"A logical conclusion or consequence of facts." - Wiktionary
With SEQUITUR, you can Import your CSV, XLS, or MySQL dump files and ask questions using Natural Language. SEQUITUR will construct the appropriate query from your question, execute it and create a meaningful narrative on the results, enhanced with what it already knows about the topic. It can also create insightful charts based on answers.
The product is currently in demo mode and we are collecting enhancement requests and usage examples to improve it. Access the SEQUITUR page here.
After all, a Symphony is a complex workflow of musical notes flowing in harmony
A platform developed from an open framework to help AI researchers and developers to rapidly prototype, test and deploy workflows that include machine learning models as worker components. The workflow can be invoked on command line or web service, as well as integrated into UX/UI as part of a larger intelligent solution.
Early Github access to this platform and experiments:
Code branch: https://github.com/2ndthoughts/symphonyGPT/tree/Early-Access-3
Release: https://github.com/2ndthoughts/symphonyGPT/releases/tag/EA3
This release introduces automatic embeddings using chromaDB for all API extractor classes. What this means is that large document retrievals in RAG symphonies now all have the advantage of using embeddings to not only pick relevant sections of a large API retrieval, but also pick relevant individual retrievals by rank. As a result, you get more accurate RAG that reads entire retrieved documents.
In this release, we also added an API extractor called WikipediaExtractor that, as you may have guessed, searches wikipedia using your prompt, and retrieves pertinent articles to flow into your LLM models for summarizing or additional generative activities.
As usual, contact us at dev@2ndthoughts.ai for any questions, or post in this forum if you need help setting up or have an idea on how to improve symphonies. Cheers.
We believe in an open and collaborative effort to create a platform to promote applications that deploy machine learning capabilities to benefit the scientific as well as business communities.
We do not believe in investing our efforts to build monolithic, expensive super machine models to solve problems. Instead we focus on an architecture that allows diversified and re-usable AI models and code to coexist and interoperate to solve the world's hardest problems, quickly.
Sign up to get notified about our product releases and company news
Copyright © 2024 2ndThoughts LLC - All Rights Reserved.
Powered by GoDaddy