haiku.rag 0.13.0__tar.gz → 0.13.1__tar.gz

{haiku_rag-0.13.0 → haiku_rag-0.13.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: haiku.rag
-Version: 0.13.0
+Version: 0.13.1
 Summary: Agentic Retrieval Augmented Generation (RAG) with LanceDB
 Author-email: Yiorgis Gozadinos <ggozadinos@gmail.com>
 License: MIT
@@ -40,6 +40,8 @@ Description-Content-Type: text/markdown
 
 # Haiku RAG
 
+mcp-name: io.github.ggozad/haiku-rag
+
 Retrieval-Augmented Generation (RAG) library built on LanceDB.
 
 `haiku.rag` is a Retrieval-Augmented Generation (RAG) library built to work with LanceDB as a local vector database. It uses LanceDB for storing embeddings and performs semantic (vector) search as well as full-text search combined through native hybrid search with Reciprocal Rank Fusion. Both open-source (Ollama) as well as commercial (OpenAI, VoyageAI) embedding providers are supported.

{haiku_rag-0.13.0 → haiku_rag-0.13.1}/README.md

@@ -1,5 +1,7 @@
 # Haiku RAG
 
+mcp-name: io.github.ggozad/haiku-rag
+
 Retrieval-Augmented Generation (RAG) library built on LanceDB.
 
 `haiku.rag` is a Retrieval-Augmented Generation (RAG) library built to work with LanceDB as a local vector database. It uses LanceDB for storing embeddings and performs semantic (vector) search as well as full-text search combined through native hybrid search with Reciprocal Rank Fusion. Both open-source (Ollama) as well as commercial (OpenAI, VoyageAI) embedding providers are supported.

{haiku_rag-0.13.0 → haiku_rag-0.13.1}/pyproject.toml

@@ -2,7 +2,7 @@
 
 name = "haiku.rag"
 description = "Agentic Retrieval Augmented Generation (RAG) with LanceDB"
-version = "0.13.0"
+version = "0.13.1"
 authors = [{ name = "Yiorgis Gozadinos", email = "ggozadinos@gmail.com" }]
 license = { text = "MIT" }
 readme = { file = "README.md", content-type = "text/markdown" }

haiku_rag-0.13.1/server.json

@@ -0,0 +1,42 @@
+{
+    "$schema": "https://static.modelcontextprotocol.io/schemas/2025-10-17/server.schema.json",
+    "name": "io.github.ggozad/haiku-rag",
+    "version": "{{VERSION}}",
+    "description": "Agentic Retrieval Augmented Generation (RAG) with LanceDB",
+    "repository": {
+        "url": "https://github.com/ggozad/haiku.rag",
+        "source": "github"
+    },
+    "license": "MIT",
+    "keywords": [
+        "rag",
+        "lancedb",
+        "vector-database",
+        "embeddings",
+        "search",
+        "qa",
+        "research"
+    ],
+    "packages": [
+        {
+            "registryType": "pypi",
+            "registryBaseUrl": "https://pypi.org",
+            "identifier": "haiku-rag",
+            "version": "{{VERSION}}",
+            "runtimeHint": "uvx",
+            "runtimeArguments": [
+                {
+                    "type": "positional",
+                    "value": "serve"
+                },
+                {
+                    "type": "named",
+                    "name": "--mcp"
+                }
+            ],
+            "transport": {
+                "type": "stdio"
+            }
+        }
+    ]
+}

{haiku_rag-0.13.0 → haiku_rag-0.13.1}/src/haiku/rag/config/__init__.py

@@ -1,7 +1,6 @@
 import os
 
 from haiku.rag.config.loader import (
-    check_for_deprecated_env,
     find_config_file,
     generate_default_config,
     load_config_from_env,
@@ -49,6 +48,3 @@ if config_path:
     Config = AppConfig.model_validate(yaml_data)
 else:
     Config = AppConfig()
-
-# Check for deprecated .env file
-check_for_deprecated_env()

{haiku_rag-0.13.0 → haiku_rag-0.13.1}/src/haiku/rag/config/loader.py

@@ -1,5 +1,4 @@
 import os
-import warnings
 from pathlib import Path
 
 import yaml
@@ -45,19 +44,6 @@ def load_yaml_config(path: Path) -> dict:
     return data or {}
 
 
-def check_for_deprecated_env() -> None:
-    """Check for .env file and warn if found."""
-    env_file = Path.cwd() / ".env"
-    if env_file.exists():
-        warnings.warn(
-            ".env file detected but YAML configuration is now preferred. "
-            "Environment variable configuration is deprecated and will be removed in future versions."
-            "Run 'haiku-rag init-config' to generate a YAML config file.",
-            DeprecationWarning,
-            stacklevel=2,
-        )
-
-
 def generate_default_config() -> dict:
     """Generate a default YAML config structure with documentation."""
     return {

{haiku_rag-0.13.0 → haiku_rag-0.13.1}/src/haiku/rag/config/models.py

@@ -46,7 +46,11 @@ class ProcessingConfig(BaseModel):
 
 
 class OllamaConfig(BaseModel):
-    base_url: str = "http://localhost:11434"
+    base_url: str = Field(
+        default_factory=lambda: __import__("os").environ.get(
+            "OLLAMA_BASE_URL", "http://localhost:11434"
+        )
+    )
 
 
 class VLLMConfig(BaseModel):

{haiku_rag-0.13.0 → haiku_rag-0.13.1}/src/haiku/rag/embeddings/__init__.py

@@ -15,7 +15,9 @@ def get_embedder(config: AppConfig = Config) -> EmbedderBase:
     """
 
     if config.embeddings.provider == "ollama":
-        return OllamaEmbedder(config.embeddings.model, config.embeddings.vector_dim)
+        return OllamaEmbedder(
+            config.embeddings.model, config.embeddings.vector_dim, config
+        )
 
     if config.embeddings.provider == "voyageai":
         try:
@@ -26,16 +28,22 @@ def get_embedder(config: AppConfig = Config) -> EmbedderBase:
                 "Please install haiku.rag with the 'voyageai' extra: "
                 "uv pip install haiku.rag[voyageai]"
             )
-        return VoyageAIEmbedder(config.embeddings.model, config.embeddings.vector_dim)
+        return VoyageAIEmbedder(
+            config.embeddings.model, config.embeddings.vector_dim, config
+        )
 
     if config.embeddings.provider == "openai":
         from haiku.rag.embeddings.openai import Embedder as OpenAIEmbedder
 
-        return OpenAIEmbedder(config.embeddings.model, config.embeddings.vector_dim)
+        return OpenAIEmbedder(
+            config.embeddings.model, config.embeddings.vector_dim, config
+        )
 
     if config.embeddings.provider == "vllm":
         from haiku.rag.embeddings.vllm import Embedder as VllmEmbedder
 
-        return VllmEmbedder(config.embeddings.model, config.embeddings.vector_dim)
+        return VllmEmbedder(
+            config.embeddings.model, config.embeddings.vector_dim, config
+        )
 
     raise ValueError(f"Unsupported embedding provider: {config.embeddings.provider}")

{haiku_rag-0.13.0 → haiku_rag-0.13.1}/src/haiku/rag/embeddings/base.py

@@ -1,15 +1,17 @@
 from typing import overload
 
-from haiku.rag.config import Config
+from haiku.rag.config import AppConfig, Config
 
 
 class EmbedderBase:
     _model: str = Config.embeddings.model
     _vector_dim: int = Config.embeddings.vector_dim
+    _config: AppConfig = Config
 
-    def __init__(self, model: str, vector_dim: int):
+    def __init__(self, model: str, vector_dim: int, config: AppConfig = Config):
         self._model = model
         self._vector_dim = vector_dim
+        self._config = config
 
     @overload
     async def embed(self, text: str) -> list[float]: ...

{haiku_rag-0.13.0 → haiku_rag-0.13.1}/src/haiku/rag/embeddings/ollama.py

@@ -2,7 +2,6 @@ from typing import overload
 
 from openai import AsyncOpenAI
 
-from haiku.rag.config import Config
 from haiku.rag.embeddings.base import EmbedderBase
 
 
@@ -15,7 +14,7 @@ class Embedder(EmbedderBase):
 
     async def embed(self, text: str | list[str]) -> list[float] | list[list[float]]:
         client = AsyncOpenAI(
-            base_url=f"{Config.providers.ollama.base_url}/v1", api_key="dummy"
+            base_url=f"{self._config.providers.ollama.base_url}/v1", api_key="dummy"
         )
         if not text:
             return []

{haiku_rag-0.13.0 → haiku_rag-0.13.1}/src/haiku/rag/embeddings/vllm.py

@@ -2,7 +2,6 @@ from typing import overload
 
 from openai import AsyncOpenAI
 
-from haiku.rag.config import Config
 from haiku.rag.embeddings.base import EmbedderBase
 
 
@@ -15,7 +14,8 @@ class Embedder(EmbedderBase):
 
     async def embed(self, text: str | list[str]) -> list[float] | list[list[float]]:
         client = AsyncOpenAI(
-            base_url=f"{Config.providers.vllm.embeddings_base_url}/v1", api_key="dummy"
+            base_url=f"{self._config.providers.vllm.embeddings_base_url}/v1",
+            api_key="dummy",
         )
         if not text:
             return []

{haiku_rag-0.13.0 → haiku_rag-0.13.1}/uv.lock

@@ -1123,7 +1123,7 @@ wheels = [
 
 [[package]]
 name = "haiku-rag"
-version = "0.13.0"
+version = "0.13.1"
 source = { editable = "." }
 dependencies = [
     { name = "docling" },

haiku_rag-0.13.0/server.json

@@ -1,253 +0,0 @@
-{
-  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-09-29/server.schema.json",
-  "name": "io.github.ggozad/haiku-rag",
-  "version": "{{VERSION}}",
-  "description": "Agentic Retrieval Augmented Generation (RAG) with LanceDB",
-  "repository": {
-    "url": "https://github.com/ggozad/haiku.rag",
-    "source": "github"
-  },
-  "homepage": "https://github.com/ggozad/haiku.rag",
-  "license": "MIT",
-  "keywords": ["rag", "lancedb", "vector-database", "embeddings", "search", "qa", "research"],
-  "vendor": {
-    "name": "Yiorgis Gozadinos",
-    "url": "https://github.com/ggozad"
-  },
-  "deployment": {
-    "packages": [
-      {
-        "type": "pypi",
-        "package": "haiku.rag",
-        "command": {
-          "linux-x86_64": {
-            "shell": "uvx",
-            "args": ["haiku.rag", "serve", "--stdio"]
-          },
-          "darwin-arm64": {
-            "shell": "uvx",
-            "args": ["haiku.rag", "serve", "--stdio"]
-          },
-          "darwin-x86_64": {
-            "shell": "uvx",
-            "args": ["haiku.rag", "serve", "--stdio"]
-          },
-          "win32-x86_64": {
-            "shell": "uvx.exe",
-            "args": ["haiku.rag", "serve", "--stdio"]
-          }
-        },
-        "environmentVariables": [
-          {
-            "name": "ENV",
-            "description": "Runtime environment (production or development)",
-            "format": "string",
-            "isRequired": false,
-            "isSecret": false
-          },
-          {
-            "name": "DEFAULT_DATA_DIR",
-            "description": "Default directory for LanceDB data and assets",
-            "format": "string",
-            "isRequired": false,
-            "isSecret": false
-          },
-          {
-            "name": "MONITOR_DIRECTORIES",
-            "description": "Comma-separated paths to watch for file changes in server mode",
-            "format": "string",
-            "isRequired": false,
-            "isSecret": false
-          },
-          {
-            "name": "LANCEDB_URI",
-            "description": "LanceDB connection URI (use db:// for cloud or a filesystem path)",
-            "format": "string",
-            "isRequired": false,
-            "isSecret": false
-          },
-          {
-            "name": "LANCEDB_REGION",
-            "description": "LanceDB cloud region (if using cloud)",
-            "format": "string",
-            "isRequired": false,
-            "isSecret": false
-          },
-          {
-            "name": "LANCEDB_API_KEY",
-            "description": "LanceDB API key (required for LanceDB Cloud)",
-            "format": "string",
-            "isRequired": false,
-            "isSecret": true
-          },
-          {
-            "name": "EMBEDDINGS_PROVIDER",
-            "description": "Embeddings provider (e.g. ollama, openai, voyageai)",
-            "format": "string",
-            "isRequired": false,
-            "isSecret": false
-          },
-          {
-            "name": "EMBEDDINGS_MODEL",
-            "description": "Embeddings model name (provider-specific)",
-            "format": "string",
-            "isRequired": false,
-            "isSecret": false
-          },
-          {
-            "name": "EMBEDDINGS_VECTOR_DIM",
-            "description": "Embedding vector dimension (must match model)",
-            "format": "number",
-            "isRequired": false,
-            "isSecret": false
-          },
-          {
-            "name": "QA_PROVIDER",
-            "description": "Question answering provider (e.g. ollama, openai, anthropic)",
-            "format": "string",
-            "isRequired": false,
-            "isSecret": false
-          },
-          {
-            "name": "QA_MODEL",
-            "description": "Question answering model name (provider-specific)",
-            "format": "string",
-            "isRequired": false,
-            "isSecret": false
-          },
-          {
-            "name": "RESEARCH_PROVIDER",
-            "description": "Research provider for multi-agent research (e.g. ollama, openai, anthropic)",
-            "format": "string",
-            "isRequired": false,
-            "isSecret": false
-          },
-          {
-            "name": "RESEARCH_MODEL",
-            "description": "Research model name for multi-agent research (provider-specific)",
-            "format": "string",
-            "isRequired": false,
-            "isSecret": false
-          },
-          {
-            "name": "RERANK_PROVIDER",
-            "description": "Rerank provider (e.g. mixedbread, cohere)",
-            "format": "string",
-            "isRequired": false,
-            "isSecret": false
-          },
-          {
-            "name": "RERANK_MODEL",
-            "description": "Rerank model name (provider-specific)",
-            "format": "string",
-            "isRequired": false,
-            "isSecret": false
-          },
-          {
-            "name": "CHUNK_SIZE",
-            "description": "Chunk size for splitting documents (characters)",
-            "format": "number",
-            "isRequired": false,
-            "isSecret": false
-          },
-          {
-            "name": "CONTEXT_CHUNK_RADIUS",
-            "description": "Number of adjacent chunks to include around search hits",
-            "format": "number",
-            "isRequired": false,
-            "isSecret": false
-          },
-          {
-            "name": "OLLAMA_BASE_URL",
-            "description": "Base URL for Ollama server",
-            "format": "string",
-            "isRequired": false,
-            "isSecret": false
-          },
-          {
-            "name": "VLLM_EMBEDDINGS_BASE_URL",
-            "description": "Base URL for vLLM embeddings endpoint",
-            "format": "string",
-            "isRequired": false,
-            "isSecret": false
-          },
-          {
-            "name": "VLLM_RERANK_BASE_URL",
-            "description": "Base URL for vLLM rerank endpoint",
-            "format": "string",
-            "isRequired": false,
-            "isSecret": false
-          },
-          {
-            "name": "VLLM_QA_BASE_URL",
-            "description": "Base URL for vLLM QA endpoint",
-            "format": "string",
-            "isRequired": false,
-            "isSecret": false
-          },
-          {
-            "name": "VLLM_RESEARCH_BASE_URL",
-            "description": "Base URL for vLLM research endpoint",
-            "format": "string",
-            "isRequired": false,
-            "isSecret": false
-          },
-          {
-            "name": "MARKDOWN_PREPROCESSOR",
-            "description": "Dotted path or file path to a callable that preprocesses markdown content before chunking",
-            "format": "string",
-            "isRequired": false,
-            "isSecret": false
-          },
-          {
-            "name": "DISABLE_DB_AUTOCREATE",
-            "description": "If true, refuse to auto-create a new LanceDB database or tables",
-            "format": "boolean",
-            "isRequired": false,
-            "isSecret": false
-          },
-          {
-            "name": "VACUUM_RETENTION_SECONDS",
-            "description": "Vacuum retention threshold in seconds (default: 60)",
-            "format": "number",
-            "isRequired": false,
-            "isSecret": false
-          },
-          {
-            "name": "OPENAI_API_KEY",
-            "description": "OpenAI API key (if using OpenAI for embeddings or QA)",
-            "format": "string",
-            "isRequired": false,
-            "isSecret": true
-          },
-          {
-            "name": "VOYAGE_API_KEY",
-            "description": "VoyageAI API key (if using VoyageAI for embeddings)",
-            "format": "string",
-            "isRequired": false,
-            "isSecret": true
-          },
-          {
-            "name": "ANTHROPIC_API_KEY",
-            "description": "Anthropic API key (if using Anthropic for QA)",
-            "format": "string",
-            "isRequired": false,
-            "isSecret": true
-          },
-          {
-            "name": "COHERE_API_KEY",
-            "description": "Cohere API key (if using Cohere for reranking)",
-            "format": "string",
-            "isRequired": false,
-            "isSecret": true
-          }
-        ]
-      }
-    ]
-  },
-  "transports": [
-    {
-      "type": "stdio"
-    }
-  ]
-}