haiku.rag 0.3.0__py3-none-any.whl → 0.3.2__py3-none-any.whl

haiku/rag/app.py

@@ -3,6 +3,7 @@ from pathlib import Path
 
 from rich.console import Console
 from rich.markdown import Markdown
+from rich.progress import Progress
 
 from haiku.rag.client import HaikuRAG
 from haiku.rag.config import Config
@@ -72,6 +73,50 @@ class HaikuRAGApp:
             except Exception as e:
                 self.console.print(f"[red]Error: {e}[/red]")
 
+    async def rebuild(self):
+        async with HaikuRAG(db_path=self.db_path) as client:
+            try:
+                documents = await client.list_documents()
+                total_docs = len(documents)
+
+                if total_docs == 0:
+                    self.console.print(
+                        "[yellow]No documents found in database.[/yellow]"
+                    )
+                    return
+
+                self.console.print(
+                    f"[b]Rebuilding database with {total_docs} documents...[/b]"
+                )
+                with Progress() as progress:
+                    task = progress.add_task("Rebuilding...", total=total_docs)
+                    async for _ in client.rebuild_database():
+                        progress.update(task, advance=1)
+
+                self.console.print("[b]Database rebuild completed successfully.[/b]")
+            except Exception as e:
+                self.console.print(f"[red]Error rebuilding database: {e}[/red]")
+
+    def show_settings(self):
+        """Display current configuration settings."""
+        self.console.print("[bold]haiku.rag configuration[/bold]")
+        self.console.print()
+
+        # Get all config fields dynamically
+        for field_name, field_value in Config.model_dump().items():
+            # Format the display value
+            if isinstance(field_value, str) and (
+                "key" in field_name.lower()
+                or "password" in field_name.lower()
+                or "token" in field_name.lower()
+            ):
+                # Hide sensitive values but show if they're set
+                display_value = "✓ Set" if field_value else "✗ Not set"
+            else:
+                display_value = field_value
+
+            self.console.print(f"  [cyan]{field_name}[/cyan]: {display_value}")
+
     def _rich_print_document(self, doc: Document, truncate: bool = False):
         """Format a document for display."""
         if truncate:
@@ -99,6 +144,12 @@ class HaikuRAGApp:
             f"[repr.attrib_name]document_id[/repr.attrib_name]: {chunk.document_id} "
             f"[repr.attrib_name]score[/repr.attrib_name]: {score:.4f}"
         )
+        if chunk.document_uri:
+            self.console.print("[repr.attrib_name]document uri[/repr.attrib_name]:")
+            self.console.print(chunk.document_uri)
+        if chunk.document_meta:
+            self.console.print("[repr.attrib_name]document meta[/repr.attrib_name]:")
+            self.console.print(chunk.document_meta)
         self.console.print("[repr.attrib_name]content[/repr.attrib_name]:")
         self.console.print(content)
         self.console.rule()

haiku/rag/cli.py

@@ -128,6 +128,27 @@ def ask(
     event_loop.run_until_complete(app.ask(question=question))
 
 
+@cli.command("settings", help="Display current configuration settings")
+def settings():
+    app = HaikuRAGApp(db_path=Path())  # Don't need actual DB for settings
+    app.show_settings()
+
+
+@cli.command(
+    "rebuild",
+    help="Rebuild the database by deleting all chunks and re-indexing all documents",
+)
+def rebuild(
+    db: Path = typer.Option(
+        get_default_data_dir() / "haiku.rag.sqlite",
+        "--db",
+        help="Path to the SQLite database file",
+    ),
+):
+    app = HaikuRAGApp(db_path=db)
+    event_loop.run_until_complete(app.rebuild())
+
+
 @cli.command(
     "serve", help="Start the haiku.rag MCP server (by default in streamable HTTP mode)"
 )

haiku/rag/client.py

@@ -1,6 +1,7 @@
 import hashlib
 import mimetypes
 import tempfile
+from collections.abc import AsyncGenerator
 from pathlib import Path
 from typing import Literal
 from urllib.parse import urlparse
@@ -270,6 +271,29 @@ class HaikuRAG:
         qa_agent = get_qa_agent(self)
         return await qa_agent.answer(question)
 
+    async def rebuild_database(self) -> AsyncGenerator[int, None]:
+        """Rebuild the database by deleting all chunks and re-indexing all documents.
+
+        Yields:
+            int: The ID of the document currently being processed
+        """
+        documents = await self.list_documents()
+
+        if not documents:
+            return
+
+        await self.chunk_repository.delete_all()
+
+        for doc in documents:
+            if doc.id is not None:
+                await self.chunk_repository.create_chunks_for_document(
+                    doc.id, doc.content, commit=False
+                )
+                yield doc.id
+
+        if self.store._connection:
+            self.store._connection.commit()
+
     def close(self):
         """Close the underlying store connection."""
         self.store.close()

haiku/rag/config.py

@@ -30,6 +30,7 @@ class AppConfig(BaseModel):
     # Provider keys
     VOYAGE_API_KEY: str = ""
     OPENAI_API_KEY: str = ""
+    ANTHROPIC_API_KEY: str = ""
 
     @field_validator("MONITOR_DIRECTORIES", mode="before")
     @classmethod
@@ -49,3 +50,5 @@ if Config.OPENAI_API_KEY:
     os.environ["OPENAI_API_KEY"] = Config.OPENAI_API_KEY
 if Config.VOYAGE_API_KEY:
     os.environ["VOYAGE_API_KEY"] = Config.VOYAGE_API_KEY
+if Config.ANTHROPIC_API_KEY:
+    os.environ["ANTHROPIC_API_KEY"] = Config.ANTHROPIC_API_KEY

haiku/rag/qa/__init__.py

@@ -8,7 +8,6 @@ def get_qa_agent(client: HaikuRAG, model: str = "") -> QuestionAnswerAgentBase:
     """
     Factory function to get the appropriate QA agent based on the configuration.
     """
-
     if Config.QA_PROVIDER == "ollama":
         return QuestionAnswerOllamaAgent(client, model or Config.QA_MODEL)
 
@@ -21,6 +20,17 @@ def get_qa_agent(client: HaikuRAG, model: str = "") -> QuestionAnswerAgentBase:
                 "Please install haiku.rag with the 'openai' extra:"
                 "uv pip install haiku.rag --extra openai"
             )
-        return QuestionAnswerOpenAIAgent(client, model or "gpt-4o-mini")
+        return QuestionAnswerOpenAIAgent(client, model or Config.QA_MODEL)
+
+    if Config.QA_PROVIDER == "anthropic":
+        try:
+            from haiku.rag.qa.anthropic import QuestionAnswerAnthropicAgent
+        except ImportError:
+            raise ImportError(
+                "Anthropic QA agent requires the 'anthropic' package. "
+                "Please install haiku.rag with the 'anthropic' extra:"
+                "uv pip install haiku.rag --extra anthropic"
+            )
+        return QuestionAnswerAnthropicAgent(client, model or Config.QA_MODEL)
 
     raise ValueError(f"Unsupported QA provider: {Config.QA_PROVIDER}")

haiku/rag/qa/anthropic.py

@@ -0,0 +1,112 @@
+from collections.abc import Sequence
+
+try:
+    from anthropic import AsyncAnthropic
+    from anthropic.types import MessageParam, TextBlock, ToolParam, ToolUseBlock
+
+    from haiku.rag.client import HaikuRAG
+    from haiku.rag.qa.base import QuestionAnswerAgentBase
+
+    class QuestionAnswerAnthropicAgent(QuestionAnswerAgentBase):
+        def __init__(self, client: HaikuRAG, model: str = "claude-3-5-haiku-20241022"):
+            super().__init__(client, model or self._model)
+            self.tools: Sequence[ToolParam] = [
+                ToolParam(
+                    name="search_documents",
+                    description="Search the knowledge base for relevant documents",
+                    input_schema={
+                        "type": "object",
+                        "properties": {
+                            "query": {
+                                "type": "string",
+                                "description": "The search query to find relevant documents",
+                            },
+                            "limit": {
+                                "type": "integer",
+                                "description": "Maximum number of results to return",
+                                "default": 3,
+                            },
+                        },
+                        "required": ["query"],
+                    },
+                )
+            ]
+
+        async def answer(self, question: str) -> str:
+            anthropic_client = AsyncAnthropic()
+
+            messages: list[MessageParam] = [{"role": "user", "content": question}]
+
+            response = await anthropic_client.messages.create(
+                model=self._model,
+                max_tokens=4096,
+                system=self._system_prompt,
+                messages=messages,
+                tools=self.tools,
+                temperature=0.0,
+            )
+
+            if response.stop_reason == "tool_use":
+                messages.append({"role": "assistant", "content": response.content})
+
+                # Process tool calls
+                tool_results = []
+                for content_block in response.content:
+                    if isinstance(content_block, ToolUseBlock):
+                        if content_block.name == "search_documents":
+                            args = content_block.input
+                            query = (
+                                args.get("query", question)
+                                if isinstance(args, dict)
+                                else question
+                            )
+                            limit = (
+                                int(args.get("limit", 3))
+                                if isinstance(args, dict)
+                                else 3
+                            )
+
+                            search_results = await self._client.search(
+                                query, limit=limit
+                            )
+
+                            context_chunks = []
+                            for chunk, score in search_results:
+                                context_chunks.append(
+                                    f"Content: {chunk.content}\nScore: {score:.4f}"
+                                )
+
+                            context = "\n\n".join(context_chunks)
+
+                            tool_results.append(
+                                {
+                                    "type": "tool_result",
+                                    "tool_use_id": content_block.id,
+                                    "content": context,
+                                }
+                            )
+
+                if tool_results:
+                    messages.append({"role": "user", "content": tool_results})
+
+                    final_response = await anthropic_client.messages.create(
+                        model=self._model,
+                        max_tokens=4096,
+                        system=self._system_prompt,
+                        messages=messages,
+                        temperature=0.0,
+                    )
+                    if final_response.content:
+                        first_content = final_response.content[0]
+                        if isinstance(first_content, TextBlock):
+                            return first_content.text
+                    return ""
+
+            if response.content:
+                first_content = response.content[0]
+                if isinstance(first_content, TextBlock):
+                    return first_content.text
+            return ""
+
+except ImportError:
+    pass

haiku/rag/store/repositories/chunk.py

@@ -208,6 +208,22 @@ class ChunkRepository(BaseRepository[Chunk]):
 
         return created_chunks
 
+    async def delete_all(self, commit: bool = True) -> bool:
+        """Delete all chunks from the database."""
+        if self.store._connection is None:
+            raise ValueError("Store connection is not available")
+
+        cursor = self.store._connection.cursor()
+
+        cursor.execute("DELETE FROM chunks_fts")
+        cursor.execute("DELETE FROM chunk_embeddings")
+        cursor.execute("DELETE FROM chunks")
+
+        deleted = cursor.rowcount > 0
+        if commit:
+            self.store._connection.commit()
+        return deleted
+
     async def delete_by_document_id(
         self, document_id: int, commit: bool = True
     ) -> bool:

{haiku_rag-0.3.0.dist-info → haiku_rag-0.3.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: haiku.rag
-Version: 0.3.0
+Version: 0.3.2
 Summary: Retrieval Augmented Generation (RAG) with SQLite
 Author-email: Yiorgis Gozadinos <ggozadinos@gmail.com>
 License: MIT
@@ -29,6 +29,8 @@ Requires-Dist: sqlite-vec>=0.1.6
 Requires-Dist: tiktoken>=0.9.0
 Requires-Dist: typer>=0.16.0
 Requires-Dist: watchfiles>=1.1.0
+Provides-Extra: anthropic
+Requires-Dist: anthropic>=0.56.0; extra == 'anthropic'
 Provides-Extra: openai
 Requires-Dist: openai>=1.0.0; extra == 'openai'
 Provides-Extra: voyageai
@@ -45,6 +47,7 @@ Retrieval-Augmented Generation (RAG) library on SQLite.
 
 - **Local SQLite**: No external servers required
 - **Multiple embedding providers**: Ollama, VoyageAI, OpenAI
+- **Multiple QA providers**: Ollama, OpenAI, Anthropic
 - **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
@@ -68,6 +71,9 @@ haiku-rag search "query"
 # Ask questions
 haiku-rag ask "Who is the author of haiku.rag?"
 
+# Rebuild database (re-chunk and re-embed all documents)
+haiku-rag rebuild
+
 # Start server with file monitoring
 export MONITOR_DIRECTORIES="/path/to/docs"
 haiku-rag serve

{haiku_rag-0.3.0.dist-info → haiku_rag-0.3.2.dist-info}/RECORD

@@ -1,9 +1,9 @@
 haiku/rag/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-haiku/rag/app.py,sha256=aiytRhpyvDMbn0uVGN-yxfwpWiwGQ_vpNbtzjGBfkOg,5436
+haiku/rag/app.py,sha256=Foi_K-sAqHWsIAAaxY2Tb0hyXnMCi06LqIFCPiBS5n0,7627
 haiku/rag/chunker.py,sha256=lSSPWgNAe7gNZL_yNLmDtqxJix4YclOiG7gbARcEpV8,1871
-haiku/rag/cli.py,sha256=rnDdC4SHUKbF02NR46F7kWVRLM2Nl-6XOU_mOYoAVCg,4456
-haiku/rag/client.py,sha256=la-8r8cD35nJjNZN5TgZfaVHVJiG1ro8Pel3ADmOCtU,10092
-haiku/rag/config.py,sha256=wXVBWqQTJ8eomSv_fRa7IX34t5jOYW9KCBz3YEkSi14,1309
+haiku/rag/cli.py,sha256=9F64IIm2c1nBKn7p9D5yYkVZr8HcjDemrzjF9SRGIY8,5017
+haiku/rag/client.py,sha256=qoVgdsP_MH8wVcDTvPIcMgW7323tTjOXH8JKugz5snY,10847
+haiku/rag/config.py,sha256=ctD_pu7nDOieirJofhNMO-OJIONLC5myvcru9iTm_ps,1433
 haiku/rag/logging.py,sha256=zTTGpGq5tPdcd7RpCbd9EGw1IZlQDbYkrCg9t9pqRc4,580
 haiku/rag/mcp.py,sha256=tMN6fNX7ZtAER1R6DL1GkC9HZozTC4HzuQs199p7icI,4551
 haiku/rag/monitor.py,sha256=r386nkhdlsU8UECwIuVwnrSlgMk3vNIuUZGNIzkZuec,2770
@@ -14,7 +14,8 @@ haiku/rag/embeddings/base.py,sha256=PTAWKTU-Q-hXIhbRK1o6pIdpaW7DFdzJXQ0Nzc6VI-w,
 haiku/rag/embeddings/ollama.py,sha256=hWdrTiuJwNSRYCqP0WP-z6XXA3RBGkAiknZMsPLH0qU,441
 haiku/rag/embeddings/openai.py,sha256=reh8AykG2f9f5hhRDmqSsjiuCPi9SsXfe2YEZFlxXk8,550
 haiku/rag/embeddings/voyageai.py,sha256=jc0JywdLJD3Ee1MUv1m8MhWCEo0enNnVcrIBtUvD-Ss,534
-haiku/rag/qa/__init__.py,sha256=k8mU7--BEIyGRyARxNShrDM8mFNxN9c9dxl8PAw5lpM,1013
+haiku/rag/qa/__init__.py,sha256=oso98Ypti7mBLTJ6Zk71YaSJ9Rgc89QXp9RSB6zSpYs,1501
+haiku/rag/qa/anthropic.py,sha256=lzHRQxpEv6Qd6iBIqexUgWnq-ITqytppwkfOuRGWdDs,4556
 haiku/rag/qa/base.py,sha256=4ZTM_l5FAZ9cA0f8NeqRJiUAmjatwCTmSoclFw0gTFQ,1349
 haiku/rag/qa/ollama.py,sha256=poShrse-RgLTwa5gbVzoERNTrn5QRpovJCZKYkIpOZI,2393
 haiku/rag/qa/openai.py,sha256=yBbSjGlG4Lo5p2B2NOTa5C6JceX0OJ1jXar_ABFZYYI,3849
@@ -26,10 +27,10 @@ haiku/rag/store/models/chunk.py,sha256=lmbPOOTz-N4PXhrA5XCUxyRcSTZBo135fqkV1mwnG
 haiku/rag/store/models/document.py,sha256=TVXVY-nQs-1vCORQEs9rA7zOtndeGC4dgCoujLAS054,396
 haiku/rag/store/repositories/__init__.py,sha256=uIBhxjQh-4o3O-ck8b7BQ58qXQTuJdPvrDIHVhY5T1A,263
 haiku/rag/store/repositories/base.py,sha256=cm3VyQXhtxvRfk1uJHpA0fDSxMpYN-mjQmRiDiLsQ68,1008
-haiku/rag/store/repositories/chunk.py,sha256=TzPbYKovC3HnTpGWkzU1zuJpphiUMoHHTKmS-4x75jk,15950
+haiku/rag/store/repositories/chunk.py,sha256=gik7ZPOK3gCoG6tU1pGueAZBPmJxIb7obYFUhwINrYg,16497
 haiku/rag/store/repositories/document.py,sha256=xpWOpjHFbhVwNJ1gpusEKNY6l_Qyibg9y_bdHCwcfpk,7133
-haiku_rag-0.3.0.dist-info/METADATA,sha256=2VTIC4nIgcS3LKPS3e32ckcLkxjwcTspdS7HVzdJCjs,3719
-haiku_rag-0.3.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-haiku_rag-0.3.0.dist-info/entry_points.txt,sha256=G1U3nAkNd5YDYd4v0tuYFbriz0i-JheCsFuT9kIoGCI,48
-haiku_rag-0.3.0.dist-info/licenses/LICENSE,sha256=eXZrWjSk9PwYFNK9yUczl3oPl95Z4V9UXH7bPN46iPo,1065
-haiku_rag-0.3.0.dist-info/RECORD,,
+haiku_rag-0.3.2.dist-info/METADATA,sha256=0A8BVZDp38i_xLznvkrZBq3f3OYtWPtqBx_U2eHRIow,3931
+haiku_rag-0.3.2.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+haiku_rag-0.3.2.dist-info/entry_points.txt,sha256=G1U3nAkNd5YDYd4v0tuYFbriz0i-JheCsFuT9kIoGCI,48
+haiku_rag-0.3.2.dist-info/licenses/LICENSE,sha256=eXZrWjSk9PwYFNK9yUczl3oPl95Z4V9UXH7bPN46iPo,1065
+haiku_rag-0.3.2.dist-info/RECORD,,