LLM Team integration: extract mode processes 8 conversations

Browse Source

- process_knowledge.py: routes PDF content through devop.live /api/run
- Uses extract mode: LLM extracts facts/entities/relationships, verifier checks
- 543 extractions (279 facts, 264 entities) from 8 conversations
- 60 verified entries from gemma2 cross-checking
- All stored as queryable Parquet (processed_extractions, processed_validated)
- Streaming SSE parsing for LLM Team responses
- This proves the architecture: Lakehouse storage + devop.live processing

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

...

This commit is contained in:

root

2026-03-28 00:22:29 -05:00

co-authored by Claude Opus 4.6

parent bd68b662b7

commit 3f19ad5d93

5 changed files with 279 additions and 0 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

data/datasets/processed_extractions.parquet

BIN

Binary file not shown.