From 273a3bda4f7899c73ebddb86ab2018b54b633cba Mon Sep 17 00:00:00 2001
From: Yiorgis Gozadinos <ggozadinos@gmail.com>
Date: Sat, 28 Jun 2025 09:37:59 +0300
Subject: [PATCH] Document QA

---
 README.md             |  8 ++++++++
 docs/cli.md           |  9 +++++++++
 docs/configuration.md | 47 +++++++++++++++++++++++++++++++++++++++++++
 docs/index.md         |  6 ++++++
 docs/python.md        | 15 ++++++++++++++
 5 files changed, 85 insertions(+)

diff --git a/README.md b/README.md
index 8e20b3e1..cf86ae99 100644
--- a/README.md
+++ b/README.md
@@ -9,6 +9,7 @@ Retrieval-Augmented Generation (RAG) library on SQLite.
 - **Local SQLite**: No external servers required
 - **Multiple embedding providers**: Ollama, VoyageAI, OpenAI
 - **Hybrid search**: Vector + full-text search with Reciprocal Rank Fusion
+- **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
 - **MCP server**: Expose as tools for AI assistants
@@ -27,6 +28,9 @@ haiku-rag add-src document.pdf
 # Search
 haiku-rag search "query"
 
+# Ask questions
+haiku-rag ask "Who is the author of haiku.rag?"
+
 # Start server with file monitoring
 export MONITOR_DIRECTORIES="/path/to/docs"
 haiku-rag serve
@@ -45,6 +49,10 @@ async with HaikuRAG("database.db") as client:
     results = await client.search("query")
     for chunk, score in results:
         print(f"{score:.3f}: {chunk.content}")
+
+    # Ask questions
+    answer = await client.ask("Who is the author of haiku.rag?")
+    print(answer)
 ```
 
 ## MCP Server
diff --git a/docs/cli.md b/docs/cli.md
index e5100062..fae3db8a 100644
--- a/docs/cli.md
+++ b/docs/cli.md
@@ -47,6 +47,15 @@ With options:
 haiku-rag search "python programming" --limit 10 --k 100
 ```
 
+## Question Answering
+
+Ask questions about your documents:
+```bash
+haiku-rag ask "Who is the author of haiku.rag?"
+```
+
+The QA agent will search your documents for relevant information and provide a comprehensive answer.
+
 ## Server
 
 Start the MCP server:
diff --git a/docs/configuration.md b/docs/configuration.md
index 8ba6cc7e..cae8a1dd 100644
--- a/docs/configuration.md
+++ b/docs/configuration.md
@@ -55,3 +55,50 @@ EMBEDDINGS_MODEL="text-embedding-3-small"  # or text-embedding-3-large
 EMBEDDINGS_VECTOR_DIM=1536
 OPENAI_API_KEY="your-api-key"
 ```
+
+## Question Answering Providers
+
+Configure which LLM provider to use for question answering.
+
+### Ollama (Default)
+
+```bash
+QA_PROVIDER="ollama"
+QA_MODEL="qwen3"
+OLLAMA_BASE_URL="http://localhost:11434"
+```
+
+### OpenAI
+
+For OpenAI QA, you need to install haiku.rag with OpenAI extras:
+
+```bash
+uv pip install haiku.rag --extra openai
+```
+
+Then configure:
+
+```bash
+QA_PROVIDER="openai"
+QA_MODEL="gpt-4o-mini"  # or gpt-4, gpt-3.5-turbo, etc.
+OPENAI_API_KEY="your-api-key"
+```
+
+## Other Settings
+
+### Database and Storage
+
+```bash
+# Default data directory (where SQLite database is stored)
+DEFAULT_DATA_DIR="/path/to/data"
+```
+
+### Document Processing
+
+```bash
+# Chunk size for document processing
+CHUNK_SIZE=256
+
+# Chunk overlap for better context
+CHUNK_OVERLAP=32
+```
diff --git a/docs/index.md b/docs/index.md
index 404ae8b4..66117c63 100644
--- a/docs/index.md
+++ b/docs/index.md
@@ -8,6 +8,7 @@
 - **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
+- **Question Answering**: Built-in QA agents using Ollama or OpenAI.
 - **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!
 - **MCP server**: Exposes functionality as MCP tools
@@ -31,12 +32,16 @@ async with HaikuRAG("database.db") as client:
 
     # Search documents
     results = await client.search("query")
+
+    # Ask questions
+    answer = await client.ask("Who is the author of haiku.rag?")
 ```
 
 Or use the CLI:
 ```bash
 haiku-rag add "Your document content"
 haiku-rag search "query"
+haiku-rag ask "Who is the author of haiku.rag?"
 ```
 
 ## Documentation
@@ -44,6 +49,7 @@ haiku-rag search "query"
 - [Installation](installation.md) - Install haiku.rag with different providers
 - [Configuration](configuration.md) - Environment variables and settings
 - [CLI](cli.md) - Command line interface usage
+- [Question Answering](qa.md) - QA agents and natural language queries
 - [Server](server.md) - File monitoring and server mode
 - [MCP](mcp.md) - Model Context Protocol integration
 - [Python](python.md) - Python API reference
diff --git a/docs/python.md b/docs/python.md
index 9908210e..ebc87f4c 100644
--- a/docs/python.md
+++ b/docs/python.md
@@ -91,4 +91,19 @@ for chunk, relevance_score in results:
     print(f"Relevance: {relevance_score:.3f}")
     print(f"Content: {chunk.content}")
     print(f"From document: {chunk.document_id}")
+    print(f"Document URI: {chunk.document_uri}")
+    print(f"Document metadata: {chunk.document_meta}")
 ```
+
+## Question Answering
+
+Ask questions about your documents:
+
+```python
+answer = await client.ask("Who is the author of haiku.rag?")
+print(answer)
+```
+
+The QA agent will search your documents for relevant information and use the configured LLM to generate a comprehensive answer.
+
+The QA provider and model can be configured via environment variables (see [Configuration](configuration.md)).