Metadata-Version: 2.4
Name: dean_research_tools
Version: 0.12.0
Summary: Retriever tools package for research task and content lookup
Author-email: Dean MacGregor <powertrading121@gmail.com>
License: MIT
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Software Development :: Libraries
Requires-Python: >=3.11
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: cohere>=5.0.0
Requires-Dist: langchain-core>=0.3.0
Requires-Dist: orjson>=3.9.0
Requires-Dist: pgvector>=0.3.0
Requires-Dist: psycopg[binary]>=3.2.0
Requires-Dist: pydantic>=2.7.0
Requires-Dist: pytest-asyncio>=1.4.0
Requires-Dist: ddgs>=9.14.4
Requires-Dist: dean-utils>=0.0.83
Provides-Extra: dev
Requires-Dist: build>=1.2.2; extra == "dev"
Requires-Dist: pytest>=8.2.0; extra == "dev"
Requires-Dist: twine>=5.1.1; extra == "dev"
Requires-Dist: psycopg_pool>=3.3.1; extra == "dev"
Dynamic: license-file

# dean_research_tools

I made this library so I could use it in different environments without copying and pasting. I'm not intending to have it be used by a lot of people.

If a lot of people want to use it then that's fine, there's no secret sauce, but you're on your own.

## Browser database

Browser queries use the `ai_proj_browser` schema. Content searches read
`text_content`, join `docs` and `tasks` by `doc_id` and `task_id`, and return
`chunk_indx` as `chunk_index`. Image content is not included in these text searches.

`PGTools.queue_browser` requires a keyword-only `deployment_id` referencing
`ai_proj.models`. Pass it as
`await tools.queue_browser(research_task_id, state, browser_task, vector, deployment_id=deployment_id)`.
The task insert stores `research_task_id` but does not store `state`, which has no
column in the browser task table.
