haiku.rag 0.4.1__py3-none-any.whl → 0.4.3__py3-none-any.whl

haiku/rag/cli.py

@@ -1,4 +1,5 @@
 import asyncio
+from importlib.metadata import version
 from pathlib import Path
 
 import typer
@@ -26,8 +27,23 @@ async def check_version():
         console.print("[yellow]Please update.[/yellow]")
 
 
+def version_callback(value: bool):
+    if value:
+        v = version("haiku.rag")
+        console.print(f"haiku.rag version {v}")
+        raise typer.Exit()
+
+
 @cli.callback()
-def main():
+def main(
+    _version: bool = typer.Option(
+        False,
+        "-v",
+        "--version",
+        callback=version_callback,
+        help="Show version and exit",
+    ),
+):
     """haiku.rag CLI - SQLite-based RAG system"""
     # Run version check before any command
     event_loop.run_until_complete(check_version())

haiku/rag/client.py

@@ -50,7 +50,11 @@ class HaikuRAG:
         return False
 
     async def create_document(
-        self, content: str, uri: str | None = None, metadata: dict | None = None
+        self,
+        content: str,
+        uri: str | None = None,
+        metadata: dict | None = None,
+        chunks: list[Chunk] | None = None,
     ) -> Document:
         """Create a new document with optional URI and metadata.
 
@@ -58,6 +62,7 @@ class HaikuRAG:
             content: The text content of the document.
             uri: Optional URI identifier for the document.
             metadata: Optional metadata dictionary.
+            chunks: Optional list of pre-created chunks to use instead of generating new ones.
 
         Returns:
             The created Document instance.
@@ -67,7 +72,7 @@ class HaikuRAG:
             uri=uri,
             metadata=metadata or {},
         )
-        return await self.document_repository.create(document)
+        return await self.document_repository.create(document, chunks)
 
     async def create_document_from_source(
         self, source: str | Path, metadata: dict = {}

haiku/rag/reader.py

@@ -1,32 +1,45 @@
 from pathlib import Path
 from typing import ClassVar
 
-from markitdown import MarkItDown
+from docling.document_converter import DocumentConverter
 
 
 class FileReader:
-    extensions: ClassVar[list[str]] = [
+    # Extensions supported by docling
+    docling_extensions: ClassVar[list[str]] = [
+        ".asciidoc",
+        ".bmp",
+        ".csv",
+        ".docx",
+        ".html",
+        ".xhtml",
+        ".jpeg",
+        ".jpg",
+        ".md",
+        ".pdf.png",
+        ".pptx",
+        ".tiff",
+        ".xlsx",
+        ".xml",
+        ".webp",
+    ]
+
+    # Plain text extensions that we'll read directly
+    text_extensions: ClassVar[list[str]] = [
         ".astro",
         ".c",
         ".cpp",
         ".css",
-        ".csv",
-        ".docx",
         ".go",
         ".h",
         ".hpp",
-        ".html",
         ".java",
         ".js",
         ".json",
         ".kt",
-        ".md",
         ".mdx",
         ".mjs",
-        ".mp3",
-        ".pdf",
         ".php",
-        ".pptx",
         ".py",
         ".rb",
         ".rs",
@@ -36,17 +49,61 @@ class FileReader:
         ".tsx",
         ".txt",
         ".vue",
-        ".wav",
-        ".xml",
-        ".xlsx",
         ".yaml",
         ".yml",
     ]
 
+    # Code file extensions with their markdown language identifiers for syntax highlighting
+    code_markdown_identifier: ClassVar[dict[str, str]] = {
+        ".astro": "astro",
+        ".c": "c",
+        ".cpp": "cpp",
+        ".css": "css",
+        ".go": "go",
+        ".h": "c",
+        ".hpp": "cpp",
+        ".java": "java",
+        ".js": "javascript",
+        ".json": "json",
+        ".kt": "kotlin",
+        ".mjs": "javascript",
+        ".php": "php",
+        ".py": "python",
+        ".rb": "ruby",
+        ".rs": "rust",
+        ".svelte": "svelte",
+        ".swift": "swift",
+        ".ts": "typescript",
+        ".tsx": "tsx",
+        ".vue": "vue",
+        ".yaml": "yaml",
+        ".yml": "yaml",
+    }
+
+    extensions: ClassVar[list[str]] = docling_extensions + text_extensions
+
     @staticmethod
     def parse_file(path: Path) -> str:
         try:
-            reader = MarkItDown()
-            return reader.convert(path).text_content
+            file_extension = path.suffix.lower()
+
+            if file_extension in FileReader.docling_extensions:
+                # Use docling for complex document formats
+                converter = DocumentConverter()
+                result = converter.convert(path)
+                return result.document.export_to_markdown()
+            elif file_extension in FileReader.text_extensions:
+                # Read plain text files directly
+                content = path.read_text(encoding="utf-8")
+
+                # Wrap code files (but not plain txt) in markdown code blocks for better presentation
+                if file_extension in FileReader.code_markdown_identifier:
+                    language = FileReader.code_markdown_identifier[file_extension]
+                    return f"```{language}\n{content}\n```"
+
+                return content
+            else:
+                # Fallback: try to read as text
+                return path.read_text(encoding="utf-8")
         except Exception:
             raise ValueError(f"Failed to parse file: {path}")

haiku/rag/store/engine.py

@@ -37,6 +37,11 @@ class Store:
         db = sqlite3.connect(self.db_path)
         db.enable_load_extension(True)
         sqlite_vec.load(db)
+
+        # Enable WAL mode for better concurrency (skip for in-memory databases)
+        if self.db_path != ":memory:":
+            db.execute("PRAGMA journal_mode=WAL")
+
         self._connection = db
         existing_tables = [
             row[0]

haiku/rag/store/models/chunk.py

@@ -7,8 +7,9 @@ class Chunk(BaseModel):
     """
 
     id: int | None = None
-    document_id: int
+    document_id: int | None = None
     content: str
     metadata: dict = {}
     document_uri: str | None = None
     document_meta: dict = {}
+    embedding: list[float] | None = None

haiku/rag/store/repositories/chunk.py

@@ -18,6 +18,8 @@ class ChunkRepository(BaseRepository[Chunk]):
         """Create a chunk in the database."""
         if self.store._connection is None:
             raise ValueError("Store connection is not available")
+        if entity.document_id is None:
+            raise ValueError("Chunk must have a document_id to be created")
 
         cursor = self.store._connection.cursor()
         cursor.execute(
@@ -34,9 +36,15 @@ class ChunkRepository(BaseRepository[Chunk]):
 
         entity.id = cursor.lastrowid
 
-        # Generate and store embedding
-        embedding = await self.embedder.embed(entity.content)
-        serialized_embedding = self.store.serialize_embedding(embedding)
+        # Generate and store embedding - use existing one if provided
+        if entity.embedding is not None:
+            # Use the provided embedding
+            serialized_embedding = self.store.serialize_embedding(entity.embedding)
+        else:
+            # Generate embedding from content
+            embedding = await self.embedder.embed(entity.content)
+            serialized_embedding = self.store.serialize_embedding(embedding)
+
         cursor.execute(
             """
             INSERT INTO chunk_embeddings (chunk_id, embedding)

haiku/rag/store/repositories/document.py

@@ -1,8 +1,12 @@
 import json
+from typing import TYPE_CHECKING
 
 from haiku.rag.store.models.document import Document
 from haiku.rag.store.repositories.base import BaseRepository
 
+if TYPE_CHECKING:
+    from haiku.rag.store.models.chunk import Chunk
+
 
 class DocumentRepository(BaseRepository[Document]):
     """Repository for Document database operations."""
@@ -16,7 +20,9 @@ class DocumentRepository(BaseRepository[Document]):
             chunk_repository = ChunkRepository(store)
         self.chunk_repository = chunk_repository
 
-    async def create(self, entity: Document) -> Document:
+    async def create(
+        self, entity: Document, chunks: list["Chunk"] | None = None
+    ) -> Document:
         """Create a document with its chunks and embeddings."""
         if self.store._connection is None:
             raise ValueError("Store connection is not available")
@@ -46,10 +52,20 @@ class DocumentRepository(BaseRepository[Document]):
             assert document_id is not None, "Failed to create document in database"
             entity.id = document_id
 
-            # Create chunks and embeddings using ChunkRepository
-            await self.chunk_repository.create_chunks_for_document(
-                document_id, entity.content, commit=False
-            )
+            # Create chunks - either use provided chunks or generate from content
+            if chunks is not None:
+                # Use provided chunks, but update their document_id and set order from list position
+                for order, chunk in enumerate(chunks):
+                    chunk.document_id = document_id
+                    # Ensure order is set from list position
+                    chunk.metadata = chunk.metadata.copy() if chunk.metadata else {}
+                    chunk.metadata["order"] = order
+                    await self.chunk_repository.create(chunk, commit=False)
+            else:
+                # Create chunks and embeddings using ChunkRepository
+                await self.chunk_repository.create_chunks_for_document(
+                    document_id, entity.content, commit=False
+                )
 
             cursor.execute("COMMIT")
             return entity

{haiku_rag-0.4.1.dist-info → haiku_rag-0.4.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: haiku.rag
-Version: 0.4.1
+Version: 0.4.3
 Summary: Retrieval Augmented Generation (RAG) with SQLite
 Author-email: Yiorgis Gozadinos <ggozadinos@gmail.com>
 License: MIT
@@ -18,9 +18,9 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Typing :: Typed
 Requires-Python: >=3.10
+Requires-Dist: docling>=2.15.0
 Requires-Dist: fastmcp>=2.8.1
 Requires-Dist: httpx>=0.28.1
-Requires-Dist: markitdown[audio-transcription,docx,pdf,pptx,xlsx]>=0.1.2
 Requires-Dist: mxbai-rerank>=0.1.6
 Requires-Dist: ollama>=0.5.1
 Requires-Dist: pydantic>=2.11.7
@@ -55,7 +55,7 @@ Retrieval-Augmented Generation (RAG) library on SQLite.
 - **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
+- **40+ file formats**: PDF, DOCX, HTML, Markdown, code files, URLs
 - **MCP server**: Expose as tools for AI assistants
 - **CLI & Python API**: Use from command line or Python
 

{haiku_rag-0.4.1.dist-info → haiku_rag-0.4.3.dist-info}/RECORD

@@ -1,13 +1,13 @@
 haiku/rag/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 haiku/rag/app.py,sha256=FpLVyP1-zAq_XPmU8CPVLkuIAeuhBOGvMqhYS8RbN40,7649
 haiku/rag/chunker.py,sha256=MbCtP66OfTFoIBvqmVT9T9c87fozsYYzAQzJJEfPBVI,1812
-haiku/rag/cli.py,sha256=oCj65JcV2MEhzA2okbLHAK1I0FrClIKuYZx2jtbjbqE,5628
-haiku/rag/client.py,sha256=gqHsRAZqM5s4-c-RjeR4HanOKqPuK0z_MtsfmZMvT-w,12553
+haiku/rag/cli.py,sha256=k7EhLkvTncxsdh5TYrg8BHLYh_lfyzupsWGj1dEEdqY,5992
+haiku/rag/client.py,sha256=MZNIpMm6MS3P6vjLqiCztT2dBOM7-bZOosX5IpbHJbI,12724
 haiku/rag/config.py,sha256=_Ss54kmfxVAJupExLKaYjYUlFxJgb7hEEdbG4-isapY,1662
 haiku/rag/logging.py,sha256=zTTGpGq5tPdcd7RpCbd9EGw1IZlQDbYkrCg9t9pqRc4,580
 haiku/rag/mcp.py,sha256=tMN6fNX7ZtAER1R6DL1GkC9HZozTC4HzuQs199p7icI,4551
 haiku/rag/monitor.py,sha256=r386nkhdlsU8UECwIuVwnrSlgMk3vNIuUZGNIzkZuec,2770
-haiku/rag/reader.py,sha256=S7-Z72pDvSHedvgt4-RkTOwZadG88Oed9keJ69SVITk,962
+haiku/rag/reader.py,sha256=dLz3yyc5r8dzdqCc2VViC3fADpScw4lxXueKiu-cI7c,2915
 haiku/rag/utils.py,sha256=Ez_tvNlRO_D8c2CBZ83Hs9Gmzcqdq4cmw_V5GBdKy_8,2214
 haiku/rag/embeddings/__init__.py,sha256=yFBlxS0jBiVHl_rWz5kb43t6Ha132U1ZGdlIPfhzPdg,1491
 haiku/rag/embeddings/base.py,sha256=NTQvuzbZPu0LBo5wAu3qGyJ4xXUaRAt1fjBO0ygWn_Y,465
@@ -25,19 +25,19 @@ haiku/rag/reranking/base.py,sha256=LM9yUSSJ414UgBZhFTgxGprlRqzfTe4I1vgjricz2JY,4
 haiku/rag/reranking/cohere.py,sha256=1iTdiaa8vvb6oHVB2qpWzUOVkyfUcimVSZp6Qr4aq4c,1049
 haiku/rag/reranking/mxbai.py,sha256=46sVTsTIkzIX9THgM3u8HaEmgY7evvEyB-N54JTHvK8,867
 haiku/rag/store/__init__.py,sha256=hq0W0DAC7ysqhWSP2M2uHX8cbG6kbr-sWHxhq6qQcY0,103
-haiku/rag/store/engine.py,sha256=4ouAD0s-TFwEoEHjVVw_KnV6aaw5nwhe9fdT8PRXfok,6061
+haiku/rag/store/engine.py,sha256=cOMBToLilI1Di1qQrFzGLqtRMsuvtiX0Q5RNIEzQy9w,6232
 haiku/rag/store/models/__init__.py,sha256=s0E72zneGlowvZrFWaNxHYjOAUjgWdLxzdYsnvNRVlY,88
-haiku/rag/store/models/chunk.py,sha256=lmbPOOTz-N4PXhrA5XCUxyRcSTZBo135fqkV1mwnGcE,309
+haiku/rag/store/models/chunk.py,sha256=9-vIxW75-kMTelIhgVIMd_WhP-Drc1q65vjaWMP8w1E,364
 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=gik7ZPOK3gCoG6tU1pGueAZBPmJxIb7obYFUhwINrYg,16497
-haiku/rag/store/repositories/document.py,sha256=xpWOpjHFbhVwNJ1gpusEKNY6l_Qyibg9y_bdHCwcfpk,7133
+haiku/rag/store/repositories/chunk.py,sha256=UyvHhKb1ESZePoTp2GneAARdfKoocEdfPOwgWPPQ0v8,16878
+haiku/rag/store/repositories/document.py,sha256=fXIWevJaOe6x2cK4u9cQxiEGD0ntKQb9y3VRqklQypE,7920
 haiku/rag/store/repositories/settings.py,sha256=dme3_ulQdQvyF9daavSjAd-SjZ5hh0MJoxP7iXgap-A,2492
 haiku/rag/store/upgrades/__init__.py,sha256=kKS1YWT_P-CYKhKtokOLTIFNKf9jlfjFFr8lyIMeogM,100
 haiku/rag/store/upgrades/v0_3_4.py,sha256=GLogKZdZ40NX1vBHKdOJju7fFzNUCHoEnjSZg17Hm2U,663
-haiku_rag-0.4.1.dist-info/METADATA,sha256=Vqg_r9uBqdKh3V4dUgPGzx40cNUtXodIELD9_sU2xYs,4235
-haiku_rag-0.4.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-haiku_rag-0.4.1.dist-info/entry_points.txt,sha256=G1U3nAkNd5YDYd4v0tuYFbriz0i-JheCsFuT9kIoGCI,48
-haiku_rag-0.4.1.dist-info/licenses/LICENSE,sha256=eXZrWjSk9PwYFNK9yUczl3oPl95Z4V9UXH7bPN46iPo,1065
-haiku_rag-0.4.1.dist-info/RECORD,,
+haiku_rag-0.4.3.dist-info/METADATA,sha256=T2ZHdGL_zd1eSfEjFolh3R_zJpuWmUhKsnNkYLKtT7E,4198
+haiku_rag-0.4.3.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+haiku_rag-0.4.3.dist-info/entry_points.txt,sha256=G1U3nAkNd5YDYd4v0tuYFbriz0i-JheCsFuT9kIoGCI,48
+haiku_rag-0.4.3.dist-info/licenses/LICENSE,sha256=eXZrWjSk9PwYFNK9yUczl3oPl95Z4V9UXH7bPN46iPo,1065
+haiku_rag-0.4.3.dist-info/RECORD,,