haiku.rag 0.3.4__tar.gz → 0.4.1__tar.gz

{haiku_rag-0.3.4 → haiku_rag-0.4.1}/PKG-INFO

@@ -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 → haiku_rag-0.4.1}/README.md

@@ -10,6 +10,7 @@ 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
@@ -49,7 +50,7 @@ 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-0.4.1/docs/benchmarks.md

@@ -0,0 +1,33 @@
+# Benchmarks
+
+We use the [repliqa](https://huggingface.co/datasets/ServiceNow/repliqa) dataset for the evaluation of `haiku.rag`.
+
+You can perform your own evaluations using as example the script found at
+`tests/generate_benchmark_db.py`.
+
+## Recall
+
+In order to calculate recall, we load the `News Stories` from `repliqa_3` which is 1035 documents and index them in a sqlite db. Subsequently, we run a search over the `question` field for each row of the dataset and check whether we match the document that answers the question.
+
+
+The recall obtained is ~0.73 for matching in the top result, raising to ~0.75 for the top 3 results.
+
+| Embedding Model                       | Document in top 1 | Document in top 3 | Reranker               |
+|---------------------------------------|-------------------|-------------------|------------------------|
+| Ollama / `mxbai-embed-large`          | 0.77              | 0.89              | None                   |
+| Ollama / `mxbai-embed-large`          | 0.81              | 0.91              | `mxbai-rerank-base-v2` |
+| Ollama / `nomic-embed-text`           | 0.74              | 0.88              | None                   |
+| OpenAI / `text-embeddings-3-small`    | 0.75              | 0.88              | None                   |
+| OpenAI / `text-embeddings-3-small`    | 0.75              | 0.88              | None                   |
+| OpenAI / `text-embeddings-3-small`    | 0.83              | 0.90              | Cohere / `rerank-v3.5` |
+
+## Question/Answer evaluation
+
+Again using the same dataset, we use a QA agent to answer the question. In addition we use an LLM judge (using the Ollama `qwen3`) to evaluate whether the answer is correct or not. The obtained accuracy is as follows:
+
+| Embedding Model                    | QA Model                          | Accuracy  | Reranker               |
+|------------------------------------|-----------------------------------|-----------|------------------------|
+| Ollama / `mxbai-embed-large`       | Ollama / `qwen3`                  | 0.64      | None                   |
+| Ollama / `mxbai-embed-large`       | Ollama / `qwen3`                  | 0.72      | `mxbai-rerank-base-v2` |
+| Ollama / `mxbai-embed-large`       | Anthropic / `Claude Sonnet 3.7`   | 0.79      | None                   |
+| OpenAI / `text-embeddings-3-small` | OpenAI / `gpt-4-turbo`            | 0.62      | None                   |

{haiku_rag-0.3.4 → haiku_rag-0.4.1}/docs/configuration.md

@@ -33,7 +33,7 @@ EMBEDDINGS_VECTOR_DIM=1024
 If you want to use VoyageAI embeddings you will need to install `haiku.rag` with the VoyageAI extras,
 
 ```bash
-uv pip install haiku.rag --extra voyageai
+uv pip install haiku.rag[voyageai]
 ```
 
 ```bash
@@ -47,7 +47,7 @@ VOYAGE_API_KEY="your-api-key"
 If you want to use OpenAI embeddings you will need to install `haiku.rag` with the VoyageAI extras,
 
 ```bash
-uv pip install haiku.rag --extra openai
+uv pip install haiku.rag[openai]
 ```
 
 and set environment variables.
@@ -76,7 +76,7 @@ OLLAMA_BASE_URL="http://localhost:11434"
 For OpenAI QA, you need to install haiku.rag with OpenAI extras:
 
 ```bash
-uv pip install haiku.rag --extra openai
+uv pip install haiku.rag[openai]
 ```
 
 Then configure:
@@ -92,7 +92,7 @@ OPENAI_API_KEY="your-api-key"
 For Anthropic QA, you need to install haiku.rag with Anthropic extras:
 
 ```bash
-uv pip install haiku.rag --extra anthropic
+uv pip install haiku.rag[anthropic]
 ```
 
 Then configure:
@@ -103,6 +103,39 @@ QA_MODEL="claude-3-5-haiku-20241022"  # or claude-3-5-sonnet-20241022, etc.
 ANTHROPIC_API_KEY="your-api-key"
 ```
 
+## Reranking
+
+Reranking is **enabled by default** and improves search quality by re-ordering the initial search results using specialized models. When enabled, the system retrieves more candidates (3x the requested limit) and then reranks them to return the most relevant results.
+
+If you use the default reranked (running locally), it can slow down searching significantly. To disable reranking for faster searches:
+
+```bash
+RERANK=false
+```
+
+### MixedBread AI (Default)
+
+```bash
+RERANK_PROVIDER="mxbai"
+RERANK_MODEL="mixedbread-ai/mxbai-rerank-base-v2"
+```
+
+### Cohere
+
+For Cohere reranking, install with Cohere extras:
+
+```bash
+uv pip install haiku.rag[cohere]
+```
+
+Then configure:
+
+```bash
+RERANK_PROVIDER="cohere"
+RERANK_MODEL="rerank-v3.5"
+COHERE_API_KEY="your-api-key"
+```
+
 ## Other Settings
 
 ### Database and Storage

{haiku_rag-0.3.4 → haiku_rag-0.4.1}/docs/index.md

@@ -1,13 +1,13 @@
 # haiku.rag
 
-`haiku.rag` is a Retrieval-Augmented Generation (RAG) library built to work on SQLite alone without the need for external vector databases. It uses [sqlite-vec](https://github.com/asg017/sqlite-vec) for storing the embeddings and performs semantic (vector) search as well as full-text search combined through Reciprocal Rank Fusion. Both open-source (Ollama) as well as commercial (OpenAI, VoyageAI) embedding providers are supported.
-
+`haiku.rag` is a Retrieval-Augmented Generation (RAG) library built to work on SQLite alone without the need for external vector databases. It uses [sqlite-vec](https://github.com/asg017/sqlite-vec) for storing the embeddings and performs semantic (vector) search as well as full-text search combined through Reciprocal Rank Fusion. Both open-source (Ollama, MixedBread AI) as well as commercial (OpenAI, VoyageAI) embedding providers are supported.
 
 ## Features
 
 - **Local SQLite**: No need to run additional servers
 - **Support for various embedding providers**: Ollama, VoyageAI, OpenAI or add your own
 - **Hybrid Search**: Vector search using `sqlite-vec` combined with full-text search `FTS5`, using Reciprocal Rank Fusion
+- **Reranking**: Optional result reranking with MixedBread AI or Cohere
 - **Question Answering**: Built-in QA agents using Ollama, OpenAI, or Anthropic.
 - **File monitoring**: Automatically index files when run as a server
 - **Extended file format support**: Parse 40+ file formats including PDF, DOCX, HTML, Markdown, audio and more. Or add a URL!
@@ -34,7 +34,7 @@ async with HaikuRAG("database.db") as client:
     results = await client.search("query")
 
     # Ask questions
-    answer = await client.ask("Who is the author of haiku.rag?")
+    answer = await client.ask("Who is the author of haiku.rag?", rerank=False)
 ```
 
 Or use the CLI:

{haiku_rag-0.3.4 → haiku_rag-0.4.1}/docs/installation.md

@@ -15,19 +15,19 @@ For other embedding providers, install with extras:
 ### VoyageAI
 
 ```bash
-uv pip install haiku.rag --extra voyageai
+uv pip install haiku.rag[voyageai]
 ```
 
 ### OpenAI
 
 ```bash
-uv pip install haiku.rag --extra openai
+uv pip install haiku.rag[openai]
 ```
 
 ### Anthropic
 
 ```bash
-uv pip install haiku.rag --extra anthropic
+uv pip install haiku.rag[anthropic]
 ```
 
 ## Requirements

{haiku_rag-0.3.4 → haiku_rag-0.4.1}/docs/python.md

@@ -76,7 +76,9 @@ async for doc_id in client.rebuild_database():
 
 ## Searching Documents
 
-Basic search:
+The search method performs hybrid search (vector + full-text) with **reranking enabled by default** for improved relevance:
+
+Basic search (with reranking):
 ```python
 results = await client.search("machine learning algorithms", limit=5)
 for chunk, score in results:
@@ -90,7 +92,8 @@ With options:
 results = await client.search(
     query="machine learning",
     limit=5,  # Maximum results to return
-    k=60      # RRF parameter for reciprocal rank fusion
+    k=60,     # RRF parameter for reciprocal rank fusion
+    rerank=False  # Disable reranking for faster search
 )
 
 # Process results

{haiku_rag-0.3.4 → haiku_rag-0.4.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "haiku.rag"
-version = "0.3.4"
+version = "0.4.1"
 description = "Retrieval Augmented Generation (RAG) with SQLite"
 authors = [{ name = "Yiorgis Gozadinos", email = "ggozadinos@gmail.com" }]
 license = { text = "MIT" }
@@ -25,6 +25,7 @@ dependencies = [
     "fastmcp>=2.8.1",
     "httpx>=0.28.1",
     "markitdown[audio-transcription,docx,pdf,pptx,xlsx]>=0.1.2",
+    "mxbai-rerank>=0.1.6",
     "ollama>=0.5.1",
     "pydantic>=2.11.7",
     "python-dotenv>=1.1.0",
@@ -39,6 +40,7 @@ dependencies = [
 voyageai = ["voyageai>=0.3.2"]
 openai = ["openai>=1.0.0"]
 anthropic = ["anthropic>=0.56.0"]
+cohere = ["cohere>=5.16.1"]
 
 [project.scripts]
 haiku-rag = "haiku.rag.cli:cli"

{haiku_rag-0.3.4 → haiku_rag-0.4.1}/src/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-0.3.4 → haiku_rag-0.4.1}/src/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-0.3.4 → haiku_rag-0.4.1}/src/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-0.3.4 → haiku_rag-0.4.1}/src/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-0.3.4 → haiku_rag-0.4.1}/src/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-0.3.4 → haiku_rag-0.4.1}/src/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-0.3.4 → haiku_rag-0.4.1}/src/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-0.3.4 → haiku_rag-0.4.1}/src/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-0.3.4 → haiku_rag-0.4.1}/src/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-0.3.4 → haiku_rag-0.4.1}/src/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-0.3.4 → haiku_rag-0.4.1}/src/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):