Skip to content
SPECIFICTION
Get listed

Dataherald vs Florentine.ai

Dataherald

github.com

Florentine.ai

florentine.ai

Side by side

FigureDataheraldFlorentine.ai
Price from—€39/mo
Free plan—Yes
Free trial—Yes
Open source——
WebYesYes
APIYesYes
Self-hostedYes—
Plans published03
Spec score · AI Database Assistants7.7 (#11)8.2 (#5)
Intended usersThe documentation is intended for developers building natural-language interfaces from structured data in their own projects and contributors to the engine.The site describes use by support teams, business analysts, internal search tools, recommendation engines, and teams querying databases.

Plans

Dataherald

No plans published.

Dataherald pricing →

Florentine.ai

  • FreeFree
  • Pro€39 a month
  • Enterprise€149 a month

Florentine.ai pricing →

In their own words

Dataherald

Dataherald is an open-source natural language-to-SQL engine that exposes an API for asking questions about relational data in plain English. Its stated uses include helping business users query warehouses, embedding data Q&A in SaaS products, and creating ChatGPT plug-ins for proprietary data. The project targets developers building natural-language interfaces or contributing to the engine. Self-hosting uses Docker, with MongoDB in a separate container for application data. Listed warehouse connections are PostgreSQL, BigQuery, Databricks, and Snowflake. Included SQL-generation approaches are LangChain SQL Agent, LangChain SQL Chain, LlamaIndex SQL Generator, and Dataherald SQL Agent. A context store can include business and database details, validated question-and-SQL examples, and table information; active learning from usage is also described. An evaluator assigns confidence scores to generated SQL. The modular architecture allows implementations to be changed through .env configuration. Startup requires an OpenAI API key, organization ID, and encryption key. Connection data is encrypted before Mongo storage. The repository uses Apache-2.0 licensing.

Visit github.com

Florentine.ai

Florentine.ai lets people ask questions of MongoDB and MySQL data in natural language, without writing queries themselves. It connects to MongoDB Atlas, MongoDB Community Edition, and MySQL using connection strings, then analyzes table and collection schemas to guide query generation. It produces MongoDB aggregation pipelines or SQL according to the database. Users may receive raw queries, results, or natural-language answers, and can choose whether read-only queries run automatically or wait for review. It supports MongoDB vector search and semantic re-ranking for MySQL using a self-hosted embedding model. OpenAI, Deepseek, Google, and Anthropic are available as bring-your-own-key LLM providers. An MCP server and API include guides for Claude, ChatGPT, and Cursor. The cloud service is aimed at support teams, business analysts, internal search tools, recommendation engines, and others querying databases. Free supports one database, five active collections or tables, and 500 requests monthly. Pro costs €39.00 per month; Enterprise costs €149.00 per month.

Visit florentine.ai