haiku.rag 0.3.4__py3-none-any.whl → 0.4.1__py3-none-any.whl

haiku/rag/chunker.py

@@ -6,15 +6,11 @@ from haiku.rag.config import Config
 
 
 class Chunker:
-    """
-    A class that chunks text into smaller pieces for embedding and retrieval.
-
-    Parameters
-    ----------
-    chunk_size : int
-        The maximum size of a chunk in characters.
-    chunk_overlap : int
-        The number of characters of overlap between chunks.
+    """A class that chunks text into smaller pieces for embedding and retrieval.
+
+    Args:
+        chunk_size: The maximum size of a chunk in tokens.
+        chunk_overlap: The number of tokens of overlap between chunks.
     """
 
     encoder: ClassVar[tiktoken.Encoding] = tiktoken.encoding_for_model("gpt-4o")
@@ -28,18 +24,13 @@ class Chunker:
         self.chunk_overlap = chunk_overlap
 
     async def chunk(self, text: str) -> list[str]:
-        """
-        Split the text into chunks.
+        """Split the text into chunks based on token boundaries.
 
-        Parameters
-        ----------
-        text : str
-            The text to be split into chunks.
+        Args:
+            text: The text to be split into chunks.
 
-        Returns
-        -------
-        list
-            A list of text chunks.
+        Returns:
+            A list of text chunks with token-based boundaries and overlap.
         """
         if not text:
             return []

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

@@ -10,6 +10,7 @@ import httpx
 
 from haiku.rag.config import Config
 from haiku.rag.reader import FileReader
+from haiku.rag.reranking import get_reranker
 from haiku.rag.store.engine import Store
 from haiku.rag.store.models.chunk import Chunk
 from haiku.rag.store.models.document import Document
@@ -26,7 +27,12 @@ class HaikuRAG:
         / "haiku.rag.sqlite",
         skip_validation: bool = False,
     ):
-        """Initialize the RAG client with a database path."""
+        """Initialize the RAG client with a database path.
+
+        Args:
+            db_path: Path to the SQLite database file or ":memory:" for in-memory database.
+            skip_validation: Whether to skip configuration validation on database load.
+        """
         if isinstance(db_path, Path):
             if not db_path.parent.exists():
                 Path.mkdir(db_path.parent, parents=True)
@@ -46,7 +52,16 @@ class HaikuRAG:
     async def create_document(
         self, content: str, uri: str | None = None, metadata: dict | None = None
     ) -> Document:
-        """Create a new document with optional URI and metadata."""
+        """Create a new document with optional URI and metadata.
+
+        Args:
+            content: The text content of the document.
+            uri: Optional URI identifier for the document.
+            metadata: Optional metadata dictionary.
+
+        Returns:
+            The created Document instance.
+        """
         document = Document(
             content=content,
             uri=uri,
@@ -219,11 +234,25 @@ class HaikuRAG:
         return ".html"
 
     async def get_document_by_id(self, document_id: int) -> Document | None:
-        """Get a document by its ID."""
+        """Get a document by its ID.
+
+        Args:
+            document_id: The unique identifier of the document.
+
+        Returns:
+            The Document instance if found, None otherwise.
+        """
         return await self.document_repository.get_by_id(document_id)
 
     async def get_document_by_uri(self, uri: str) -> Document | None:
-        """Get a document by its URI."""
+        """Get a document by its URI.
+
+        Args:
+            uri: The URI identifier of the document.
+
+        Returns:
+            The Document instance if found, None otherwise.
+        """
         return await self.document_repository.get_by_uri(uri)
 
     async def update_document(self, document: Document) -> Document:
@@ -237,32 +266,54 @@ class HaikuRAG:
     async def list_documents(
         self, limit: int | None = None, offset: int | None = None
     ) -> list[Document]:
-        """List all documents with optional pagination."""
+        """List all documents with optional pagination.
+
+        Args:
+            limit: Maximum number of documents to return.
+            offset: Number of documents to skip.
+
+        Returns:
+            List of Document instances.
+        """
         return await self.document_repository.list_all(limit=limit, offset=offset)
 
     async def search(
-        self, query: str, limit: int = 5, k: int = 60
+        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).
+        """Search for relevant chunks using hybrid search (vector similarity + full-text search) with reranking.
 
         Args:
-            query: The search query string
-            limit: Maximum number of results to return
-            k: Parameter for Reciprocal Rank Fusion (default: 60)
+            query: The search query string.
+            limit: Maximum number of results to return.
+            k: Parameter for Reciprocal Rank Fusion (default: 60).
 
         Returns:
-            List of (chunk, score) tuples ordered by relevance
+            List of (chunk, score) tuples ordered by relevance.
         """
-        return await self.chunk_repository.search_chunks_hybrid(query, limit, k)
+
+        if not rerank:
+            return await self.chunk_repository.search_chunks_hybrid(query, limit, k)
+
+        # Get more initial results (3X) for reranking
+        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]
+        reranked_results = await reranker.rerank(query, chunks, top_n=limit)
+
+        # Return reranked results with scores from reranker
+        return reranked_results
 
     async def ask(self, question: str) -> str:
         """Ask a question using the configured QA agent.
 
         Args:
-            question: The question to ask
+            question: The question to ask.
 
         Returns:
-            The generated answer as a string
+            The generated answer as a string.
         """
         from haiku.rag.qa import get_qa_agent
 

haiku/rag/config.py

@@ -19,6 +19,10 @@ class AppConfig(BaseModel):
     EMBEDDINGS_MODEL: str = "mxbai-embed-large"
     EMBEDDINGS_VECTOR_DIM: int = 1024
 
+    RERANK: bool = True
+    RERANK_PROVIDER: str = "mxbai"
+    RERANK_MODEL: str = "mixedbread-ai/mxbai-rerank-base-v2"
+
     QA_PROVIDER: str = "ollama"
     QA_MODEL: str = "qwen3"
 
@@ -31,6 +35,7 @@ class AppConfig(BaseModel):
     VOYAGE_API_KEY: str = ""
     OPENAI_API_KEY: str = ""
     ANTHROPIC_API_KEY: str = ""
+    COHERE_API_KEY: str = ""
 
     @field_validator("MONITOR_DIRECTORIES", mode="before")
     @classmethod
@@ -52,3 +57,5 @@ 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
+if Config.COHERE_API_KEY:
+    os.environ["CO_API_KEY"] = Config.COHERE_API_KEY

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/embeddings/base.py

@@ -1,6 +1,9 @@
+from haiku.rag.config import Config
+
+
 class EmbedderBase:
-    _model: str = ""
-    _vector_dim: int = 0
+    _model: str = Config.EMBEDDINGS_MODEL
+    _vector_dim: int = Config.EMBEDDINGS_VECTOR_DIM
 
     def __init__(self, model: str, vector_dim: int):
         self._model = model

haiku/rag/embeddings/ollama.py

@@ -5,9 +5,6 @@ from haiku.rag.embeddings.base import EmbedderBase
 
 
 class Embedder(EmbedderBase):
-    _model: str = Config.EMBEDDINGS_MODEL
-    _vector_dim: int = 1024
-
     async def embed(self, text: str) -> list[float]:
         client = AsyncClient(host=Config.OLLAMA_BASE_URL)
         res = await client.embeddings(model=self._model, prompt=text)

haiku/rag/embeddings/openai.py

@@ -1,13 +1,9 @@
 try:
     from openai import AsyncOpenAI
 
-    from haiku.rag.config import Config
     from haiku.rag.embeddings.base import EmbedderBase
 
     class Embedder(EmbedderBase):
-        _model: str = Config.EMBEDDINGS_MODEL
-        _vector_dim: int = 1536
-
         async def embed(self, text: str) -> list[float]:
             client = AsyncOpenAI()
             response = await client.embeddings.create(

haiku/rag/embeddings/voyageai.py

@@ -1,13 +1,9 @@
 try:
     from voyageai.client import Client  # type: ignore
 
-    from haiku.rag.config import Config
     from haiku.rag.embeddings.base import EmbedderBase
 
     class Embedder(EmbedderBase):
-        _model: str = Config.EMBEDDINGS_MODEL
-        _vector_dim: int = 1024
-
         async def embed(self, text: str) -> list[float]:
             client = Client()
             res = client.embed([text], model=self._model, output_dtype="float")

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

@@ -6,7 +6,7 @@ Your process:
 2. Search with specific keywords and phrases from the user's question
 3. Review the search results and their relevance scores
 4. If you need additional context, perform follow-up searches with different keywords
-5. Provide a comprehensive answer based only on the retrieved documents
+5. Provide a short and to the point comprehensive answer based only on the retrieved documents
 
 Guidelines:
 - Base your answers strictly on the provided document content
@@ -15,6 +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 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

@@ -0,0 +1,37 @@
+from haiku.rag.config import Config
+from haiku.rag.reranking.base import RerankerBase
+
+try:
+    from haiku.rag.reranking.cohere import CohereReranker
+except ImportError:
+    pass
+
+_reranker: RerankerBase | None = None
+
+
+def get_reranker() -> RerankerBase:
+    """
+    Factory function to get the appropriate reranker based on the configuration.
+    """
+    global _reranker
+    if _reranker is not None:
+        return _reranker
+    if Config.RERANK_PROVIDER == "mxbai":
+        from haiku.rag.reranking.mxbai import MxBAIReranker
+
+        _reranker = MxBAIReranker()
+        return _reranker
+
+    if Config.RERANK_PROVIDER == "cohere":
+        try:
+            from haiku.rag.reranking.cohere import CohereReranker
+        except ImportError:
+            raise ImportError(
+                "Cohere reranker requires the 'cohere' package. "
+                "Please install haiku.rag with the 'cohere' extra:"
+                "uv pip install haiku.rag[cohere]"
+            )
+        _reranker = CohereReranker()
+        return _reranker
+
+    raise ValueError(f"Unsupported reranker provider: {Config.RERANK_PROVIDER}")

haiku/rag/reranking/base.py

@@ -0,0 +1,13 @@
+from haiku.rag.config import Config
+from haiku.rag.store.models.chunk import Chunk
+
+
+class RerankerBase:
+    _model: str = Config.RERANK_MODEL
+
+    async def rerank(
+        self, query: str, chunks: list[Chunk], top_n: int = 10
+    ) -> list[tuple[Chunk, float]]:
+        raise NotImplementedError(
+            "Reranker is an abstract class. Please implement the rerank method in a subclass."
+        )

haiku/rag/reranking/cohere.py

@@ -0,0 +1,34 @@
+from haiku.rag.config import Config
+from haiku.rag.reranking.base import RerankerBase
+from haiku.rag.store.models.chunk import Chunk
+
+try:
+    import cohere
+except ImportError as e:
+    raise ImportError(
+        "cohere is not installed. Please install it with `pip install cohere` or use the cohere optional dependency."
+    ) from e
+
+
+class CohereReranker(RerankerBase):
+    def __init__(self):
+        self._client = cohere.ClientV2(api_key=Config.COHERE_API_KEY)
+
+    async def rerank(
+        self, query: str, chunks: list[Chunk], top_n: int = 10
+    ) -> list[tuple[Chunk, float]]:
+        if not chunks:
+            return []
+
+        documents = [chunk.content for chunk in chunks]
+
+        response = self._client.rerank(
+            model=self._model, query=query, documents=documents, top_n=top_n
+        )
+
+        reranked_chunks = []
+        for result in response.results:
+            original_chunk = chunks[result.index]
+            reranked_chunks.append((original_chunk, result.relevance_score))
+
+        return reranked_chunks

haiku/rag/reranking/mxbai.py

@@ -0,0 +1,28 @@
+from mxbai_rerank import MxbaiRerankV2
+
+from haiku.rag.config import Config
+from haiku.rag.reranking.base import RerankerBase
+from haiku.rag.store.models.chunk import Chunk
+
+
+class MxBAIReranker(RerankerBase):
+    def __init__(self):
+        self._client = MxbaiRerankV2(
+            Config.RERANK_MODEL, disable_transformers_warnings=True
+        )
+
+    async def rerank(
+        self, query: str, chunks: list[Chunk], top_n: int = 10
+    ) -> list[tuple[Chunk, float]]:
+        if not chunks:
+            return []
+
+        documents = [chunk.content for chunk in chunks]
+
+        results = self._client.rank(query=query, documents=documents, top_k=top_n)
+        reranked_chunks = []
+        for result in results:
+            original_chunk = chunks[result.index]
+            reranked_chunks.append((original_chunk, result.score))
+
+        return reranked_chunks

haiku/rag/utils.py

@@ -7,15 +7,14 @@ from packaging.version import Version, parse
 
 
 def get_default_data_dir() -> Path:
-    """
-    Get the user data directory for the current system platform.
+    """Get the user data directory for the current system platform.
 
     Linux: ~/.local/share/haiku.rag
     macOS: ~/Library/Application Support/haiku.rag
     Windows: C:/Users/<USER>/AppData/Roaming/haiku.rag
 
-    :return: User Data Path
-    :rtype: Path
+    Returns:
+        User Data Path.
     """
     home = Path.home()
 
@@ -30,13 +29,13 @@ def get_default_data_dir() -> Path:
 
 
 def semantic_version_to_int(version: str) -> int:
-    """
-    Convert a semantic version string to an integer.
+    """Convert a semantic version string to an integer.
+
+    Args:
+        version: Semantic version string.
 
-    :param version: Semantic version string
-    :type version: str
-    :return: Integer representation of semantic version
-    :rtype: int
+    Returns:
+        Integer representation of semantic version.
     """
     major, minor, patch = version.split(".")
     major = int(major) << 16
@@ -46,13 +45,13 @@ def semantic_version_to_int(version: str) -> int:
 
 
 def int_to_semantic_version(version: int) -> str:
-    """
-    Convert an integer to a semantic version string.
+    """Convert an integer to a semantic version string.
+
+    Args:
+        version: Integer representation of semantic version.
 
-    :param version: Integer representation of semantic version
-    :type version: int
-    :return: Semantic version string
-    :rtype: str
+    Returns:
+        Semantic version string.
     """
     major = version >> 16
     minor = (version >> 8) & 255
@@ -61,11 +60,11 @@ def int_to_semantic_version(version: int) -> str:
 
 
 async def is_up_to_date() -> tuple[bool, Version, Version]:
-    """
-    Checks whether haiku.rag is current.
+    """Check whether haiku.rag is current.
 
-    :return: A tuple containing a boolean indicating whether haiku.rag is current, the running version and the latest version
-    :rtype: tuple[bool, Version, Version]
+    Returns:
+        A tuple containing a boolean indicating whether haiku.rag is current,
+        the running version and the latest version.
     """
 
     async with httpx.AsyncClient() as client:

{haiku_rag-0.3.4.dist-info → haiku_rag-0.4.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: haiku.rag
-Version: 0.3.4
+Version: 0.4.1
 Summary: Retrieval Augmented Generation (RAG) with SQLite
 Author-email: Yiorgis Gozadinos <ggozadinos@gmail.com>
 License: MIT
@@ -21,6 +21,7 @@ Requires-Python: >=3.10
 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
 Requires-Dist: python-dotenv>=1.1.0
@@ -31,6 +32,8 @@ 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: cohere
+Requires-Dist: cohere>=5.16.1; extra == 'cohere'
 Provides-Extra: openai
 Requires-Dist: openai>=1.0.0; extra == 'openai'
 Provides-Extra: voyageai
@@ -49,6 +52,7 @@ Retrieval-Augmented Generation (RAG) library on SQLite.
 - **Multiple embedding providers**: Ollama, VoyageAI, OpenAI
 - **Multiple QA providers**: Ollama, OpenAI, Anthropic
 - **Hybrid search**: Vector + full-text search with Reciprocal Rank Fusion
+- **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
@@ -88,7 +92,7 @@ async with HaikuRAG("database.db") as client:
     # Add document
     doc = await client.create_document("Your content")
 
-    # Search
+    # Search (reranking enabled by default)
     results = await client.search("query")
     for chunk, score in results:
         print(f"{score:.3f}: {chunk.content}")

{haiku_rag-0.3.4.dist-info → haiku_rag-0.4.1.dist-info}/RECORD

@@ -1,25 +1,29 @@
 haiku/rag/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 haiku/rag/app.py,sha256=FpLVyP1-zAq_XPmU8CPVLkuIAeuhBOGvMqhYS8RbN40,7649
-haiku/rag/chunker.py,sha256=lSSPWgNAe7gNZL_yNLmDtqxJix4YclOiG7gbARcEpV8,1871
-haiku/rag/cli.py,sha256=8PC7r5odIVLyksSm_BXor2rznIZ2KDug-YhzqbFPvms,5605
-haiku/rag/client.py,sha256=AeRXw67E1dr6ICI6EJE1q0WwZgA6ezwFw55v6QVydYk,11014
-haiku/rag/config.py,sha256=ctD_pu7nDOieirJofhNMO-OJIONLC5myvcru9iTm_ps,1433
+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/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=flQqO12OIqApINYAfkg8VDXBgRDFVR_HRaIaydk_OBQ,2310
-haiku/rag/embeddings/__init__.py,sha256=4jUPe2FyIf8BGZ7AncWSlBdNXG3URejBbnkhQf3JiD0,1505
-haiku/rag/embeddings/base.py,sha256=PTAWKTU-Q-hXIhbRK1o6pIdpaW7DFdzJXQ0Nzc6VI-w,379
-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=oso98Ypti7mBLTJ6Zk71YaSJ9Rgc89QXp9RSB6zSpYs,1501
+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
+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=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=578LJGZJ0LQ_q7ccyj5hLabtHo8Zcfw5-DiLGN9lC-w,1200
+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
@@ -32,8 +36,8 @@ haiku/rag/store/repositories/document.py,sha256=xpWOpjHFbhVwNJ1gpusEKNY6l_Qyibg9
 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-0.3.4.dist-info/METADATA,sha256=9FEVS2pZkPrRYVGd1qaMmfjyxr4fc9sHx1NTeyCbTo0,4019
-haiku_rag-0.3.4.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-haiku_rag-0.3.4.dist-info/entry_points.txt,sha256=G1U3nAkNd5YDYd4v0tuYFbriz0i-JheCsFuT9kIoGCI,48
-haiku_rag-0.3.4.dist-info/licenses/LICENSE,sha256=eXZrWjSk9PwYFNK9yUczl3oPl95Z4V9UXH7bPN46iPo,1065
-haiku_rag-0.3.4.dist-info/RECORD,,
+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,,