Blendsql

Given a set of values from a database, answer the question row-by-row, in order.
Your outputs should be separated by ';'.

Question: Size in km2?
Source table: parks
Source column: Area

Values:

Of course, the effects of this async processing will be felt more when we need to pass *many* values to the `LLMMap` function.

**Full Changelog**: https://github.com/parkervg/blendsql/compare/v0.0.27...v0.0.28

import blendsql` was taking a while - this release just makes imports lazier, to speed things up.

BlendSQL now supports 100+ model providers via [LiteLLM](https://github.com/BerriAI/litellm)!

python
import blendsql
from blendsql.models import LiteLLM

Use LiteLLM to load many different model providers
model = LiteLLM('gemini/gemini-2.0-flash-exp')
model = LiteLLM('openai/gpt-4o')
model = LiteLLM('anthropic/claude-3-5-sonnet-20241022')



What's Changed
* Add Gemini Support to BlendSQL by rohitkhoja in https://github.com/parkervg/blendsql/pull/36
* Switching to LiteLLM by parkervg in https://github.com/parkervg/blendsql/pull/37
* Pinning version requirements, to ensure compatibility

New Contributors
* rohitkhoja made their first contribution in https://github.com/parkervg/blendsql/pull/36

**Full Changelog**: https://github.com/parkervg/blendsql/compare/v0.0.31...v0.0.32

Bugfixes from previous release.

We need to set `--prerelease=allow` to use the `guidance` AzurePhi serverside control.

**Full Changelog**: https://github.com/parkervg/blendsql/compare/v0.0.30...v0.0.31

🧠 Smarter `LLMQA` with `modifier` Arg
As described in [blendsql-by-example.ipynb](https://github.com/parkervg/blendsql/blob/main/examples/blendsql-by-example.ipynb), `LLMQA` can now generate constrained lists. This means the following query is valid:

python
SELECT * FROM People
WHERE People.Name IN {{LLMQA('First 3 presidents of the U.S?')}}


Or, even pseudo-agent-based processing like this:

python
WITH letter_agent_output AS (
SELECT * FROM (VALUES {{LLMQA('List some greek letters', modifier='{3}')}})
) SELECT {{
LLMQA(
'What is the first letter of the alphabet?',
options=(SELECT * FROM letter_agent_output)
)}}


Additionally, the `AzurePhi` model allows for easy constrained decoding with a larger model, powered by guidance's server-side Azure AI integration: https://github.com/guidance-ai/guidance?tab=readme-ov-file#azure-ai

What's Changed
* `_dialect.py` Re-Work, `modifier` Argument for `LLMQA`, Documentation updates by parkervg in https://github.com/parkervg/blendsql/pull/35


**Full Changelog**: https://github.com/parkervg/blendsql/compare/v0.0.29...v0.0.30