Home/Data & Retrieval/filco

filco

zorazrw/filco

Learning to Filter Context for Retrieval-Augmented Generation

GitHub Website

GraphCanon updated Sep 20, 2026 · GitHub synced Sep 20, 2026

24views this month

199 stars20 forksLast push Apr 6, 2024 Python CC-BY-SA-4.0

Decision brief

Filco is a Python-based project that focuses on dialog generation, fact verification, and question answering using models like Flan-T5 and LLaMA2, with Dense Passage Retriever for retrieving relevant Wikipedia passages.

Good fit when

When you need to generate dialogues that require fact verification and question answering capabilities, leveraging models like Flan-T5 and LLaMA2.
If your project involves retrieval-augmented generation and you want to use preprocessed datasets with top-5 retrieved passages from Wikipedia.

Avoid when

If your project does not require the use of Flan-T5 or LLaMA2 models for dialog generation, fact verification, or question answering.
When you do not need to retrieve relevant Wikipedia passages using Dense Passage Retriever.

Observed Sep 18, 2026 · Source: enrich:decision_facts

filco alternatives Trust report

Verify the decision

Maintenance and security

Full trust report

Maintenance: Dormant (894d since push); As of Sep 18, 2026
Provenance: Not a fork · Personal account; As of Sep 18, 2026
Security (OSV): 1 critical, 7 high, 12 medium, 32 low (1 critical, 7 high, 12 medium, 32 low); As of Sep 18, 2026

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

pip install filco

PyPI

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

prompt-in-context-learning

Resources for in-context learning and prompt engineering with LLMs like ChatGPT and GPT-3

2.2k★

rag-fusion

multi-query generation + Reciprocal Rank Fusion for retrieval-augmented generation

958★

RAG-FiT

Framework for enhancing LLMs for RAG tasks using fine-tuning

768★

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

A Python-based project focusing on dialog generation, fact verification, and question answering using models like Flan-T5 and LLaMA2. It employs Dense Passage Retriever for retrieving relevant Wikipedia passages.

Capability facts

Languages: python
Source: github.language · Sep 18, 2026

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Python runtimePython

Source: README excerpt (regex_v1, Sep 18, 2026)

pip install -r requirements.txt

Source link

README

Install Install all required libraries by running Retrieve top relevant Wikipedia passages using Dense Passage Retriever (DPR) and store into the directory. We also provide preprocessed datasets with top 5 retrieved passages (here). We specify for six datasets with ['nq', 'tqa',...

For agents

This page has a .md twin and JSON over the API.

/tools/zorazrw-filco.md GET /api/graphcanon/tools/zorazrw-filco GET /api/graphcanon/graph?tool=zorazrw-filco