LangChain RAG
Skill ImethibitishwaINVOKE THIS SKILL when building ANY retrieval-augmented generation (RAG) system. Covers document loaders, RecursiveCharacterTextSplitter, embeddings (OpenAI), and vector stores (Chroma, FAISS, Pinecone).
This skill facilitates the construction of RAG pipelines by offering implementations for document loading, text splitting, embedding generation, and various vector stores including Chroma, FAISS, and Pinecone. It showcases end-to-end examples in both Python and TypeScript, detailing the setup, retrieval, and generation stages.
Documentation
- info:Configuration & parameter referenceWhile examples show configurations for chunk size, overlap, and vector stores, explicit defaults and precedence order for all parameters are not fully documented.
License
- info:License usabilityLicense is not explicitly declared in the manifest files or a dedicated LICENSE file, and is only mentioned in the README footer as 'MIT'.
Versioning
- warning:Release ManagementNo explicit version information (e.g., `version:` in SKILL.md frontmatter, `package.json`, or CHANGELOG) is present for this skill; installation via 'npx skills' or plugin marketplace does not allow for version pinning.
Code Execution
- info:ValidationWhile parameters like chunk size and overlap are shown, explicit schema validation for all inputs and outputs is not demonstrated in the provided examples.
- info:Error HandlingError handling is not explicitly demonstrated in the provided examples, though LangChain's general error handling mechanisms are assumed.
Practical Utility
- info:Edge casesFailure modes like dimension mismatch are hinted at in the 'fix' sections, but not explicitly documented with symptoms and recovery paths within the main skill instructions.
Usakinishaji
Kwanza, ongeza marketplace
/plugin marketplace add langchain-ai/langchain-skills/plugin install langchain-skills@langchain-skillsVipanuzi vinavyofanana
Building with LLMs
85Help users build effective AI applications. Use when someone is building with LLMs, writing prompts, designing AI features, implementing RAG, creating agents, running evals, or trying to improve AI output quality.
Tandem Panel Scaffold
100Scaffold an editable Tandem control panel app
ESLint Plugin React Hooks
99ESLint rules for React Hooks