13 results

We've built the best Retrieval Augmented Generation (RAG) as-a-Service anywhere - now with page-level citations! Absorb tables, PDFs, docs, links, videos or audio clips and use our synthetic data maker to generate FAQs and structured data from noisy, unstructured files. Search 1000s of files with our incredibly fast, hybrid database (finding related concepts OR specific keywords). Summarize results with OpenAI, Gemini or any open-source LLM of your choice. And finally, make informed LLM and synthetic data decisions by evaluating with your own golden data sets.

Here is our Quickstart Guide

Our benefits:

  1. Page level citations to PDFs.
  2. We understand tables and dirty PDFs!
  3. No-code UX with full API support.
  4. Use any LLM model + your own scripts to create synthetic data .
  5. Support for Google docs, sheets, etc + PDF, doc, docx, txt, links, ppt, sheets, xls, wav, mp3, mp4 and mov, including transcription and optional translation from the best speech recognition models.
  6. Links to live documents automatically re-indexed if they change
  7. Use our Golden QnA eval framework to test any workflow (especially useful for testing different embeddings + synthetic data creation prompts)
  8. Hybrid search - search for vectors, keywords or both.
  9. Cloud-based, per-API-call and per-MB pricing.

FAQ:

> Is there any AI for documentation?
Absolutely! There are now more AI tools for documentation than there are excuses to avoid writing it. Documentation is no longer the boring chore it once was. Thereโ€™s even AI that will summarize legal contracts, write technical docs, and translate your workplace guides into multiple languages (so your SOPs can finally go global, even if your coffee canโ€™t).

> Can I use AI to search a document?
Absolutely! With all the AI-powered tools out there, you can now search your documents so smartly, your files might start hiding just to make it interesting. With Gooey.AI Document AI helping you wrestle control of your PDFs, indexing your emails, and even summarizing and chatting with your files, itโ€™s like giving your documents a search partyโ€”hosted by a genius. So yes, with AI, document search is no longer hide-and-seek... it's more like hide-and-you're-already-found!

> Which AI search is free?
Gooey.AI offers AI search functions that are free if called from another workflow. Some features, like google search, can be used without an API key and do not incur cost when integrated within another Gooey.AI workflow.

> What is vector API?
A vector API is a tool or interface that allows you to store, search, and retrieve information from documents (such as PDFs, Word files, HTML, or text) by converting their content into vector embeddings. These embeddings are numerical representations of the documents' content, enabling efficient similarity searches. When a user asks a question, the vector API searches the database for the closest matching texts and retrieves relevant information, making it useful for advanced document search, chatbots, and AI copilots that need to summarize or answer questions based on large amounts of data.

> website search api
A website search API allows you to search the web or specific documents, such as PDFs and Word files, programmatically. These APIs let you call a search function, retrieve relevant results from the web or particular domains, and are often used to generate SEO-optimized content, parse top ranked sites, or enhance document search efficiency. Many platforms provide such APIs, sometimes requiring an API key, and recommend providing citation URLs when using content from search results. Additionally, these APIs can be integrated into workflows for customized web or document searches, making them useful for both general web search and targeted domain-specific queries.

> What is the best AI search to use?
The best AI search tools combine the power of advanced language models like GPT-4 with real-time web search capabilities. These solutions query Google or other search engines, then use AI to summarize and organize the resultsโ€”often providing citations for transparency. Some platforms also offer advanced features like searching within documents (PDFs, Word files), generating AI-optimized content, and supporting multiple large language models (such as GPT-4, Gemini, and Claude). Additionally, modern AI search tools can handle tasks beyond simple queries, including voice understanding, code execution, and integration with APIs, making them highly versatile for various needs.

๐Ÿ”

15.2K runs

We've built the best Retrieval Augmented Generation (RAG) as-a-Service anywhere - now with page-level citations! Absorb tables, PDFs, docs, links, videos or audio clips and use our synthetic data maker to generate FAQs and structured data from noisy, unstructured files. Search 1000s of files with our incredibly fast, hybrid database (finding related concepts OR specific keywords). Summarize results with OpenAI, Gemini or any open-source LLM of your choice. And finally, make informed LLM and synthetic data decisions by evaluating with your own golden data sets.

Our benefits:

  1. Page level citations to PDFs.
  2. We understand tables and dirty PDFs!
  3. No-code UX with full API support.
  4. Use any LLM model + your own scripts to create synthetic data.
  5. Support for Google docs, sheets, etc + PDF, doc, docx, txt, links, ppt, sheets, xls, wav, mp3, mp4 and mov
  6. Links to live documents automatically re-indexed if they change
  7. Use our Golden QnA eval framework to test any workflow (especially useful for testing different embeddings + synthetic data creation prompts)
  8. Hybrid search - search for vectors, keywords or both.
  9. Cloud-based, per-API and per MB pricing

๐Ÿ”

Enhance your search results and summary with Retreival Augemented Generation. Use vector database (vectorDB) search on documents, links, pdfs, docx, txt, and use summarize with any LLM of your choice. You can choose from several embeddings models, customize hybrid search, choose from a range of citation styles and also create synthetic data! If you are looking for a quick RAG (Retrieval Augmented Generation) tool, look no further!

๐Ÿ”

310 runs

Add your PDF, Word, HTML or Text docs, train our AI on them with OpenAI embeddings & vector search and then process results with a GPT3 script. This workflow is perfect for anything NOT in ChatGPT: 250-page compliance PDFs, training manuals, your diary, etc.

๐Ÿ”

Add your PDF, Word, HTML or Text docs, train our AI on them with OpenAI embeddings & vector search and then process results with a GPT3 script. This workflow is perfect for anything NOT in ChatGPT: 250-page compliance PDFs, training manuals, your diary, etc.

๐Ÿ”

Add your PDF, Word, HTML or Text docs, train our AI on them with OpenAI embeddings & vector search and then process results with the LLM script and engine of your choice.

๐Ÿ”

Aimed at Indian Chili farmers, this bot parses 4 documents representing best practices from the Indian Ministry of Culture and Digital Green's work to collect common questions from Indian Chili farmers. We then load these as text embeddings and then run the GPT3 script below to create an answer to the farmer's question, giving citations back to the source documents.

๐Ÿ”

Here's how you can do this for your own account:

  1. Request your twitter archive
  2. Download archive, unzip, and open Your archive.html in Chrome.
  3. Go to the tweets section and scroll to the bottom.
  4. Save page as html (Web Page, Complete)
  5. Upload it here

๐Ÿ”

96 runs

Here we use the WHOโ€™s 180 page guide to antenatal care for pregnancies and then can ask any question to receive simple, referenced answers. https://www.who.int/publications-detail-redirect/9789241549912

๐Ÿ”

Add your PDF, Word, HTML or Text docs, train our AI on them with OpenAI embeddings & vector search and then process results with a GPT3 script. This workflow is perfect for anything NOT in ChatGPT: 250-page compliance PDFs, training manuals, your diary, etc.

๐Ÿ”

Here we downloaded a webpage into a PDF and then

  1. Parse the PDF into openai embeddings
  2. Search the PDF for "What are the most interesting aspects of this character?"
  3. Add the results into a GPT3 script that is asked to generate a poll from the most interesting aspects.

๐Ÿ”

Add your PDF, Word, HTML or Text docs, train our AI on them with OpenAI embeddings & vector search and then process results with a GPT3 script. This workflow is perfect for anything NOT in ChatGPT: 250-page compliance PDFs, training manuals, your diary, etc.

๐Ÿ”

Here we feed our workflow an SEC filing and then have it output structured data about the company.

๐Ÿ”