Firecrawl

Introducing Logo Tree Builder ??? Just enter a company URL to build an interactive graph of their customer network and beyond. Easily map customer relationships and visualize business connections using Firecrawl and Streamlit.

Announcing Claude 3.7 Company Researcher ?? Ask for any company's info, and it will search the web to extract structured data using Firecrawl's new /extract endpoint. Open source and powered by Claude 3.7 API & @firecrawl_dev See the code and get API keys here: https://lnkd.in/gsmQ6Epr

Excited to announce our @n8n_io integration ?? Use our all of our endpoints with one of the leading AI workflow automation platforms! Watch how easy it is to connect Firecrawl to Github Issues with n8n:

Introducing LLMs.txt generator v2 ?? You can now concatenate any website into a single text file that can be fed into any Agent or LLM. Now 10x faster powered by Firecrawl's official llmstxt endpoint!

Introducing Groq Web Crawler Bot ?? Easily scrape websites, summarize content, analyze sentiment, and extract key topics using @firecrawl_dev and @GroqInc APIs Just enter a URL, and it will scrape the entire page to deliver the output you need. Check it out: See the code and get your API keys here: https://lnkd.in/emstE66Y

Announcing AGI News powered by Claude 3.7! ?? A daily web-connected AI newsletter now powered with Anthropic's new model. It extracts the latest AGI news from the web using @firecrawl_dev + Claude 3.7, generates a newsletter, and sends it straight to your inbox! See the code and get API Keys here: https://lnkd.in/gHiqHR2d

I just built a multimodal RAG over complex webpages! (powered by locally running DeepSeek-Janus) It still feels like traditional RAG but without OCR, text extraction, broken tables, or missing images. Tech stack: - ColiVara's SOTA document understanding and retrieval to index webpages. - Firecrawl for reliable scrapping. - Hugging Face transformers to locally run DeepSeek-Janus Pro Here's an overview of our app: 1) Generate a PDF of web page screenshots with Firecrawl. 2) Index it on ColiVara for SOTA retrieval. 3) Query the ColiVara client to retrieve context. 4) Use DeepSeek Janus Pro as the LLM to generate a response. The video below gives you a quick demo of how it works. We used ColiVara, a unique document retrieval method that requires no chunking or text processing—no OCR, text extraction, broken tables, or missing images. Hassle-FREE. Link to their open-source repo: https://lnkd.in/gTCpi4Nn I have shared the code for the demo in comments. _____ Find me → Akshay Pachaar ?? For daily insights and tutorials on LLMs, RAG and AI Agents.

Excited to (re)announce AGI News! ?? A daily AI newsletter fully generated by web-connected Gemini 2.0 LLM agents. It extracts the latest AGI news from the web using Firecrawl + Gemini 2.0 Flash, generates a newsletter, and sends it straight to your inbox! See the code and get your API key here: https://lnkd.in/eN5z_Spm

Generate LLMs.txt for your websites via the CLI You can now easily create llms txt files for your website using the command line with npx. Powered by Firecrawl npx generate-llmstxt -u url

Generate an llms.txt file for any website in seconds with /llmstxt Our new Firecrawl endpoint turns any site into a single text file that can be fed into any LLM. Available now on our API and SDKs. Check out the docs here: https://lnkd.in/emV_BbAH