GraphCanon updated 2w · GitHub synced 2w
Decision brief
Filco enhances context filtering for retrieval-augmented generation tasks like dialog-generation and question-answering by integrating with Dense Passage Retriever for precise passage retrieval.
Good fit when
- When developing applications requiring accurate and relevant context extraction, such as refined conversational agents
- For projects that benefit from preprocessed datasets with top-relevant passages for training
Avoid when
- If you need a general-purpose context generation tool without advanced passage retrieval capabilities
- For tasks that do not depend on preexisting Wikipedia-based or similar text corpus retrieval mechanisms
Observed Jul 12, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Dormant (846d since push)
- As of 2w
- Provenance
- Not a fork · Personal account
- As of 2w
- Security (OSV)
- 1 critical, 5 high, 12 medium, 28 low (1 critical, 5 high, 12 medium, 28 low)
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install filcoSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
A tool for improving context filtering in retrieval-augmented generation tasks such as dialog-generation and question-answering.
Capability facts
- Languages
- python
Source: github.language · Aug 1, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Aug 1, 2026)
pip install -r requirements.txtSource link
Tags
README
Install
Install all required libraries by running
pip install -r requirements.txt
Retrieve top relevant Wikipedia passages using Dense Passage Retriever (DPR)
and store into the ./datasets/${name} directory. We also provide preprocessed datasets with top-5 retrieved passages (here).
We specify ${name} for six datasets with ['nq', 'tqa', 'hotpotqa', 'fever', 'wow'] in following example commands.
For agents
This page has a .md twin and JSON over the API.