haiku.rag 0.12.1__tar.gz → 0.13.1__tar.gz

{haiku_rag-0.12.1 → haiku_rag-0.13.1}/.dockerignore

@@ -25,9 +25,19 @@ wheels/
 venv/
 env/
 
+# Node.js
+node_modules/
+.next/
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+
 # Data
 *.lancedb/
 data/
+
+# Docs
+mkdocs.yml
 docs/
 
 # IDE
@@ -50,6 +60,7 @@ tests/
 .pytest_cache/
 .coverage
 htmlcov/
-
+src/evaluations/
+server.json
 # Examples
 examples/

{haiku_rag-0.12.1 → haiku_rag-0.13.1}/.gitignore

@@ -16,8 +16,9 @@ tests/data/
 .pytest_cache/
 .ruff_cache/
 
-# environment variables
+# environment variables and config files
 .env
+haiku.rag.yaml
 TODO.md
 PLAN.md
 DEVNOTES.md
@@ -25,3 +26,6 @@ DEVNOTES.md
 # mcp registry
 .mcpregistry_github_token
 .mcpregistry_registry_token
+
+# MkDocs site directory when doing local docs builds
+site/

{haiku_rag-0.12.1 → haiku_rag-0.13.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: haiku.rag
-Version: 0.12.1
+Version: 0.13.1
 Summary: Agentic Retrieval Augmented Generation (RAG) with LanceDB
 Author-email: Yiorgis Gozadinos <ggozadinos@gmail.com>
 License: MIT
@@ -13,9 +13,8 @@ Classifier: Operating System :: MacOS
 Classifier: Operating System :: Microsoft :: Windows :: Windows 10
 Classifier: Operating System :: Microsoft :: Windows :: Windows 11
 Classifier: Operating System :: POSIX :: Linux
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Classifier: Typing :: Typed
 Requires-Python: >=3.12
 Requires-Dist: docling>=2.56.1
@@ -26,6 +25,7 @@ Requires-Dist: pydantic-ai>=1.0.18
 Requires-Dist: pydantic-graph>=1.0.18
 Requires-Dist: pydantic>=2.12.2
 Requires-Dist: python-dotenv>=1.1.1
+Requires-Dist: pyyaml>=6.0.1
 Requires-Dist: rich>=14.2.0
 Requires-Dist: tiktoken>=0.12.0
 Requires-Dist: typer>=0.19.2
@@ -40,11 +40,13 @@ Description-Content-Type: text/markdown
 
 # Haiku RAG
 
+mcp-name: io.github.ggozad/haiku-rag
+
 Retrieval-Augmented Generation (RAG) library built on LanceDB.
 
 `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.
 
-> **Note**: Starting with version 0.7.0, haiku.rag uses LanceDB instead of SQLite. If you have an existing SQLite database, use `haiku-rag migrate old_database.sqlite` to migrate your data safely.
+> **Note**: Configuration now uses YAML files instead of environment variables. If you're upgrading from an older version, run `haiku-rag init-config --from-env` to migrate your `.env` file to `haiku.rag.yaml`. See [Configuration](https://ggozad.github.io/haiku.rag/configuration/) for details.
 
 ## Features
 
@@ -65,6 +67,7 @@ Retrieval-Augmented Generation (RAG) library built on LanceDB.
 
 ```bash
 # Install
+# Python 3.12 or newer required
 uv pip install haiku.rag
 
 # Add documents
@@ -98,14 +101,12 @@ haiku-rag research \
 # Rebuild database (re-chunk and re-embed all documents)
 haiku-rag rebuild
 
-# Migrate from SQLite to LanceDB
-haiku-rag migrate old_database.sqlite
-
 # Start server with file monitoring
-export MONITOR_DIRECTORIES="/path/to/docs"
-haiku-rag serve
+haiku-rag serve --monitor
 ```
 
+To customize settings, create a `haiku.rag.yaml` config file (see [Configuration](https://ggozad.github.io/haiku.rag/configuration/)).
+
 ## Python Usage
 
 ```python
@@ -197,17 +198,26 @@ haiku-rag a2aclient
 ```
 
 The A2A agent provides:
+
 - Multi-turn dialogue with context
 - Intelligent multi-search for complex questions
 - Source citations with titles and URIs
 - Full document retrieval on request
 
+## Examples
+
+See the [examples directory](examples/) for working examples:
+
+- **[Interactive Research Assistant](examples/ag-ui-research/)** - Full-stack research assistant with Pydantic AI and AG-UI featuring human-in-the-loop approval and real-time state synchronization
+- **[Docker Setup](examples/docker/)** - Complete Docker deployment with file monitoring, MCP server, and A2A agent
+- **[A2A Security](examples/a2a-security/)** - Authentication examples (API key, OAuth2, GitHub)
+
 ## Documentation
 
 Full documentation at: https://ggozad.github.io/haiku.rag/
 
 - [Installation](https://ggozad.github.io/haiku.rag/installation/) - Provider setup
-- [Configuration](https://ggozad.github.io/haiku.rag/configuration/) - Environment variables
+- [Configuration](https://ggozad.github.io/haiku.rag/configuration/) - YAML configuration
 - [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

{haiku_rag-0.12.1 → haiku_rag-0.13.1}/README.md

@@ -1,10 +1,12 @@
 # Haiku RAG
 
+mcp-name: io.github.ggozad/haiku-rag
+
 Retrieval-Augmented Generation (RAG) library built on LanceDB.
 
 `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.
 
-> **Note**: Starting with version 0.7.0, haiku.rag uses LanceDB instead of SQLite. If you have an existing SQLite database, use `haiku-rag migrate old_database.sqlite` to migrate your data safely.
+> **Note**: Configuration now uses YAML files instead of environment variables. If you're upgrading from an older version, run `haiku-rag init-config --from-env` to migrate your `.env` file to `haiku.rag.yaml`. See [Configuration](https://ggozad.github.io/haiku.rag/configuration/) for details.
 
 ## Features
 
@@ -25,6 +27,7 @@ Retrieval-Augmented Generation (RAG) library built on LanceDB.
 
 ```bash
 # Install
+# Python 3.12 or newer required
 uv pip install haiku.rag
 
 # Add documents
@@ -58,14 +61,12 @@ haiku-rag research \
 # Rebuild database (re-chunk and re-embed all documents)
 haiku-rag rebuild
 
-# Migrate from SQLite to LanceDB
-haiku-rag migrate old_database.sqlite
-
 # Start server with file monitoring
-export MONITOR_DIRECTORIES="/path/to/docs"
-haiku-rag serve
+haiku-rag serve --monitor
 ```
 
+To customize settings, create a `haiku.rag.yaml` config file (see [Configuration](https://ggozad.github.io/haiku.rag/configuration/)).
+
 ## Python Usage
 
 ```python
@@ -157,17 +158,26 @@ haiku-rag a2aclient
 ```
 
 The A2A agent provides:
+
 - Multi-turn dialogue with context
 - Intelligent multi-search for complex questions
 - Source citations with titles and URIs
 - Full document retrieval on request
 
+## Examples
+
+See the [examples directory](examples/) for working examples:
+
+- **[Interactive Research Assistant](examples/ag-ui-research/)** - Full-stack research assistant with Pydantic AI and AG-UI featuring human-in-the-loop approval and real-time state synchronization
+- **[Docker Setup](examples/docker/)** - Complete Docker deployment with file monitoring, MCP server, and A2A agent
+- **[A2A Security](examples/a2a-security/)** - Authentication examples (API key, OAuth2, GitHub)
+
 ## Documentation
 
 Full documentation at: https://ggozad.github.io/haiku.rag/
 
 - [Installation](https://ggozad.github.io/haiku.rag/installation/) - Provider setup
-- [Configuration](https://ggozad.github.io/haiku.rag/configuration/) - Environment variables
+- [Configuration](https://ggozad.github.io/haiku.rag/configuration/) - YAML configuration
 - [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

{haiku_rag-0.12.1 → haiku_rag-0.13.1}/mkdocs.yml

@@ -57,6 +57,7 @@ plugins:
 nav:
   - haiku.rag:
       - index.md
+      - Getting started: tutorial.md
       - Installation: installation.md
       - Configuration: configuration.md
       - CLI: cli.md

{haiku_rag-0.12.1 → haiku_rag-0.13.1}/pyproject.toml

@@ -2,7 +2,7 @@
 
 name = "haiku.rag"
 description = "Agentic Retrieval Augmented Generation (RAG) with LanceDB"
-version = "0.12.1"
+version = "0.13.1"
 authors = [{ name = "Yiorgis Gozadinos", email = "ggozadinos@gmail.com" }]
 license = { text = "MIT" }
 readme = { file = "README.md", content-type = "text/markdown" }
@@ -16,9 +16,8 @@ classifiers = [
     "Operating System :: Microsoft :: Windows :: Windows 11",
     "Operating System :: MacOS",
     "Operating System :: POSIX :: Linux",
-    "Programming Language :: Python :: 3.10",
-    "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
     "Typing :: Typed",
 ]
 
@@ -31,6 +30,7 @@ dependencies = [
     "pydantic-ai>=1.0.18",
     "pydantic-graph>=1.0.18",
     "python-dotenv>=1.1.1",
+    "pyyaml>=6.0.1",
     "rich>=14.2.0",
     "tiktoken>=0.12.0",
     "typer>=0.19.2",

haiku_rag-0.13.1/server.json

@@ -0,0 +1,42 @@
+{
+    "$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",
+    "repository": {
+        "url": "https://github.com/ggozad/haiku.rag",
+        "source": "github"
+    },
+    "license": "MIT",
+    "keywords": [
+        "rag",
+        "lancedb",
+        "vector-database",
+        "embeddings",
+        "search",
+        "qa",
+        "research"
+    ],
+    "packages": [
+        {
+            "registryType": "pypi",
+            "registryBaseUrl": "https://pypi.org",
+            "identifier": "haiku-rag",
+            "version": "{{VERSION}}",
+            "runtimeHint": "uvx",
+            "runtimeArguments": [
+                {
+                    "type": "positional",
+                    "value": "serve"
+                },
+                {
+                    "type": "named",
+                    "name": "--mcp"
+                }
+            ],
+            "transport": {
+                "type": "stdio"
+            }
+        }
+    ]
+}

{haiku_rag-0.12.1 → haiku_rag-0.13.1}/src/evaluations/benchmark.py

@@ -174,7 +174,7 @@ async def run_qa_benchmark(
 
     judge_model = OpenAIChatModel(
         model_name=QA_JUDGE_MODEL,
-        provider=OllamaProvider(base_url=f"{Config.OLLAMA_BASE_URL}/v1"),
+        provider=OllamaProvider(base_url=f"{Config.providers.ollama.base_url}/v1"),
     )
 
     evaluation_dataset = EvalDataset[str, str, dict[str, str]](

{haiku_rag-0.12.1 → haiku_rag-0.13.1}/src/evaluations/llm_judge.py

@@ -41,7 +41,7 @@ class LLMJudge:
         # Create Ollama model
         ollama_model = OpenAIChatModel(
             model_name=model,
-            provider=OllamaProvider(base_url=f"{Config.OLLAMA_BASE_URL}/v1"),
+            provider=OllamaProvider(base_url=f"{Config.providers.ollama.base_url}/v1"),
         )
 
         # Create Pydantic AI agent

{haiku_rag-0.12.1 → haiku_rag-0.13.1}/src/haiku/rag/a2a/__init__.py

@@ -57,12 +57,12 @@ def create_a2a_app(
     """
     base_storage = InMemoryStorage()
     storage = LRUMemoryStorage(
-        storage=base_storage, max_contexts=Config.A2A_MAX_CONTEXTS
+        storage=base_storage, max_contexts=Config.a2a.max_contexts
     )
     broker = InMemoryBroker()
 
     # Create the agent with native search tool
-    model = get_model(Config.QA_PROVIDER, Config.QA_MODEL)
+    model = get_model(Config.qa.provider, Config.qa.model)
     agent = Agent(
         model=model,
         deps_type=AgentDependencies,
@@ -120,7 +120,7 @@ def create_a2a_app(
     # Create FastA2A app with custom worker lifecycle
     @asynccontextmanager
     async def lifespan(app):
-        logger.info(f"Started A2A server (max contexts: {Config.A2A_MAX_CONTEXTS})")
+        logger.info(f"Started A2A server (max contexts: {Config.a2a.max_contexts})")
         async with app.task_manager:
             async with worker.run():
                 yield

{haiku_rag-0.12.1 → haiku_rag-0.13.1}/src/haiku/rag/app.py

@@ -231,8 +231,8 @@ class HaikuRAGApp:
                     )
 
                     start_node = DeepQAPlanNode(
-                        provider=Config.QA_PROVIDER,
-                        model=Config.QA_MODEL,
+                        provider=Config.qa.provider,
+                        model=Config.qa.model,
                     )
 
                     result = await graph.run(
@@ -278,8 +278,8 @@ class HaikuRAGApp:
                 )
 
                 start = PlanNode(
-                    provider=Config.RESEARCH_PROVIDER or Config.QA_PROVIDER,
-                    model=Config.RESEARCH_MODEL or Config.QA_MODEL,
+                    provider=Config.research.provider or Config.qa.provider,
+                    model=Config.research.model or Config.qa.model,
                 )
                 report = None
                 async for event in stream_research_graph(graph, start, state, deps):
@@ -474,7 +474,9 @@ class HaikuRAGApp:
 
             # Start file monitor if enabled
             if enable_monitor:
-                monitor = FileWatcher(paths=Config.MONITOR_DIRECTORIES, client=client)
+                monitor = FileWatcher(
+                    paths=Config.storage.monitor_directories, client=client
+                )
                 monitor_task = asyncio.create_task(monitor.observe())
                 tasks.append(monitor_task)
 

{haiku_rag-0.12.1 → haiku_rag-0.13.1}/src/haiku/rag/chunker.py

@@ -22,7 +22,7 @@ class Chunker:
 
     def __init__(
         self,
-        chunk_size: int = Config.CHUNK_SIZE,
+        chunk_size: int = Config.processing.chunk_size,
     ):
         self.chunk_size = chunk_size
         tokenizer = OpenAITokenizer(

{haiku_rag-0.12.1 → haiku_rag-0.13.1}/src/haiku/rag/cli.py

@@ -42,10 +42,21 @@ def main(
         callback=version_callback,
         help="Show version and exit",
     ),
+    config: Path | None = typer.Option(
+        None,
+        "--config",
+        help="Path to YAML configuration file",
+    ),
 ):
     """haiku.rag CLI - Vector database RAG system"""
+    # Store config path in environment for config loader to use
+    if config:
+        import os
+
+        os.environ["HAIKU_RAG_CONFIG_PATH"] = str(config.absolute())
+
     # Configure logging minimally for CLI context
-    if Config.ENV == "development":
+    if Config.environment == "development":
         # Lazy import logfire only in development
         try:
             import logfire  # type: ignore
@@ -69,7 +80,7 @@ def main(
 @cli.command("list", help="List all stored documents")
 def list_documents(
     db: Path = typer.Option(
-        Config.DEFAULT_DATA_DIR / "haiku.rag.lancedb",
+        Config.storage.data_dir / "haiku.rag.lancedb",
         "--db",
         help="Path to the LanceDB database file",
     ),
@@ -116,7 +127,7 @@ def add_document_text(
         metavar="KEY=VALUE",
     ),
     db: Path = typer.Option(
-        Config.DEFAULT_DATA_DIR / "haiku.rag.lancedb",
+        Config.storage.data_dir / "haiku.rag.lancedb",
         "--db",
         help="Path to the LanceDB database file",
     ),
@@ -145,7 +156,7 @@ def add_document_src(
         metavar="KEY=VALUE",
     ),
     db: Path = typer.Option(
-        Config.DEFAULT_DATA_DIR / "haiku.rag.lancedb",
+        Config.storage.data_dir / "haiku.rag.lancedb",
         "--db",
         help="Path to the LanceDB database file",
     ),
@@ -167,7 +178,7 @@ def get_document(
         help="The ID of the document to get",
     ),
     db: Path = typer.Option(
-        Config.DEFAULT_DATA_DIR / "haiku.rag.lancedb",
+        Config.storage.data_dir / "haiku.rag.lancedb",
         "--db",
         help="Path to the LanceDB database file",
     ),
@@ -184,7 +195,7 @@ def delete_document(
         help="The ID of the document to delete",
     ),
     db: Path = typer.Option(
-        Config.DEFAULT_DATA_DIR / "haiku.rag.lancedb",
+        Config.storage.data_dir / "haiku.rag.lancedb",
         "--db",
         help="Path to the LanceDB database file",
     ),
@@ -211,7 +222,7 @@ def search(
         help="Maximum number of results to return",
     ),
     db: Path = typer.Option(
-        Config.DEFAULT_DATA_DIR / "haiku.rag.lancedb",
+        Config.storage.data_dir / "haiku.rag.lancedb",
         "--db",
         help="Path to the LanceDB database file",
     ),
@@ -228,7 +239,7 @@ def ask(
         help="The question to ask",
     ),
     db: Path = typer.Option(
-        Config.DEFAULT_DATA_DIR / "haiku.rag.lancedb",
+        Config.storage.data_dir / "haiku.rag.lancedb",
         "--db",
         help="Path to the LanceDB database file",
     ),
@@ -276,7 +287,7 @@ def research(
         help="Max concurrent searches per iteration (planned)",
     ),
     db: Path = typer.Option(
-        Config.DEFAULT_DATA_DIR / "haiku.rag.lancedb",
+        Config.storage.data_dir / "haiku.rag.lancedb",
         "--db",
         help="Path to the LanceDB database file",
     ),
@@ -308,13 +319,61 @@ def settings():
     app.show_settings()
 
 
+@cli.command("init-config", help="Generate a YAML configuration file")
+def init_config(
+    output: Path = typer.Argument(
+        Path("haiku.rag.yaml"),
+        help="Output path for the config file",
+    ),
+    from_env: bool = typer.Option(
+        False,
+        "--from-env",
+        help="Migrate settings from .env file",
+    ),
+):
+    """Generate a YAML configuration file with defaults or from .env."""
+    import yaml
+
+    from haiku.rag.config.loader import generate_default_config, load_config_from_env
+
+    if output.exists():
+        typer.echo(
+            f"Error: {output} already exists. Remove it first or choose a different path."
+        )
+        raise typer.Exit(1)
+
+    if from_env:
+        # Load from environment variables (including .env if present)
+        from dotenv import load_dotenv
+
+        load_dotenv()
+        config_data = load_config_from_env()
+        if not config_data:
+            typer.echo("Warning: No environment variables found to migrate.")
+            typer.echo("Generating default configuration instead.")
+            config_data = generate_default_config()
+    else:
+        config_data = generate_default_config()
+
+    # Write YAML with comments
+    with open(output, "w") as f:
+        f.write("# haiku.rag configuration file\n")
+        f.write(
+            "# See https://ggozad.github.io/haiku.rag/configuration/ for details\n\n"
+        )
+        yaml.dump(config_data, f, default_flow_style=False, sort_keys=False)
+
+    typer.echo(f"Configuration file created: {output}")
+    typer.echo("Edit the file to customize your settings.")
+
+
 @cli.command(
     "rebuild",
     help="Rebuild the database by deleting all chunks and re-indexing all documents",
 )
 def rebuild(
     db: Path = typer.Option(
-        Config.DEFAULT_DATA_DIR / "haiku.rag.lancedb",
+        Config.storage.data_dir / "haiku.rag.lancedb",
         "--db",
         help="Path to the LanceDB database file",
     ),
@@ -328,7 +387,7 @@ def rebuild(
 @cli.command("vacuum", help="Optimize and clean up all tables to reduce disk usage")
 def vacuum(
     db: Path = typer.Option(
-        Config.DEFAULT_DATA_DIR / "haiku.rag.lancedb",
+        Config.storage.data_dir / "haiku.rag.lancedb",
         "--db",
         help="Path to the LanceDB database file",
     ),
@@ -342,7 +401,7 @@ def vacuum(
 @cli.command("info", help="Show read-only database info (no upgrades or writes)")
 def info(
     db: Path = typer.Option(
-        Config.DEFAULT_DATA_DIR / "haiku.rag.lancedb",
+        Config.storage.data_dir / "haiku.rag.lancedb",
         "--db",
         help="Path to the LanceDB database file",
     ),
@@ -371,7 +430,7 @@ def download_models_cmd():
 )
 def serve(
     db: Path = typer.Option(
-        Config.DEFAULT_DATA_DIR / "haiku.rag.lancedb",
+        Config.storage.data_dir / "haiku.rag.lancedb",
         "--db",
         help="Path to the LanceDB database file",
     ),
@@ -442,24 +501,6 @@ def serve(
     )
 
 
-@cli.command("migrate", help="Migrate an SQLite database to LanceDB")
-def migrate(
-    sqlite_path: Path = typer.Argument(
-        help="Path to the SQLite database file to migrate",
-    ),
-):
-    # Generate LanceDB path in same parent directory
-    lancedb_path = sqlite_path.parent / (sqlite_path.stem + ".lancedb")
-
-    # Lazy import to avoid heavy deps on simple invocations
-    from haiku.rag.migration import migrate_sqlite_to_lancedb
-
-    success = asyncio.run(migrate_sqlite_to_lancedb(sqlite_path, lancedb_path))
-
-    if not success:
-        raise typer.Exit(1)
-
-
 @cli.command(
     "a2aclient", help="Run interactive client to chat with haiku.rag's A2A server"
 )