haiku.rag 0.4.0__py3-none-any.whl → 0.4.2__py3-none-any.whl

haiku/rag/cli.py

@@ -5,7 +5,8 @@ import typer
 from rich.console import Console
 
 from haiku.rag.app import HaikuRAGApp
-from haiku.rag.utils import get_default_data_dir, is_up_to_date
+from haiku.rag.config import Config
+from haiku.rag.utils import is_up_to_date
 
 cli = typer.Typer(
     context_settings={"help_option_names": ["-h", "--help"]}, no_args_is_help=True
@@ -35,7 +36,7 @@ def main():
 @cli.command("list", help="List all stored documents")
 def list_documents(
     db: Path = typer.Option(
-        get_default_data_dir() / "haiku.rag.sqlite",
+        Config.DEFAULT_DATA_DIR / "haiku.rag.sqlite",
         "--db",
         help="Path to the SQLite database file",
     ),
@@ -50,7 +51,7 @@ def add_document_text(
         help="The text content of the document to add",
     ),
     db: Path = typer.Option(
-        get_default_data_dir() / "haiku.rag.sqlite",
+        Config.DEFAULT_DATA_DIR / "haiku.rag.sqlite",
         "--db",
         help="Path to the SQLite database file",
     ),
@@ -65,7 +66,7 @@ def add_document_src(
         help="The file path or URL of the document to add",
     ),
     db: Path = typer.Option(
-        get_default_data_dir() / "haiku.rag.sqlite",
+        Config.DEFAULT_DATA_DIR / "haiku.rag.sqlite",
         "--db",
         help="Path to the SQLite database file",
     ),
@@ -80,7 +81,7 @@ def get_document(
         help="The ID of the document to get",
     ),
     db: Path = typer.Option(
-        get_default_data_dir() / "haiku.rag.sqlite",
+        Config.DEFAULT_DATA_DIR / "haiku.rag.sqlite",
         "--db",
         help="Path to the SQLite database file",
     ),
@@ -95,7 +96,7 @@ def delete_document(
         help="The ID of the document to delete",
     ),
     db: Path = typer.Option(
-        get_default_data_dir() / "haiku.rag.sqlite",
+        Config.DEFAULT_DATA_DIR / "haiku.rag.sqlite",
         "--db",
         help="Path to the SQLite database file",
     ),
@@ -121,7 +122,7 @@ def search(
         help="Reciprocal Rank Fusion k parameter",
     ),
     db: Path = typer.Option(
-        get_default_data_dir() / "haiku.rag.sqlite",
+        Config.DEFAULT_DATA_DIR / "haiku.rag.sqlite",
         "--db",
         help="Path to the SQLite database file",
     ),
@@ -136,7 +137,7 @@ def ask(
         help="The question to ask",
     ),
     db: Path = typer.Option(
-        get_default_data_dir() / "haiku.rag.sqlite",
+        Config.DEFAULT_DATA_DIR / "haiku.rag.sqlite",
         "--db",
         help="Path to the SQLite database file",
     ),
@@ -157,7 +158,7 @@ def settings():
 )
 def rebuild(
     db: Path = typer.Option(
-        get_default_data_dir() / "haiku.rag.sqlite",
+        Config.DEFAULT_DATA_DIR / "haiku.rag.sqlite",
         "--db",
         help="Path to the SQLite database file",
     ),
@@ -171,7 +172,7 @@ def rebuild(
 )
 def serve(
     db: Path = typer.Option(
-        get_default_data_dir() / "haiku.rag.sqlite",
+        Config.DEFAULT_DATA_DIR / "haiku.rag.sqlite",
         "--db",
         help="Path to the SQLite database file",
     ),

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 = {}
@@ -278,7 +283,7 @@ class HaikuRAG:
         return await self.document_repository.list_all(limit=limit, offset=offset)
 
     async def search(
-        self, query: str, limit: int = 3, k: int = 60, rerank=Config.RERANK
+        self, query: str, limit: int = 5, k: int = 60, rerank=Config.RERANK
     ) -> list[tuple[Chunk, float]]:
         """Search for relevant chunks using hybrid search (vector similarity + full-text search) with reranking.
 
@@ -298,7 +303,6 @@ class HaikuRAG:
         search_results = await self.chunk_repository.search_chunks_hybrid(
             query, limit * 3, k
         )
-
         # Apply reranking
         reranker = get_reranker()
         chunks = [chunk for chunk, _ in search_results]

haiku/rag/embeddings/__init__.py

@@ -18,7 +18,7 @@ def get_embedder() -> EmbedderBase:
             raise ImportError(
                 "VoyageAI embedder requires the 'voyageai' package. "
                 "Please install haiku.rag with the 'voyageai' extra:"
-                "uv pip install haiku.rag --extra voyageai"
+                "uv pip install haiku.rag[voyageai]"
             )
         return VoyageAIEmbedder(Config.EMBEDDINGS_MODEL, Config.EMBEDDINGS_VECTOR_DIM)
 
@@ -29,7 +29,7 @@ def get_embedder() -> EmbedderBase:
             raise ImportError(
                 "OpenAI embedder requires the 'openai' package. "
                 "Please install haiku.rag with the 'openai' extra:"
-                "uv pip install haiku.rag --extra openai"
+                "uv pip install haiku.rag[openai]"
             )
         return OpenAIEmbedder(Config.EMBEDDINGS_MODEL, Config.EMBEDDINGS_VECTOR_DIM)
 

haiku/rag/qa/__init__.py

@@ -18,7 +18,7 @@ def get_qa_agent(client: HaikuRAG, model: str = "") -> QuestionAnswerAgentBase:
             raise ImportError(
                 "OpenAI QA agent requires the 'openai' package. "
                 "Please install haiku.rag with the 'openai' extra:"
-                "uv pip install haiku.rag --extra openai"
+                "uv pip install haiku.rag[openai]"
             )
         return QuestionAnswerOpenAIAgent(client, model or Config.QA_MODEL)
 
@@ -29,7 +29,7 @@ def get_qa_agent(client: HaikuRAG, model: str = "") -> QuestionAnswerAgentBase:
             raise ImportError(
                 "Anthropic QA agent requires the 'anthropic' package. "
                 "Please install haiku.rag with the 'anthropic' extra:"
-                "uv pip install haiku.rag --extra anthropic"
+                "uv pip install haiku.rag[anthropic]"
             )
         return QuestionAnswerAnthropicAgent(client, model or Config.QA_MODEL)
 

haiku/rag/qa/ollama.py

@@ -4,7 +4,7 @@ from haiku.rag.client import HaikuRAG
 from haiku.rag.config import Config
 from haiku.rag.qa.base import QuestionAnswerAgentBase
 
-OLLAMA_OPTIONS = {"temperature": 0.0, "seed": 42, "num_ctx": 64000}
+OLLAMA_OPTIONS = {"temperature": 0.0, "seed": 42, "num_ctx": 16384}
 
 
 class QuestionAnswerOllamaAgent(QuestionAnswerAgentBase):

haiku/rag/qa/prompts.py

@@ -15,7 +15,7 @@ Guidelines:
 - Indicate when information is incomplete or when you need to search for additional context
 - If the retrieved documents don't contain sufficient information, clearly state: "I cannot find enough information in the knowledge base to answer this question."
 - For complex questions, consider breaking them down and performing multiple searches
-- Stick to the answer, do not ellaborate or provde context unless asked for it.
+- Stick to the answer, do not ellaborate or provide context unless explicitly asked for it.
 
 Be concise, and always maintain accuracy over completeness. Prefer short, direct answers that are well-supported by the documents.
 """

haiku/rag/reranking/__init__.py

@@ -29,7 +29,7 @@ def get_reranker() -> RerankerBase:
             raise ImportError(
                 "Cohere reranker requires the 'cohere' package. "
                 "Please install haiku.rag with the 'cohere' extra:"
-                "uv pip install haiku.rag --extra cohere"
+                "uv pip install haiku.rag[cohere]"
             )
         _reranker = CohereReranker()
         return _reranker

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-0.4.0.dist-info → haiku_rag-0.4.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: haiku.rag
-Version: 0.4.0
+Version: 0.4.2
 Summary: Retrieval Augmented Generation (RAG) with SQLite
 Author-email: Yiorgis Gozadinos <ggozadinos@gmail.com>
 License: MIT

{haiku_rag-0.4.0.dist-info → haiku_rag-0.4.2.dist-info}/RECORD

@@ -1,43 +1,43 @@
 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=8PC7r5odIVLyksSm_BXor2rznIZ2KDug-YhzqbFPvms,5605
-haiku/rag/client.py,sha256=W8iw22v9Muoq37e3uGww2DpbQnQhQzaPZiP9MVMRKJE,12554
+haiku/rag/cli.py,sha256=oCj65JcV2MEhzA2okbLHAK1I0FrClIKuYZx2jtbjbqE,5628
+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/utils.py,sha256=Ez_tvNlRO_D8c2CBZ83Hs9Gmzcqdq4cmw_V5GBdKy_8,2214
-haiku/rag/embeddings/__init__.py,sha256=4jUPe2FyIf8BGZ7AncWSlBdNXG3URejBbnkhQf3JiD0,1505
+haiku/rag/embeddings/__init__.py,sha256=yFBlxS0jBiVHl_rWz5kb43t6Ha132U1ZGdlIPfhzPdg,1491
 haiku/rag/embeddings/base.py,sha256=NTQvuzbZPu0LBo5wAu3qGyJ4xXUaRAt1fjBO0ygWn_Y,465
 haiku/rag/embeddings/ollama.py,sha256=y6-lp0XpbnyIjoOEdtSzMdEVkU5glOwnWQ1FkpUZnpI,370
 haiku/rag/embeddings/openai.py,sha256=i4Ui5hAJkcKqJkH9L3jJo7fuGYHn07td532w-ksg_T8,431
 haiku/rag/embeddings/voyageai.py,sha256=0hiRTIqu-bpl-4OaCtMHvWfPdgbrzhnfZJowSV8pLRA,415
-haiku/rag/qa/__init__.py,sha256=oso98Ypti7mBLTJ6Zk71YaSJ9Rgc89QXp9RSB6zSpYs,1501
+haiku/rag/qa/__init__.py,sha256=f9ZU7YDzJJoyglV1hGja1j9B6NcWerAImuKO1gFP-qs,1487
 haiku/rag/qa/anthropic.py,sha256=6I6cf6ySNkYbmDFdy22sA8r3GO5moiiH75tJnHcgJQA,4448
 haiku/rag/qa/base.py,sha256=4ZTM_l5FAZ9cA0f8NeqRJiUAmjatwCTmSoclFw0gTFQ,1349
-haiku/rag/qa/ollama.py,sha256=-UtNFErYlA_66g3WLU6lK38a1Y5zhAL6s_uZ5AP0TFs,2381
+haiku/rag/qa/ollama.py,sha256=EGUi4urSx9nrnsr5j-qHVDVOnvRTbSMKUbMvXEMIcxM,2381
 haiku/rag/qa/openai.py,sha256=dF32sGgVt8mZi5oVxByaeECs9NqLjvDiZnnpJBsrHm8,3968
-haiku/rag/qa/prompts.py,sha256=W6QYvqIGcW_VmnTA88quJqCi6h6bafEP4pyrcGze9TA,1303
-haiku/rag/reranking/__init__.py,sha256=6tuQCrk5CEfyGaUjB7uaskWxsB15GaV8t9rm7VVSMrg,1125
+haiku/rag/qa/prompts.py,sha256=8uYMxHzbzI9vo2FPkCSSNTh_RNL96WkBbUWPCMBlLpo,1315
+haiku/rag/reranking/__init__.py,sha256=DsPCdU94wRzDCYl6hz2DySOMWwOvNxKviqKAUfyykK8,1118
 haiku/rag/reranking/base.py,sha256=LM9yUSSJ414UgBZhFTgxGprlRqzfTe4I1vgjricz2JY,405
 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/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-0.4.0.dist-info/METADATA,sha256=59rxYHim3hZeKPkQhEmnNR_Tj6DuF9hLBj2GA2T3T_s,4235
-haiku_rag-0.4.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-haiku_rag-0.4.0.dist-info/entry_points.txt,sha256=G1U3nAkNd5YDYd4v0tuYFbriz0i-JheCsFuT9kIoGCI,48
-haiku_rag-0.4.0.dist-info/licenses/LICENSE,sha256=eXZrWjSk9PwYFNK9yUczl3oPl95Z4V9UXH7bPN46iPo,1065
-haiku_rag-0.4.0.dist-info/RECORD,,
+haiku_rag-0.4.2.dist-info/METADATA,sha256=0ctTSGB6uqGl2INUcNxnCphxwrLTlK7KVdKKXXB35mg,4235
+haiku_rag-0.4.2.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+haiku_rag-0.4.2.dist-info/entry_points.txt,sha256=G1U3nAkNd5YDYd4v0tuYFbriz0i-JheCsFuT9kIoGCI,48
+haiku_rag-0.4.2.dist-info/licenses/LICENSE,sha256=eXZrWjSk9PwYFNK9yUczl3oPl95Z4V9UXH7bPN46iPo,1065
+haiku_rag-0.4.2.dist-info/RECORD,,