Update docs

README.md

@@ -10,6 +10,7 @@ Retrieval-Augmented Generation (RAG) library on SQLite.
 - **Multiple embedding providers**: Ollama, VoyageAI, OpenAI
 - **Multiple QA providers**: Ollama, OpenAI, Anthropic
 - **Hybrid search**: Vector + full-text search with Reciprocal Rank Fusion
+- **Reranking**: Optional result reranking with MixedBread AI or Cohere
 - **Question answering**: Built-in QA agents on your documents
 - **File monitoring**: Auto-index files when run as server
 - **40+ file formats**: PDF, DOCX, HTML, Markdown, audio, URLs
@@ -49,8 +50,8 @@ async with HaikuRAG("database.db") as client:
     # Add document
     doc = await client.create_document("Your content")
 
-    # Search
-    results = await client.search("query")
+    # Search (with optional reranking)
+    results = await client.search("query", rerank=True)
     for chunk, score in results:
         print(f"{score:.3f}: {chunk.content}")
 

docs/configuration.md

@@ -103,6 +103,35 @@ QA_MODEL="claude-3-5-haiku-20241022"  # or claude-3-5-sonnet-20241022, etc.
 ANTHROPIC_API_KEY="your-api-key"
 ```
 
+## Reranking
+
+Reranking improves search quality by re-ordering the initial search results using specialized models. When enabled, the system retrieves more candidates (3x the requested limit) and then reranks them to return the most relevant results.
+
+### MixedBread AI (Default)
+
+```bash
+RERANK=true
+RERANK_PROVIDER="mxbai"
+RERANK_MODEL="mixedbread-ai/mxbai-rerank-base-v2"
+```
+
+### Cohere
+
+For Cohere reranking, install with Cohere extras:
+
+```bash
+uv pip install haiku.rag --extra cohere
+```
+
+Then configure:
+
+```bash
+RERANK=true
+RERANK_PROVIDER="cohere"
+RERANK_MODEL="rerank-v3.5"
+COHERE_API_KEY="your-api-key"
+```
+
 ## Other Settings
 
 ### Database and Storage