@agentskit/rag
Advanced tools
+13
-3
| { | ||
| "name": "@agentskit/rag", | ||
| "version": "0.1.3", | ||
| "version": "0.1.4", | ||
| "description": "Plug-and-play retrieval-augmented generation for AgentsKit.", | ||
@@ -14,3 +14,13 @@ "keywords": [ | ||
| "retrieval", | ||
| "embeddings" | ||
| "embeddings", | ||
| "openai", | ||
| "anthropic", | ||
| "claude", | ||
| "gemini", | ||
| "chatgpt", | ||
| "ai-agents", | ||
| "vector-search", | ||
| "semantic-search", | ||
| "knowledge-base", | ||
| "chunking" | ||
| ], | ||
@@ -32,3 +42,3 @@ "type": "module", | ||
| "dependencies": { | ||
| "@agentskit/core": "1.0.0" | ||
| "@agentskit/core": "1.0.1" | ||
| }, | ||
@@ -35,0 +45,0 @@ "devDependencies": { |
+31
-10
| # @agentskit/rag | ||
|  | ||
| Plug-and-play retrieval-augmented generation: chunk documents, embed them, and retrieve the right context at query time. | ||
| ## Why | ||
| [](https://www.npmjs.com/package/@agentskit/rag) | ||
| [](https://www.npmjs.com/package/@agentskit/rag) | ||
| [](https://bundlephobia.com/package/@agentskit/rag) | ||
| [](../../LICENSE) | ||
| [](../../docs/STABILITY.md) | ||
| [](https://github.com/EmersonBraun/agentskit) | ||
| **Tags:** `ai` · `agents` · `llm` · `agentskit` · `rag` · `retrieval` · `vector-search` · `embeddings` · `ai-agents` · `semantic-search` · `knowledge-base` | ||
| ## Why rag | ||
| - **Your data, your agent** — no fine-tuning required; ingest plain text and query with natural language | ||
| - **Composable stack** — uses any `EmbedFn` and any `VectorMemory` from [`@agentskit/adapters`](https://www.npmjs.com/package/@agentskit/adapters) and [`@agentskit/memory`](https://www.npmjs.com/package/@agentskit/memory) | ||
| - **Retriever-ready** — `createRAG()` returns a [`Retriever`](https://www.npmjs.com/package/@agentskit/core) you pass to [`@agentskit/runtime`](https://www.npmjs.com/package/@agentskit/runtime) or [`useChat`](https://www.npmjs.com/package/@agentskit/react) so context is injected automatically | ||
| - **Composable stack** — uses any `EmbedFn` and any `VectorMemory` from `@agentskit/adapters` and `@agentskit/memory`; swap either layer without touching RAG logic | ||
| - **Retriever-ready** — `createRAG()` returns a `Retriever` you pass to `@agentskit/runtime` or `useChat` so context is injected automatically | ||
| - **Tune chunking without a PhD** — `chunkSize`, `chunkOverlap`, or a custom `split` function — three knobs that cover 95% of use cases | ||
@@ -57,7 +65,10 @@ ## Install | ||
| ## Next steps | ||
| ## Features | ||
| - Tune chunking with `chunkSize`, `chunkOverlap`, or a custom `split` function on `createRAG` | ||
| - Swap `fileVectorMemory` for `redisVectorMemory` or a custom `VectorMemory` for production | ||
| - Use `geminiEmbedder`, `ollamaEmbedder`, or any `(text) => Promise<number[]>` as `embed` | ||
| - `createRAG({ embed, store })` — single entry point for ingest + retrieve | ||
| - `rag.ingest(docs)` — chunk, embed, and store documents | ||
| - `rag.search(query, { topK })` — semantic similarity search | ||
| - `rag.retrieve({ query, messages })` — `Retriever` contract v1 for runtime/controller injection | ||
| - Configurable chunking: `chunkSize`, `chunkOverlap`, custom `split` | ||
| - Works with any `EmbedFn` and any `VectorMemory` | ||
@@ -74,4 +85,14 @@ ## Ecosystem | ||
| ## Contributors | ||
| <a href="https://github.com/EmersonBraun/agentskit/graphs/contributors"> | ||
| <img src="https://contrib.rocks/image?repo=EmersonBraun/agentskit" alt="AgentsKit contributors" /> | ||
| </a> | ||
| ## License | ||
| MIT — see [LICENSE](../../LICENSE). | ||
| ## Docs | ||
| [Full documentation](https://emersonbraun.github.io/agentskit/) | ||
| [Full documentation](https://www.agentskit.io) · [GitHub](https://github.com/EmersonBraun/agentskit) |
23720
5.71%97
27.63%+ Added
- Removed
Updated