By Jesus Jiménez and Aaron Boxerman from NYT World https://ift.tt/owcQ6XO
via IFTTT
Friday, 31 May 2024
Thursday, 30 May 2024
Wednesday, 29 May 2024
Tuesday, 28 May 2024
Monday, 27 May 2024
New best story on Hacker News: Instead of “auth”, we should say “permissions” and “login”
Instead of “auth”, we should say “permissions” and “login”
391 by tambourine_man | 224 comments on Hacker News.
391 by tambourine_man | 224 comments on Hacker News.
Sunday, 26 May 2024
Saturday, 25 May 2024
New best story on Hacker News: Show HN: We open sourced our entire text-to-SQL product
Show HN: We open sourced our entire text-to-SQL product
416 by aazo11 | 136 comments on Hacker News.
Long story short: We (Dataherald) just open-sourced our entire codebase, including the core engine, the clients that interact with it and the backend application layer for authentication and RBAC. You can now use the full solution to build text-to-SQL into your product. The Problem: modern LLMs write syntactically correct SQL, but they struggle with real-world relational data. This is because real world data and schema is messy, natural language can often be ambiguous and LLMs are not trained on your specific dataset. Solution: The core NL-to-SQL engine in Dataherald is an LLM based agent which uses Chain of Thought (CoT) reasoning and a number of different tools to generate high accuracy SQL from a given user prompt. The engine achieves this by: - Collecting context at configuration from the database and sources such as data dictionaries and unstructured documents which are stored in a data store or a vector DB and injected if relevant - Allowing users to upload sample NL <> SQL pairs (golden SQL) which can be used in few shot prompting or to fine-tune an NL-to-SQL LLM for that specific dataset - Executing the SQL against the DB to get a few sample rows and recover from errors - Using an evaluator to assign a confidence score to the generated SQL The repo includes four services https://ift.tt/Z9p7M36 : 1- Engine: The core service which includes the LLM agent, vector stores and DB connectors. 2- Admin Console: a NextJS front-end for configuring the engine and observability. 3- Enterprise Backend: Wraps the core engine, adding authentication, caching, and APIs for the frontend. 4- Slackbot: Integrate Dataherald directly into your Slack workflow for on-the-fly data exploration. Would love to hear from the community on building natural language interfaces to relational data. Anyone live in production without a human in the loop? Thoughts on how to improve performance without spending weeks on model training?
416 by aazo11 | 136 comments on Hacker News.
Long story short: We (Dataherald) just open-sourced our entire codebase, including the core engine, the clients that interact with it and the backend application layer for authentication and RBAC. You can now use the full solution to build text-to-SQL into your product. The Problem: modern LLMs write syntactically correct SQL, but they struggle with real-world relational data. This is because real world data and schema is messy, natural language can often be ambiguous and LLMs are not trained on your specific dataset. Solution: The core NL-to-SQL engine in Dataherald is an LLM based agent which uses Chain of Thought (CoT) reasoning and a number of different tools to generate high accuracy SQL from a given user prompt. The engine achieves this by: - Collecting context at configuration from the database and sources such as data dictionaries and unstructured documents which are stored in a data store or a vector DB and injected if relevant - Allowing users to upload sample NL <> SQL pairs (golden SQL) which can be used in few shot prompting or to fine-tune an NL-to-SQL LLM for that specific dataset - Executing the SQL against the DB to get a few sample rows and recover from errors - Using an evaluator to assign a confidence score to the generated SQL The repo includes four services https://ift.tt/Z9p7M36 : 1- Engine: The core service which includes the LLM agent, vector stores and DB connectors. 2- Admin Console: a NextJS front-end for configuring the engine and observability. 3- Enterprise Backend: Wraps the core engine, adding authentication, caching, and APIs for the frontend. 4- Slackbot: Integrate Dataherald directly into your Slack workflow for on-the-fly data exploration. Would love to hear from the community on building natural language interfaces to relational data. Anyone live in production without a human in the loop? Thoughts on how to improve performance without spending weeks on model training?
Friday, 24 May 2024
Thursday, 23 May 2024
Wednesday, 22 May 2024
Tuesday, 21 May 2024
Monday, 20 May 2024
Sunday, 19 May 2024
Saturday, 18 May 2024
Friday, 17 May 2024
Thursday, 16 May 2024
Wednesday, 15 May 2024
Blinken Warns Fighting Could Undo Aid Gains in Gaza
By Adam Rasgon, Aaron Boxerman, Michael Crowley and Thomas Fuller from NYT World https://ift.tt/4CL9xYf
via IFTTT
Tuesday, 14 May 2024
U.K. Summons Chinese Ambassador for Reprimand as Tensions Rise
By Stephen Castle, Mara Hvistendahl and Megan Specia from NYT World https://ift.tt/05z4AeL
via IFTTT
Monday, 13 May 2024
Sunday, 12 May 2024
Saturday, 11 May 2024
As Israel Steps Up Attacks, 300,000 Gazans Are on the Move
By Raja Abdulrahim, Bilal Shbair, Aaron Boxerman and Ben Shpigel from NYT World https://ift.tt/FXseop5
via IFTTT
