Alternatives and similar repositories for scrapy-ai

Users that are interested in scrapy-ai are comparing it to the libraries listed below

• spider-rs / spider-py
  Spider ported to Python
  ☆97Updated 9 months ago
• zzstoatzz / raggy
  scraping and querying documents for LLMs
  ☆24Updated last month
• islamshahil / Text-To-SQL-Using-GPT-3
  Taking Normal Text as Input and Generating SQL commands using the OpenAI's GPT-3
  ☆15Updated 5 years ago
• repollo / llm_data_parser
  This is a proof-of-concept of using an LLM to find and extract meaningful data without parsing the html too much.
  ☆30Updated 2 years ago
• AnswerDotAI / fastsql
  ☆62Updated 7 months ago
• inngest / inngest-py
  Python SDK for Inngest: Durable functions and workflows in Python, hosted anywhere
  ☆148Updated last week
• zytedata / zyte-spider-templates-project
  ☆20Updated 7 months ago
• blairhudson / fastapi-agents
  A FastAPI extension for integrating common AI agent frameworks.
  ☆45Updated 9 months ago
• adbar / courlan
  Clean, filter and sample URLs to optimize data collection – Python & command-line – Deduplication, spam, content and language filters
  ☆150Updated 3 weeks ago
• gormlabenz / topcast
  ☆22Updated last year
• jrieke / fastapi-csv
  🏗️ Create APIs from CSV files within seconds, using fastapi
  ☆79Updated 4 years ago
• PublicDataWorks / verdad
  https://verdad.app
  ☆83Updated last week
• browserbase / sdk-python
  Python SDK for Browserbase
  ☆69Updated last week
• zytedata / zyte-spider-templates
  Spider templates for automatic crawlers.
  ☆32Updated last month
• airtai / faststream-gen
  The faststream-gen library uses advanced AI to generate FastStream code from user descriptions, speeding up FastStream app development.
  ☆48Updated last year
• ContextData / VectorETL
  Build super simple end-to-end data & ETL pipelines for your vector databases and Generative AI applications
  ☆104Updated last year
• tsterbak / promptmage
  simplifies the process of creating and managing LLM workflows.
  ☆112Updated last year
• amosgyamfi / awesome-fasthtml
  Awesome and Best FastHTML Resources For Python Developers
  ☆75Updated last year
• JSv4 / Python-Redlines
  Docx tracked change redlines for the Python ecosystem.
  ☆87Updated last year
• ispras / scrapy-puppeteer
  Library that helps use puppeteer in scrapy.
  ☆52Updated 3 months ago
• Query-farm / openprompt
  DuckDB Community Extension to prompt LLMs from SQL
  ☆51Updated last month
• langchain-ai / competitor-analysis-bot
  Example LangGraph flow that does "competitor analysis" on the web.
  ☆37Updated last year
• trancethehuman / factory-pattern-vectorstore-interface
  A pattern to let you try several vector databases and change a little code as possible
  ☆38Updated 2 years ago
• duriantaco / pykomodo
  A Python-based parallel file chunking system designed for processing large codebases into LLM-friendly chunks.
  ☆45Updated 3 months ago
• datasette / datasette-extract
  Import unstructured data (text and images) into structured tables
  ☆159Updated last week
• langstruct-ai / langstruct
  Extract structured data from any content using LLMs.
  ☆55Updated last week
• msoedov / vector_lake
  S3 vector database for LLM Agents and RAG.
  ☆49Updated 2 years ago
• AnswerDotAI / FastHTML-Gallery
  ☆104Updated 5 months ago
• etewiah / awesome-notebooklm
  A curated list of tools related to notebooklm as well as examples of great podcasts generated by notebooklm
  ☆88Updated last year
• callmephilip / html2ft
  Visual Studio Code extension to convert HTML to FastHTML FT
  ☆21Updated 8 months ago