Alex f8bdf998ac Add document extraction tool using Docling ...

Add a document extractor tool with an extract_document action that converts an
input artifact (PDF, docx, pptx, ...) into structured JSON by running a fixed
Docling program in the sandbox (the document and parameters travel as data, so
nothing in them can execute). Output is a compact payload bounded by an input
size cap, a head-and-tail markdown window, and per-table caps, can be validated
against a JSON schema, and is persisted as a data artifact by reference. Docling
is heavy, so it stays out of the base image and ships in an opt-in sandbox image
variant.

2026-06-24 12:50:45 +01:00

..

models

fix: tool calls on free model

2026-06-16 10:50:33 +01:00

__init__.py

Added settings file

2023-04-29 15:40:55 +01:00

db_uri.py

feat: init pg migration

2026-04-12 00:07:24 +01:00

json_schema_utils.py

fix: mini workflow fixes

2026-02-22 11:10:42 +00:00

log_context.py

feat: better logging

2026-04-28 00:14:43 +01:00

logging_config.py

feat: better logging

2026-04-28 00:14:43 +01:00

model_registry.py

feat: BYOM (#2433)

2026-04-27 22:09:33 +01:00

model_settings.py

Merge origin/main into responses-api

2026-06-03 14:03:15 +01:00

model_utils.py

feat: BYOM (#2433)

2026-04-27 22:09:33 +01:00

model_yaml.py

Merge origin/main into responses-api

2026-06-03 14:03:15 +01:00

settings.py

Add document extraction tool using Docling

2026-06-24 12:50:45 +01:00

shutdown.py

feat: better shutdowns

2026-06-08 15:07:31 +01:00

url_validation.py

Patches (#2218)

2025-12-24 17:05:35 +02:00