--- title: "vectordb-recipes vs cherche" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/lancedb-vectordb-recipes-vs-raphaelsty-cherche" tools: ["lancedb-vectordb-recipes", "raphaelsty-cherche"] --- # vectordb-recipes vs cherche *GraphCanon updated Jul 12, 2026* ## Verdict Pick vectordb-recipes if vectordb-recipes offers resources and tutorials for building GenAI applications using LanceDB. It is particularly designed to help users get started quickly with minimal setup required; pick cherche if cherche is a Python library for implementing neural search capabilities. [vectordb-recipes](https://github.com/lancedb/vectordb-recipes) reports 967 GitHub stars, 171 forks, and 4 open issues, last pushed Apr 24, 2026. [cherche](https://github.com/raphaelsty/cherche) has 331 stars, 14 forks, and 4 open issues, last pushed Jun 1, 2024. Figures are from public GitHub metadata via [vectordb-recipes's repository](https://github.com/lancedb/vectordb-recipes) and [cherche's repository](https://github.com/raphaelsty/cherche). | | [vectordb-recipes](/tools/lancedb-vectordb-recipes.md) | [cherche](/tools/raphaelsty-cherche.md) | | --- | --- | --- | | Tagline | Resource, examples & tutorials for multimodal AI, RAG and agents using vector search and LLMs | Neural Search | | Stars | 967 | 331 | | Forks | 171 | 14 | | Open issues | 4 | 4 | | Language | Jupyter Notebook | Python | | Adopt for | Vectordb-recipes offers resources and tutorials for building GenAI applications using LanceDB. It is particularly designed to help users get started quickly with minimal setup required. | Cherche is a Python library for implementing neural search capabilities. | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | MIT | | Categories | AI Agents, Developer Tools, Evaluation & Observability, Model Training, Vector Databases | Data & Retrieval, Evaluation & Observability, Vector Databases | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [vectordb-recipes](/tools/lancedb-vectordb-recipes.md) | [cherche](/tools/raphaelsty-cherche.md) | | --- | --- | --- | | Maintenance | Steady (60%) | Dormant (18%) | | Days since push | 77d | 769d | | Owner type | Organization | User | | Full report | [trust report](/tools/lancedb-vectordb-recipes/trust.md) | [trust report](/tools/raphaelsty-cherche/trust.md) | ## Decision facts: vectordb-recipes - **Adopt for:** Vectordb-recipes offers resources and tutorials for building GenAI applications using LanceDB. It is particularly designed to help users get started quickly with minimal setup required. ## Decision facts: cherche - **Adopt for:** Cherche is a Python library for implementing neural search capabilities. ## Choose when ### Choose vectordb-recipes if… - vectordb-recipes is primarily Jupyter Notebook; cherche is Python. - License: vectordb-recipes is Apache-2.0, cherche is MIT. - Tags unique to vectordb-recipes: agents, ai, deep-learning, embeddings. - Also covers AI Agents, Developer Tools, Model Training. - - When you need a comprehensive set of examples, starter code and tutorials specifically optimized for LanceDB, an open-source vector database that integrates seamlessly into the Python data ecosystem ### Choose cherche if… - cherche is primarily Python; vectordb-recipes is Jupyter Notebook. - License: cherche is MIT, vectordb-recipes is Apache-2.0. - Tags unique to cherche: bm25, flashtext, information-retrieval, machine-learning. - Also covers Data & Retrieval. - Cherche is a Python library for implementing neural search capabilities. ## When NOT to use vectordb-recipes - - When seeking support for a specific competitor's vector database (like Pinecone or Weaviate), as Vectordb-recipes focuses solely on LanceDB’s ecosystem - - If you have strict requirements for custom database tuning that only vendor-specific proprietary databases can offer, as Vectordb-recipes’ focus is on leveraging the out-of-the-box advantages of an - critical_facts_for_deployment_or_use_case_specifics: [ ## 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. ## Common questions ### What is the difference between vectordb-recipes and cherche? vectordb-recipes: Resource, examples & tutorials for multimodal AI, RAG and agents using vector search and LLMs. cherche: Neural Search. See the comparison table for live GitHub stats and shared categories. ### When should I choose vectordb-recipes over cherche? Choose vectordb-recipes over cherche when vectordb-recipes is primarily Jupyter Notebook; cherche is Python; License: vectordb-recipes is Apache-2.0, cherche is MIT; Tags unique to vectordb-recipes: agents, ai, deep-learning, embeddings; Also covers AI Agents, Developer Tools, Model Training; - When you need a comprehensive set of examples, starter code and tutorials specifically optimized for LanceDB, an open-source vector database that integrates seamlessly into the Python data ecosystem. ### When should I choose cherche over vectordb-recipes? Choose cherche over vectordb-recipes when cherche is primarily Python; vectordb-recipes is Jupyter Notebook; License: cherche is MIT, vectordb-recipes is Apache-2.0; Tags unique to cherche: bm25, flashtext, information-retrieval, machine-learning; Also covers Data & Retrieval; Cherche is a Python library for implementing neural search capabilities. ### When should I avoid vectordb-recipes? - When seeking support for a specific competitor's vector database (like Pinecone or Weaviate), as Vectordb-recipes focuses solely on LanceDB’s ecosystem - If you have strict requirements for custom database tuning that only vendor-specific proprietary databases can offer, as Vectordb-recipes’ focus is on leveraging the out-of-the-box advantages of an critical_facts_for_deployment_or_use_case_specifics: [ ### 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. ### Is vectordb-recipes or cherche more popular on GitHub? vectordb-recipes has more GitHub stars (967 vs 331). Stars measure visibility, not whether either tool fits your constraints. ### Are vectordb-recipes and cherche open source? Yes - both are open-source projects on GitHub (vectordb-recipes: Apache-2.0, cherche: MIT). ### Where can I find alternatives to vectordb-recipes or cherche? GraphCanon lists graph-backed alternatives at [vectordb-recipes alternatives](/tools/lancedb-vectordb-recipes/alternatives) and [cherche alternatives](/tools/raphaelsty-cherche/alternatives) ([vectordb-recipes markdown twin](/tools/lancedb-vectordb-recipes/alternatives.md), [cherche markdown twin](/tools/raphaelsty-cherche/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/lancedb-vectordb-recipes-vs-raphaelsty-cherche.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, vectordb-recipes or cherche? vectordb-recipes: Steady. cherche: Dormant. 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 vectordb-recipes and cherche? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [vectordb-recipes trust report](/tools/lancedb-vectordb-recipes/trust); [cherche trust report](/tools/raphaelsty-cherche/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=lancedb-vectordb-recipes`](/api/graphcanon/graph?tool=lancedb-vectordb-recipes) - 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/_