haiku.rag 0.19.4__tar.gz → 0.19.6__tar.gz

{haiku_rag-0.19.4 → haiku_rag-0.19.6}/CHANGELOG.md

@@ -1,6 +1,27 @@
 # Changelog
 ## [Unreleased]
 
+## [0.19.6] - 2025-12-03
+
+## [0.19.6] - 2025-12-03
+
+### Changed
+
+- **BREAKING: Explicit Database Creation**: Databases must now be explicitly created before use
+  - New `haiku-rag init` command creates a new empty database
+  - Python API: `HaikuRAG(path, create=True)` to create database programmatically
+  - Operations on non-existent databases raise `FileNotFoundError`
+- **BREAKING: Embeddings Configuration**: Restructured to nested `EmbeddingModelConfig`
+  - Config path changed from `embeddings.{provider, model, vector_dim}` to `embeddings.model.{provider, name, vector_dim}`
+  - Automatic migration upgrades existing databases to new format
+- **Database Migrations**: Always run when opening an existing database
+
+## [0.19.5] - 2025-12-01
+
+### Changed
+
+- **Rebuild Performance**: Optimized `rebuild --embed-only` to use batch updates via LanceDB's `merge_insert` instead of individual chunk updates, and skip chunks with unchanged embeddings
+
 ## [0.19.4] - 2025-11-28
 
 ### Added

{haiku_rag-0.19.4 → haiku_rag-0.19.6}/PKG-INFO

@@ -1,11 +1,11 @@
 Metadata-Version: 2.4
 Name: haiku.rag
-Version: 0.19.4
-Summary: Agentic Retrieval Augmented Generation (RAG) with LanceDB
+Version: 0.19.6
+Summary: Opinionated agentic RAG powered by LanceDB, Pydantic AI, and Docling
 Author-email: Yiorgis Gozadinos <ggozadinos@gmail.com>
 License: MIT
 License-File: LICENSE
-Keywords: RAG,lancedb,mcp,ml,vector-database
+Keywords: RAG,docling,lancedb,mcp,ml,pydantic-ai,vector-database
 Classifier: Development Status :: 4 - Beta
 Classifier: Environment :: Console
 Classifier: Intended Audience :: Developers
@@ -17,16 +17,16 @@ Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Classifier: Typing :: Typed
 Requires-Python: >=3.12
-Requires-Dist: haiku-rag-slim[cohere,docling,inspector,mxbai,voyageai,zeroentropy]==0.19.4
+Requires-Dist: haiku-rag-slim[cohere,docling,inspector,mxbai,voyageai,zeroentropy]==0.19.6
 Provides-Extra: inspector
 Requires-Dist: textual>=1.0.0; extra == 'inspector'
 Description-Content-Type: text/markdown
 
 # Haiku RAG
 
-Retrieval-Augmented Generation (RAG) library built on LanceDB.
+Opinionated agentic RAG powered by LanceDB, Pydantic AI, and Docling.
 
-`haiku.rag` is a Retrieval-Augmented Generation (RAG) library built to work with LanceDB as a local vector database. It uses LanceDB for storing embeddings and performs semantic (vector) search as well as full-text search combined through native hybrid search with Reciprocal Rank Fusion. Both open-source (Ollama) as well as commercial (OpenAI, VoyageAI) embedding providers are supported.
+`haiku.rag` is an opinionated agentic RAG system that uses LanceDB for vector storage, Pydantic AI for multi-agent workflows, and Docling for document processing. It supports hybrid search (vector + full-text) with Reciprocal Rank Fusion, multiple embedding providers (Ollama, LM Studio, vLLM, OpenAI, VoyageAI), and includes research agents that plan, search, evaluate, and synthesize answers.
 
 ## Features
 
@@ -168,10 +168,23 @@ async with HaikuRAG("database.lancedb") as client:
 Use with AI assistants like Claude Desktop:
 
 ```bash
-haiku-rag serve --stdio
+haiku-rag serve --mcp --stdio
 ```
 
-Provides tools for document management and search directly in your AI assistant.
+Add to your Claude Desktop configuration:
+
+```json
+{
+  "mcpServers": {
+    "haiku-rag": {
+      "command": "haiku-rag",
+      "args": ["serve", "--mcp", "--stdio"]
+    }
+  }
+}
+```
+
+Provides tools for document management, search, QA, and research directly in your AI assistant.
 
 ## Examples
 
@@ -190,7 +203,10 @@ Full documentation at: https://ggozad.github.io/haiku.rag/
 - [CLI](https://ggozad.github.io/haiku.rag/cli/) - Command reference
 - [Python API](https://ggozad.github.io/haiku.rag/python/) - Complete API docs
 - [Agents](https://ggozad.github.io/haiku.rag/agents/) - QA agent and multi-agent research
-- [MCP Server](https://ggozad.github.io/haiku.rag/mcp/) - Model Context Protocol integration
-- [Benchmarks](https://ggozad.github.io/haiku.rag/benchmarks/) - Performance Benchmarks
+- [Server](https://ggozad.github.io/haiku.rag/server/) - File monitoring, MCP, and AG-UI
+- [MCP](https://ggozad.github.io/haiku.rag/mcp/) - Model Context Protocol integration
+- [Inspector](https://ggozad.github.io/haiku.rag/inspector/) - Database browser TUI
+- [Benchmarks](https://ggozad.github.io/haiku.rag/benchmarks/) - Performance benchmarks
+- [Changelog](https://ggozad.github.io/haiku.rag/changelog/) - Version history
 
 mcp-name: io.github.ggozad/haiku-rag

{haiku_rag-0.19.4 → haiku_rag-0.19.6}/README.md

@@ -1,8 +1,8 @@
 # Haiku RAG
 
-Retrieval-Augmented Generation (RAG) library built on LanceDB.
+Opinionated agentic RAG powered by LanceDB, Pydantic AI, and Docling.
 
-`haiku.rag` is a Retrieval-Augmented Generation (RAG) library built to work with LanceDB as a local vector database. It uses LanceDB for storing embeddings and performs semantic (vector) search as well as full-text search combined through native hybrid search with Reciprocal Rank Fusion. Both open-source (Ollama) as well as commercial (OpenAI, VoyageAI) embedding providers are supported.
+`haiku.rag` is an opinionated agentic RAG system that uses LanceDB for vector storage, Pydantic AI for multi-agent workflows, and Docling for document processing. It supports hybrid search (vector + full-text) with Reciprocal Rank Fusion, multiple embedding providers (Ollama, LM Studio, vLLM, OpenAI, VoyageAI), and includes research agents that plan, search, evaluate, and synthesize answers.
 
 ## Features
 
@@ -144,10 +144,23 @@ async with HaikuRAG("database.lancedb") as client:
 Use with AI assistants like Claude Desktop:
 
 ```bash
-haiku-rag serve --stdio
+haiku-rag serve --mcp --stdio
 ```
 
-Provides tools for document management and search directly in your AI assistant.
+Add to your Claude Desktop configuration:
+
+```json
+{
+  "mcpServers": {
+    "haiku-rag": {
+      "command": "haiku-rag",
+      "args": ["serve", "--mcp", "--stdio"]
+    }
+  }
+}
+```
+
+Provides tools for document management, search, QA, and research directly in your AI assistant.
 
 ## Examples
 
@@ -166,7 +179,10 @@ Full documentation at: https://ggozad.github.io/haiku.rag/
 - [CLI](https://ggozad.github.io/haiku.rag/cli/) - Command reference
 - [Python API](https://ggozad.github.io/haiku.rag/python/) - Complete API docs
 - [Agents](https://ggozad.github.io/haiku.rag/agents/) - QA agent and multi-agent research
-- [MCP Server](https://ggozad.github.io/haiku.rag/mcp/) - Model Context Protocol integration
-- [Benchmarks](https://ggozad.github.io/haiku.rag/benchmarks/) - Performance Benchmarks
+- [Server](https://ggozad.github.io/haiku.rag/server/) - File monitoring, MCP, and AG-UI
+- [MCP](https://ggozad.github.io/haiku.rag/mcp/) - Model Context Protocol integration
+- [Inspector](https://ggozad.github.io/haiku.rag/inspector/) - Database browser TUI
+- [Benchmarks](https://ggozad.github.io/haiku.rag/benchmarks/) - Performance benchmarks
+- [Changelog](https://ggozad.github.io/haiku.rag/changelog/) - Version history
 
 mcp-name: io.github.ggozad/haiku-rag

{haiku_rag-0.19.4 → haiku_rag-0.19.6}/mkdocs.yml

@@ -1,5 +1,5 @@
 site_name: haiku.rag
-site_description: Retrieval-Augmented Generation (RAG) library on LanceDB.
+site_description: Opinionated agentic RAG powered by LanceDB, Pydantic AI, and Docling.
 site_url: https://ggozad.github.io/haiku.rag/
 theme:
   name: material
@@ -73,6 +73,7 @@ nav:
       - MCP: mcp.md
       - Inspector: inspector.md
       - Benchmarks: benchmarks.md
+      - Changelog: changelog.md
 markdown_extensions:
   - admonition
   - attr_list
@@ -83,7 +84,8 @@ markdown_extensions:
       pygments_lang_class: true
       use_pygments: true
   - pymdownx.inlinehilite
-  - pymdownx.snippets
+  - pymdownx.snippets:
+      base_path: ['.']
   - pymdownx.superfences:
       custom_fences:
         - name: mermaid

{haiku_rag-0.19.4 → haiku_rag-0.19.6}/pyproject.toml

@@ -1,13 +1,21 @@
 [project]
 
 name = "haiku.rag"
-description = "Agentic Retrieval Augmented Generation (RAG) with LanceDB"
-version = "0.19.4"
+description = "Opinionated agentic RAG powered by LanceDB, Pydantic AI, and Docling"
+version = "0.19.6"
 authors = [{ name = "Yiorgis Gozadinos", email = "ggozadinos@gmail.com" }]
 license = { text = "MIT" }
 readme = { file = "README.md", content-type = "text/markdown" }
 requires-python = ">=3.12"
-keywords = ["RAG", "lancedb", "vector-database", "ml", "mcp"]
+keywords = [
+    "RAG",
+    "lancedb",
+    "vector-database",
+    "ml",
+    "mcp",
+    "pydantic-ai",
+    "docling",
+]
 classifiers = [
     "Development Status :: 4 - Beta",
     "Environment :: Console",
@@ -22,16 +30,14 @@ classifiers = [
 ]
 
 dependencies = [
-    "haiku.rag-slim[docling,voyageai,mxbai,cohere,zeroentropy,inspector]==0.19.4",
+    "haiku.rag-slim[docling,voyageai,mxbai,cohere,zeroentropy,inspector]==0.19.6",
 ]
 
 [project.scripts]
 haiku-rag = "haiku.rag.cli:cli"
 
 [project.optional-dependencies]
-inspector = [
-    "textual>=1.0.0",
-]
+inspector = ["textual>=1.0.0"]
 
 [build-system]
 requires = ["hatchling"]

{haiku_rag-0.19.4 → haiku_rag-0.19.6}/server.json

@@ -2,7 +2,7 @@
     "$schema": "https://static.modelcontextprotocol.io/schemas/2025-10-17/server.schema.json",
     "name": "io.github.ggozad/haiku-rag",
     "version": "{{VERSION}}",
-    "description": "Agentic Retrieval Augmented Generation (RAG) with LanceDB",
+    "description": "Opinionated agentic RAG powered by LanceDB, Pydantic AI, and Docling",
     "repository": {
         "url": "https://github.com/ggozad/haiku.rag",
         "source": "github"

{haiku_rag-0.19.4 → haiku_rag-0.19.6}/uv.lock

@@ -1264,7 +1264,7 @@ wheels = [
 
 [[package]]
 name = "haiku-rag"
-version = "0.19.4"
+version = "0.19.6"
 source = { editable = "." }
 dependencies = [
     { name = "haiku-rag-slim", extra = ["cohere", "docling", "inspector", "mxbai", "voyageai", "zeroentropy"] },
@@ -1312,7 +1312,7 @@ dev = [
 
 [[package]]
 name = "haiku-rag-evals"
-version = "0.19.4"
+version = "0.19.6"
 source = { editable = "evaluations" }
 dependencies = [
     { name = "datasets" },
@@ -1333,7 +1333,7 @@ requires-dist = [
 
 [[package]]
 name = "haiku-rag-slim"
-version = "0.19.4"
+version = "0.19.6"
 source = { editable = "haiku_rag_slim" }
 dependencies = [
     { name = "docling-core" },