Sumit Datta
Sumit Datta
As a user of Dwata, I would like to be able to connect to SQLite databases, read schema and data from them. i would like Dwata to provide schema information...
As a user of Dwata I would like to able to read both data and structure of CSV files.
As a user I would like to generate embedding for my text sources. Text from Markdown files will have some structure which may be useful internally. # Engineering notes We...
As a user I would like to store embedding into a vector databases. # Engineering notes We can use Qdrant and SQLite-vss as options. SQLite-vss would make immediate sense since...
As a user I would like to import Markdown files, for example from my company documentation. A folder containing Markdown files should become a data source.
As a user I would like to use Replicate API for public language models and embeddings. Links: - https://replicate.com/pricing - https://replicate.com/collections/language-models - https://replicate.com/collections/embedding-models
As a use I would like to use libraries like `SentenceTransformers` and this should use my local Python installation with a virtual environment for Dwata. If Python is not available,...
As a potential user, I would like the website of Dwata to tell me clearly about the problem(s) that Dwata is trying to solve. The website should highlight use-cases, example...
As a use I would to use the embeddings in a chat with AI models and get good quality answers. The questions will be related to usage of programming languages...