biorxiv-medrxiv-rag-extractor

Scrape bioRxiv and medRxiv preprints by server, category, and date range. Returns RAG-ready JSON with JATS full-text chunks (cl100k_base, 512/50) when available and abstract fallback otherwise. Drop-in for LangChain, LlamaIndex, Qdrant, Pinecone, Weaviate, pgvector. $0.02 per preprint.