---
title: "cherche vs rag-fusion"
type: "comparison"
canonical_url: "https://www.graphcanon.com/compare/raphaelsty-cherche-vs-raudaschl-rag-fusion"
tools: ["raphaelsty-cherche", "raudaschl-rag-fusion"]
---

# cherche vs rag-fusion

*GraphCanon updated Jul 12, 2026*

## Verdict

Pick cherche when tags unique to cherche: bm25, flashtext, machine-learning, natural-language-processing; pick rag-fusion when tags unique to rag-fusion: chromadb, openai, python, rag.

[cherche](https://github.com/raphaelsty/cherche) reports 331 GitHub stars, 14 forks, and 4 open issues, last pushed Jun 1, 2024. [rag-fusion](https://github.com/Raudaschl/rag-fusion) has 946 stars, 113 forks, and 0 open issues, last pushed Apr 26, 2026. Figures are from public GitHub metadata via [cherche's repository](https://github.com/raphaelsty/cherche) and [rag-fusion's repository](https://github.com/Raudaschl/rag-fusion).

| | [cherche](/tools/raphaelsty-cherche.md) | [rag-fusion](/tools/raudaschl-rag-fusion.md) |
| --- | --- | --- |
| Tagline | Neural Search | RAG-Fusion: multi-query generation + Reciprocal Rank Fusion for better retrieval-augmented generation. Includes evaluation harness with NFCorpus/BEIR. |
| Stars | 331 | 946 |
| Forks | 14 | 113 |
| Open issues | 4 | 0 |
| Language | Python | Python |
| Adopt for | Cherche is a Python library for implementing neural search capabilities. | - |
| Persona | - | - |
| Runtime | - | - |
| License | MIT | MIT |
| Categories | Data & Retrieval, Evaluation & Observability, Vector Databases | Data & Retrieval, LLM Frameworks, Vector Databases |

## Trust and health

_Sourced signals - not a safety guarantee. No winner column._

| | [cherche](/tools/raphaelsty-cherche.md) | [rag-fusion](/tools/raudaschl-rag-fusion.md) |
| --- | --- | --- |
| Maintenance | Dormant (18%) | Steady (60%) |
| Days since push | 769d | 75d |
| Open issues (now) | 4 | 0 |
| Full report | [trust report](/tools/raphaelsty-cherche/trust.md) | [trust report](/tools/raudaschl-rag-fusion/trust.md) |

## Decision facts: cherche

- **Adopt for:** Cherche is a Python library for implementing neural search capabilities.

## Choose when

### Choose cherche if…

- Tags unique to cherche: bm25, flashtext, machine-learning, natural-language-processing.
- Also covers Evaluation & Observability.
- Cherche is a Python library for implementing neural search capabilities.

### Choose rag-fusion if…

- Tags unique to rag-fusion: chromadb, openai, python, rag.
- Also covers LLM Frameworks.
- More GitHub stars (946 vs 331) - visibility, not fit.

## When NOT to use cherche

- Last GitHub push was 770 days ago (dormant maintenance, Jun 1, 2024). Validate activity before betting a new project on cherche.
- Data & Retrieval: Skip a heavy ingestion framework when your corpus is small and static; a script plus the embedding API is enough.
- Evaluation & Observability: Defer heavyweight eval infra only until you have real traffic - never skip it once users depend on answers.
- Vector Databases: Don't reach for a dedicated vector DB under ~100k vectors; pgvector on your existing Postgres is simpler to operate.

## When NOT to use rag-fusion

- Data & Retrieval: Skip a heavy ingestion framework when your corpus is small and static; a script plus the embedding API is enough.
- LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves.
- Vector Databases: Don't reach for a dedicated vector DB under ~100k vectors; pgvector on your existing Postgres is simpler to operate.

## Common questions

### What is the difference between cherche and rag-fusion?

cherche: Neural Search. rag-fusion: RAG-Fusion: multi-query generation + Reciprocal Rank Fusion for better retrieval-augmented generation. Includes evaluation harness with NFCorpus/BEIR.. See the comparison table for live GitHub stats and shared categories.

### When should I choose cherche over rag-fusion?

Choose cherche over rag-fusion when Tags unique to cherche: bm25, flashtext, machine-learning, natural-language-processing; Also covers Evaluation & Observability; Cherche is a Python library for implementing neural search capabilities.

### When should I choose rag-fusion over cherche?

Choose rag-fusion over cherche when Tags unique to rag-fusion: chromadb, openai, python, rag; Also covers LLM Frameworks; More GitHub stars (946 vs 331) - visibility, not fit.

### When should I avoid cherche?

Last GitHub push was 770 days ago (dormant maintenance, Jun 1, 2024). Validate activity before betting a new project on cherche. Data & Retrieval: Skip a heavy ingestion framework when your corpus is small and static; a script plus the embedding API is enough. Evaluation & Observability: Defer heavyweight eval infra only until you have real traffic - never skip it once users depend on answers. Vector Databases: Don't reach for a dedicated vector DB under ~100k vectors; pgvector on your existing Postgres is simpler to operate.

### When should I avoid rag-fusion?

Data & Retrieval: Skip a heavy ingestion framework when your corpus is small and static; a script plus the embedding API is enough. LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. Vector Databases: Don't reach for a dedicated vector DB under ~100k vectors; pgvector on your existing Postgres is simpler to operate.

### Is cherche or rag-fusion more popular on GitHub?

rag-fusion has more GitHub stars (946 vs 331). Stars measure visibility, not whether either tool fits your constraints.

### Are cherche and rag-fusion open source?

Yes - both are open-source projects on GitHub (cherche: MIT, rag-fusion: MIT).

### Where can I find alternatives to cherche or rag-fusion?

GraphCanon lists graph-backed alternatives at [cherche alternatives](/tools/raphaelsty-cherche/alternatives) and [rag-fusion alternatives](/tools/raudaschl-rag-fusion/alternatives) ([cherche markdown twin](/tools/raphaelsty-cherche/alternatives.md), [rag-fusion markdown twin](/tools/raudaschl-rag-fusion/alternatives.md)), ranked by typed relationship edges rather than popularity votes.

### Is there a machine-readable version of this comparison?

Yes. The markdown twin at [this comparison](/compare/raphaelsty-cherche-vs-raudaschl-rag-fusion.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers.

### Which is better maintained, cherche or rag-fusion?

cherche: Dormant. rag-fusion: Steady. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance.

### Where are the full trust reports for cherche and rag-fusion?

GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [cherche trust report](/tools/raphaelsty-cherche/trust); [rag-fusion trust report](/tools/raudaschl-rag-fusion/trust).

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon/graph?tool=raphaelsty-cherche`](/api/graphcanon/graph?tool=raphaelsty-cherche)
- LLM index: [/llms.txt](/llms.txt)
- Full corpus: [/llms-full.txt](/llms-full.txt)

_GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_