Update docs

README.md

@@ -10,7 +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
+- **Reranking**: Default search 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
@@ -50,8 +50,8 @@ async with HaikuRAG("database.db") as client:
     # Add document
     doc = await client.create_document("Your content")
 
-    # Search (with optional reranking)
+    # Search (reranking enabled by default)
-    results = await client.search("query", rerank=True)
+    results = await client.search("query")
     for chunk, score in results:
         print(f"{score:.3f}: {chunk.content}")
 

docs/configuration.md

@@ -105,12 +105,17 @@ 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.
+Reranking is **enabled by default** and 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.
+
+If you use the default reranked (running locally), it can slow down searching significantly. To disable reranking for faster searches:
+
+```bash
+RERANK=false
+```
 
 ### MixedBread AI (Default)
 
 ```bash
-RERANK=true
 RERANK_PROVIDER="mxbai"
 RERANK_MODEL="mixedbread-ai/mxbai-rerank-base-v2"
 ```
@@ -126,7 +131,6 @@ 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"

docs/index.md

@@ -1,13 +1,13 @@
 # haiku.rag
 
-`haiku.rag` is a Retrieval-Augmented Generation (RAG) library built to work on SQLite alone without the need for external vector databases. It uses [sqlite-vec](https://github.com/asg017/sqlite-vec) for storing the embeddings and performs semantic (vector) search as well as full-text search combined through Reciprocal Rank Fusion. Both open-source (Ollama) as well as commercial (OpenAI, VoyageAI) embedding providers are supported.
+`haiku.rag` is a Retrieval-Augmented Generation (RAG) library built to work on SQLite alone without the need for external vector databases. It uses [sqlite-vec](https://github.com/asg017/sqlite-vec) for storing the embeddings and performs semantic (vector) search as well as full-text search combined through Reciprocal Rank Fusion. Both open-source (Ollama, MixedBread AI) as well as commercial (OpenAI, VoyageAI) embedding providers are supported.
-
 
 ## Features
 
 - **Local SQLite**: No need to run additional servers
 - **Support for various embedding providers**: Ollama, VoyageAI, OpenAI or add your own
 - **Hybrid Search**: Vector search using `sqlite-vec` combined with full-text search `FTS5`, using Reciprocal Rank Fusion
+- **Reranking**: Optional result reranking with MixedBread AI or Cohere
 - **Question Answering**: Built-in QA agents using Ollama, OpenAI, or Anthropic.
 - **File monitoring**: Automatically index files when run as a server
 - **Extended file format support**: Parse 40+ file formats including PDF, DOCX, HTML, Markdown, audio and more. Or add a URL!
@@ -34,7 +34,7 @@ async with HaikuRAG("database.db") as client:
     results = await client.search("query")
 
     # Ask questions
-    answer = await client.ask("Who is the author of haiku.rag?")
+    answer = await client.ask("Who is the author of haiku.rag?", rerank=False)
 ```
 
 Or use the CLI:

docs/python.md

@@ -76,7 +76,9 @@ async for doc_id in client.rebuild_database():
 
 ## Searching Documents
 
-Basic search:
+The search method performs hybrid search (vector + full-text) with **reranking enabled by default** for improved relevance:
+
+Basic search (with reranking):
 ```python
 results = await client.search("machine learning algorithms", limit=5)
 for chunk, score in results:
@@ -90,7 +92,8 @@ With options:
 results = await client.search(
     query="machine learning",
     limit=5,  # Maximum results to return
-    k=60      # RRF parameter for reciprocal rank fusion
+    k=60,     # RRF parameter for reciprocal rank fusion
+    rerank=False  # Disable reranking for faster search
 )
 
 # Process results

src/haiku/rag/config.py

@@ -19,7 +19,7 @@ class AppConfig(BaseModel):
     EMBEDDINGS_MODEL: str = "mxbai-embed-large"
     EMBEDDINGS_VECTOR_DIM: int = 1024
 
-    RERANK: bool = False
+    RERANK: bool = True
     RERANK_PROVIDER: str = "mxbai"
     RERANK_MODEL: str = "mixedbread-ai/mxbai-rerank-base-v2"