feat: add custom embedding types and migrate providers

- introduce baseembeddingsprovider and helper for embedding functions  
- add core embedding types and migrate providers, factory, and storage modules  
- remove unused type aliases and fix pydantic schema error  
- update providers with env var support and related fixes

pyproject.toml

@@ -72,6 +72,15 @@ aisuite = [
 qdrant = [
     "qdrant-client[fastembed]>=1.14.3",
 ]
+aws = [
+    "boto3>=1.40.38",
+]
+watson = [
+    "ibm-watsonx-ai>=1.3.39",
+]
+voyageai = [
+    "voyageai>=0.3.5",
+]
 
 [dependency-groups]
 dev = [

src/crewai/knowledge/storage/knowledge_storage.py

@@ -8,7 +8,9 @@ from crewai.rag.chromadb.config import ChromaDBConfig
 from crewai.rag.chromadb.types import ChromaEmbeddingFunctionWrapper
 from crewai.rag.config.utils import get_rag_client
 from crewai.rag.core.base_client import BaseClient
-from crewai.rag.embeddings.factory import EmbedderConfig, get_embedding_function
+from crewai.rag.core.base_embeddings_provider import BaseEmbeddingsProvider
+from crewai.rag.embeddings.factory import build_embedder
+from crewai.rag.embeddings.types import ProviderSpec
 from crewai.rag.factory import create_client
 from crewai.rag.types import BaseRecord, SearchResult
 from crewai.utilities.logger import Logger
@@ -22,12 +24,11 @@ class KnowledgeStorage(BaseKnowledgeStorage):
 
     def __init__(
         self,
-        embedder: dict[str, Any] | None = None,
+        embedder: ProviderSpec | BaseEmbeddingsProvider | None = None,
         collection_name: str | None = None,
     ) -> None:
         self.collection_name = collection_name
         self._client: BaseClient | None = None
-        self._embedder_config = embedder  # Store embedder config
 
         warnings.filterwarnings(
             "ignore",
@@ -36,29 +37,12 @@ class KnowledgeStorage(BaseKnowledgeStorage):
         )
 
         if embedder:
-            # Cast to EmbedderConfig for type checking
+            embedding_function = build_embedder(embedder)
-            embedder_typed = cast(EmbedderConfig, embedder)
+            config = ChromaDBConfig(
-            embedding_function = get_embedding_function(embedder_typed)
+                embedding_function=cast(
-            batch_size = None
+                    ChromaEmbeddingFunctionWrapper, embedding_function
-            if isinstance(embedder, dict) and "config" in embedder:
-                nested_config = embedder["config"]
-                if isinstance(nested_config, dict):
-                    batch_size = nested_config.get("batch_size")
-
-            # Create config with batch_size if provided
-            if batch_size is not None:
-                config = ChromaDBConfig(
-                    embedding_function=cast(
-                        ChromaEmbeddingFunctionWrapper, embedding_function
-                    ),
-                    batch_size=batch_size,
-                )
-            else:
-                config = ChromaDBConfig(
-                    embedding_function=cast(
-                        ChromaEmbeddingFunctionWrapper, embedding_function
-                    )
                 )
+            )
             self._client = create_client(config)
 
     def _get_client(self) -> BaseClient:
@@ -123,23 +107,9 @@ class KnowledgeStorage(BaseKnowledgeStorage):
 
             rag_documents: list[BaseRecord] = [{"content": doc} for doc in documents]
 
-            batch_size = None
+            client.add_documents(
-            if self._embedder_config and isinstance(self._embedder_config, dict):
+                collection_name=collection_name, documents=rag_documents
-                if "config" in self._embedder_config:
+            )
-                    nested_config = self._embedder_config["config"]
-                    if isinstance(nested_config, dict):
-                        batch_size = nested_config.get("batch_size")
-
-            if batch_size is not None:
-                client.add_documents(
-                    collection_name=collection_name,
-                    documents=rag_documents,
-                    batch_size=batch_size,
-                )
-            else:
-                client.add_documents(
-                    collection_name=collection_name, documents=rag_documents
-                )
         except Exception as e:
             if "dimension mismatch" in str(e).lower():
                 Logger(verbose=True).log(

src/crewai/memory/storage/rag_storage.py

@@ -7,8 +7,9 @@ from crewai.rag.chromadb.config import ChromaDBConfig
 from crewai.rag.chromadb.types import ChromaEmbeddingFunctionWrapper
 from crewai.rag.config.utils import get_rag_client
 from crewai.rag.core.base_client import BaseClient
-from crewai.rag.embeddings.factory import EmbedderConfig, get_embedding_function
+from crewai.rag.core.base_embeddings_provider import BaseEmbeddingsProvider
-from crewai.rag.embeddings.types import EmbeddingOptions
+from crewai.rag.embeddings.factory import build_embedder
+from crewai.rag.embeddings.types import ProviderSpec
 from crewai.rag.factory import create_client
 from crewai.rag.storage.base_rag_storage import BaseRAGStorage
 from crewai.rag.types import BaseRecord
@@ -26,7 +27,7 @@ class RAGStorage(BaseRAGStorage):
         self,
         type: str,
         allow_reset: bool = True,
-        embedder_config: EmbeddingOptions | EmbedderConfig | None = None,
+        embedder_config: ProviderSpec | BaseEmbeddingsProvider | None = None,
         crew: Any = None,
         path: str | None = None,
     ) -> None:
@@ -50,15 +51,17 @@ class RAGStorage(BaseRAGStorage):
         )
 
         if self.embedder_config:
-            embedding_function = get_embedding_function(self.embedder_config)
+            embedding_function = build_embedder(self.embedder_config)
 
             try:
                 _ = embedding_function(["test"])
             except Exception as e:
                 provider = (
-                    self.embedder_config.provider
+                    self.embedder_config["provider"]
-                    if isinstance(self.embedder_config, EmbeddingOptions)
+                    if isinstance(self.embedder_config, dict)
-                    else self.embedder_config.get("provider", "unknown")
+                    else self.embedder_config.__class__.__name__.replace(
+                        "Provider", ""
+                    ).lower()
                 )
                 raise ValueError(
                     f"Failed to initialize embedder. Please check your configuration or connection.\n"
@@ -80,7 +83,7 @@ class RAGStorage(BaseRAGStorage):
                     embedding_function=cast(
                         ChromaEmbeddingFunctionWrapper, embedding_function
                     ),
-                    batch_size=batch_size,
+                    batch_size=cast(int, batch_size),
                 )
             else:
                 config = ChromaDBConfig(
@@ -142,7 +145,7 @@ class RAGStorage(BaseRAGStorage):
                 client.add_documents(
                     collection_name=collection_name,
                     documents=[document],
-                    batch_size=batch_size,
+                    batch_size=cast(int, batch_size),
                 )
             else:
                 client.add_documents(

src/crewai/rag/core/base_embeddings_callable.py

@@ -0,0 +1,142 @@
+"""Base embeddings callable utilities for RAG systems."""
+
+from typing import Protocol, TypeVar, runtime_checkable
+
+import numpy as np
+
+from crewai.rag.core.types import (
+    Embeddable,
+    Embedding,
+    Embeddings,
+    PyEmbedding,
+)
+
+T = TypeVar("T")
+D = TypeVar("D", bound=Embeddable, contravariant=True)
+
+
+def normalize_embeddings(
+    target: Embedding | list[Embedding] | PyEmbedding | list[PyEmbedding],
+) -> Embeddings | None:
+    """Normalize various embedding formats to a standard list of numpy arrays.
+
+    Args:
+        target: Input embeddings in various formats (list of floats, list of lists,
+                numpy array, or list of numpy arrays).
+
+    Returns:
+        Normalized embeddings as a list of numpy arrays, or None if input is None.
+
+    Raises:
+        ValueError: If embeddings are empty or in an unsupported format.
+    """
+    if isinstance(target, np.ndarray):
+        if target.ndim == 1:
+            return [target.astype(np.float32)]
+        if target.ndim == 2:
+            return [row.astype(np.float32) for row in target]
+        raise ValueError(f"Unsupported numpy array shape: {target.shape}")
+
+    first = target[0]
+    if isinstance(first, (int, float)) and not isinstance(first, bool):
+        return [np.array(target, dtype=np.float32)]
+    if isinstance(first, list):
+        return [np.array(emb, dtype=np.float32) for emb in target]
+    if isinstance(first, np.ndarray):
+        return [emb.astype(np.float32) for emb in target]  # type: ignore[union-attr]
+
+    raise ValueError(f"Unsupported embeddings format: {type(first)}")
+
+
+def maybe_cast_one_to_many(target: T | list[T] | None) -> list[T] | None:
+    """Cast a single item to a list if needed.
+
+    Args:
+        target: A single item or list of items.
+
+    Returns:
+        A list of items or None if input is None.
+    """
+    if target is None:
+        return None
+    return target if isinstance(target, list) else [target]
+
+
+def validate_embeddings(embeddings: Embeddings) -> Embeddings:
+    """Validate embeddings format and content.
+
+    Args:
+        embeddings: List of numpy arrays to validate.
+
+    Returns:
+        Validated embeddings.
+
+    Raises:
+        ValueError: If embeddings format or content is invalid.
+    """
+    if not isinstance(embeddings, list):
+        raise ValueError(
+            f"Expected embeddings to be a list, got {type(embeddings).__name__}"
+        )
+    if len(embeddings) == 0:
+        raise ValueError(
+            f"Expected embeddings to be a list with at least one item, got {len(embeddings)} embeddings"
+        )
+    if not all(isinstance(e, np.ndarray) for e in embeddings):
+        raise ValueError(
+            "Expected each embedding in the embeddings to be a numpy array"
+        )
+    for i, embedding in enumerate(embeddings):
+        if embedding.ndim == 0:
+            raise ValueError(
+                f"Expected a 1-dimensional array, got a 0-dimensional array {embedding}"
+            )
+        if embedding.size == 0:
+            raise ValueError(
+                f"Expected each embedding to be a 1-dimensional numpy array with at least 1 value. "
+                f"Got an array with no values at position {i}"
+            )
+        if not all(
+            isinstance(value, (np.integer, float, np.floating))
+            and not isinstance(value, bool)
+            for value in embedding
+        ):
+            raise ValueError(
+                f"Expected embedding to contain numeric values, got non-numeric values at position {i}"
+            )
+    return embeddings
+
+
+@runtime_checkable
+class EmbeddingFunction(Protocol[D]):
+    """Protocol for embedding functions.
+
+    Embedding functions convert input data (documents or images) into vector embeddings.
+    """
+
+    def __call__(self, input: D) -> Embeddings:
+        """Convert input data to embeddings.
+
+        Args:
+            input: Input data to embed (documents or images).
+
+        Returns:
+            List of numpy arrays representing the embeddings.
+        """
+        ...
+
+    def __init_subclass__(cls) -> None:
+        """Wrap __call__ method to normalize and validate embeddings."""
+        super().__init_subclass__()
+        original_call = cls.__call__
+
+        def wrapped_call(self: EmbeddingFunction[D], input: D) -> Embeddings:
+            result = original_call(self, input)
+            if result is None:
+                raise ValueError("Embedding function returned None")
+            normalized = normalize_embeddings(result)
+            if normalized is None:
+                raise ValueError("Normalization returned None for non-None input")
+            return validate_embeddings(normalized)
+
+        cls.__call__ = wrapped_call  # type: ignore[method-assign]

src/crewai/rag/core/base_embeddings_provider.py

@@ -0,0 +1,23 @@
+"""Base class for embedding providers."""
+
+from typing import Generic, TypeVar
+
+from pydantic import Field
+from pydantic_settings import BaseSettings, SettingsConfigDict
+
+from crewai.rag.core.base_embeddings_callable import EmbeddingFunction
+
+T = TypeVar("T", bound=EmbeddingFunction)
+
+
+class BaseEmbeddingsProvider(BaseSettings, Generic[T]):
+    """Abstract base class for embedding providers.
+
+    This class provides a common interface for dynamically loading and building
+    embedding functions from various providers.
+    """
+
+    model_config = SettingsConfigDict(extra="allow", populate_by_name=True)
+    embedding_callable: type[T] = Field(
+        ..., description="The embedding function class to use"
+    )

src/crewai/rag/core/types.py

@@ -0,0 +1,28 @@
+"""Core type definitions for RAG systems."""
+
+from collections.abc import Sequence
+from typing import TypeVar
+
+import numpy as np
+from numpy import floating, integer, number
+from numpy.typing import NDArray
+
+T = TypeVar("T")
+
+PyEmbedding = Sequence[float] | Sequence[int]
+PyEmbeddings = list[PyEmbedding]
+Embedding = NDArray[np.int32 | np.float32]
+Embeddings = list[Embedding]
+
+Documents = list[str]
+Images = list[np.ndarray]
+Embeddable = Documents | Images
+
+ScalarType = TypeVar("ScalarType", bound=np.generic)
+IntegerType = TypeVar("IntegerType", bound=integer)
+FloatingType = TypeVar("FloatingType", bound=floating)
+NumberType = TypeVar("NumberType", bound=number)
+
+DType32 = TypeVar("DType32", np.int32, np.float32)
+DType64 = TypeVar("DType64", np.int64, np.float64)
+DTypeCommon = TypeVar("DTypeCommon", np.int32, np.int64, np.float32, np.float64)

src/crewai/rag/embeddings/configurator.py

@@ -1,245 +0,0 @@
-import os
-from typing import Any, cast
-
-from chromadb import Documents, EmbeddingFunction, Embeddings
-from chromadb.api.types import validate_embedding_function
-
-
-class EmbeddingConfigurator:
-    def __init__(self):
-        self.embedding_functions = {
-            "openai": self._configure_openai,
-            "azure": self._configure_azure,
-            "ollama": self._configure_ollama,
-            "vertexai": self._configure_vertexai,
-            "google": self._configure_google,
-            "cohere": self._configure_cohere,
-            "voyageai": self._configure_voyageai,
-            "bedrock": self._configure_bedrock,
-            "huggingface": self._configure_huggingface,
-            "watson": self._configure_watson,
-            "custom": self._configure_custom,
-        }
-
-    def configure_embedder(
-        self,
-        embedder_config: dict[str, Any] | None = None,
-    ) -> EmbeddingFunction:
-        """Configures and returns an embedding function based on the provided config."""
-        if embedder_config is None:
-            return self._create_default_embedding_function()
-
-        provider = embedder_config.get("provider")
-        config = embedder_config.get("config", {})
-        model_name = config.get("model") if provider != "custom" else None
-
-        if provider not in self.embedding_functions:
-            raise Exception(
-                f"Unsupported embedding provider: {provider}, supported providers: {list(self.embedding_functions.keys())}"
-            )
-
-        try:
-            embedding_function = self.embedding_functions[provider]
-        except ImportError as e:
-            missing_package = str(e).split()[-1]
-            raise ImportError(
-                f"{missing_package} is not installed. Please install it with: pip install {missing_package}"
-            ) from e
-
-        return (
-            embedding_function(config)
-            if provider == "custom"
-            else embedding_function(config, model_name)
-        )
-
-    @staticmethod
-    def _create_default_embedding_function():
-        from chromadb.utils.embedding_functions.openai_embedding_function import (
-            OpenAIEmbeddingFunction,
-        )
-
-        return OpenAIEmbeddingFunction(
-            api_key=os.getenv("OPENAI_API_KEY"), model_name="text-embedding-3-small"
-        )
-
-    @staticmethod
-    def _configure_openai(config, model_name):
-        from chromadb.utils.embedding_functions.openai_embedding_function import (
-            OpenAIEmbeddingFunction,
-        )
-
-        return OpenAIEmbeddingFunction(
-            api_key=config.get("api_key") or os.getenv("OPENAI_API_KEY"),
-            model_name=model_name,
-            api_base=config.get("api_base", None),
-            api_type=config.get("api_type", None),
-            api_version=config.get("api_version", None),
-            default_headers=config.get("default_headers", None),
-            dimensions=config.get("dimensions", None),
-            deployment_id=config.get("deployment_id", None),
-            organization_id=config.get("organization_id", None),
-        )
-
-    @staticmethod
-    def _configure_azure(config, model_name):
-        from chromadb.utils.embedding_functions.openai_embedding_function import (
-            OpenAIEmbeddingFunction,
-        )
-
-        return OpenAIEmbeddingFunction(
-            api_key=config.get("api_key"),
-            api_base=config.get("api_base"),
-            api_type=config.get("api_type", "azure"),
-            api_version=config.get("api_version"),
-            model_name=model_name,
-            default_headers=config.get("default_headers"),
-            dimensions=config.get("dimensions"),
-            deployment_id=config.get("deployment_id"),
-            organization_id=config.get("organization_id"),
-        )
-
-    @staticmethod
-    def _configure_ollama(config, model_name):
-        from chromadb.utils.embedding_functions.ollama_embedding_function import (
-            OllamaEmbeddingFunction,
-        )
-
-        return OllamaEmbeddingFunction(
-            url=config.get("url", "http://localhost:11434/api/embeddings"),
-            model_name=model_name,
-        )
-
-    @staticmethod
-    def _configure_vertexai(config, model_name):
-        from chromadb.utils.embedding_functions.google_embedding_function import (
-            GoogleVertexEmbeddingFunction,
-        )
-
-        return GoogleVertexEmbeddingFunction(
-            model_name=model_name,
-            api_key=config.get("api_key"),
-            project_id=config.get("project_id"),
-            region=config.get("region"),
-        )
-
-    @staticmethod
-    def _configure_google(config, model_name):
-        from chromadb.utils.embedding_functions.google_embedding_function import (
-            GoogleGenerativeAiEmbeddingFunction,
-        )
-
-        return GoogleGenerativeAiEmbeddingFunction(
-            model_name=model_name,
-            api_key=config.get("api_key"),
-            task_type=config.get("task_type"),
-        )
-
-    @staticmethod
-    def _configure_cohere(config, model_name):
-        from chromadb.utils.embedding_functions.cohere_embedding_function import (
-            CohereEmbeddingFunction,
-        )
-
-        return CohereEmbeddingFunction(
-            model_name=model_name,
-            api_key=config.get("api_key"),
-        )
-
-    @staticmethod
-    def _configure_voyageai(config, model_name):
-        from chromadb.utils.embedding_functions.voyageai_embedding_function import (  # type: ignore[import-not-found]
-            VoyageAIEmbeddingFunction,
-        )
-
-        return VoyageAIEmbeddingFunction(
-            model_name=model_name,
-            api_key=config.get("api_key"),
-        )
-
-    @staticmethod
-    def _configure_bedrock(config, model_name):
-        from chromadb.utils.embedding_functions.amazon_bedrock_embedding_function import (
-            AmazonBedrockEmbeddingFunction,
-        )
-
-        # Allow custom model_name override with backwards compatibility
-        kwargs = {"session": config.get("session")}
-        if model_name is not None:
-            kwargs["model_name"] = model_name
-        return AmazonBedrockEmbeddingFunction(**kwargs)
-
-    @staticmethod
-    def _configure_huggingface(config, model_name):
-        from chromadb.utils.embedding_functions.huggingface_embedding_function import (
-            HuggingFaceEmbeddingServer,
-        )
-
-        return HuggingFaceEmbeddingServer(
-            url=config.get("api_url"),
-        )
-
-    @staticmethod
-    def _configure_watson(config, model_name):
-        try:
-            import ibm_watsonx_ai.foundation_models as watson_models  # type: ignore[import-not-found]
-            from ibm_watsonx_ai import Credentials  # type: ignore[import-not-found]
-            from ibm_watsonx_ai.metanames import (  # type: ignore[import-not-found]
-                EmbedTextParamsMetaNames as EmbedParams,
-            )
-        except ImportError as e:
-            raise ImportError(
-                "IBM Watson dependencies are not installed. Please install them to use Watson embedding."
-            ) from e
-
-        class WatsonEmbeddingFunction(EmbeddingFunction):
-            def __call__(self, input: Documents) -> Embeddings:
-                if isinstance(input, str):
-                    input = [input]
-
-                embed_params = {
-                    EmbedParams.TRUNCATE_INPUT_TOKENS: 3,
-                    EmbedParams.RETURN_OPTIONS: {"input_text": True},
-                }
-
-                embedding = watson_models.Embeddings(
-                    model_id=config.get("model"),
-                    params=embed_params,
-                    credentials=Credentials(
-                        api_key=config.get("api_key"), url=config.get("api_url")
-                    ),
-                    project_id=config.get("project_id"),
-                )
-
-                try:
-                    embeddings = embedding.embed_documents(input)
-                    return cast(Embeddings, embeddings)
-                except Exception as e:
-                    print("Error during Watson embedding:", e)
-                    raise e
-
-        return WatsonEmbeddingFunction()
-
-    @staticmethod
-    def _configure_custom(config):
-        custom_embedder = config.get("embedder")
-        if isinstance(custom_embedder, EmbeddingFunction):
-            try:
-                validate_embedding_function(custom_embedder)
-                return custom_embedder
-            except Exception as e:
-                raise ValueError(f"Invalid custom embedding function: {e!s}") from e
-        elif callable(custom_embedder):
-            try:
-                instance = custom_embedder()
-                if isinstance(instance, EmbeddingFunction):
-                    validate_embedding_function(instance)
-                    return instance
-                raise ValueError(
-                    "Custom embedder does not create an EmbeddingFunction instance"
-                )
-            except Exception as e:
-                raise ValueError(f"Error instantiating custom embedder: {e!s}") from e
-        else:
-            raise ValueError(
-                "Custom embedder must be an instance of `EmbeddingFunction` or a callable that creates one"
-            )

src/crewai/rag/embeddings/factory.py

@@ -1,249 +1,363 @@
-"""Minimal embedding function factory for CrewAI."""
+"""Factory functions for creating embedding providers and functions."""
 
-import os
+from __future__ import annotations
-from collections.abc import Callable, MutableMapping
-from typing import Any, Final, Literal, TypedDict
 
-from chromadb import EmbeddingFunction
+from typing import TYPE_CHECKING, TypeVar, overload
-from chromadb.utils.embedding_functions.amazon_bedrock_embedding_function import (
-    AmazonBedrockEmbeddingFunction,
-)
-from chromadb.utils.embedding_functions.cohere_embedding_function import (
-    CohereEmbeddingFunction,
-)
-from chromadb.utils.embedding_functions.google_embedding_function import (
-    GoogleGenerativeAiEmbeddingFunction,
-    GooglePalmEmbeddingFunction,
-    GoogleVertexEmbeddingFunction,
-)
-from chromadb.utils.embedding_functions.huggingface_embedding_function import (
-    HuggingFaceEmbeddingFunction,
-)
-from chromadb.utils.embedding_functions.instructor_embedding_function import (
-    InstructorEmbeddingFunction,
-)
-from chromadb.utils.embedding_functions.jina_embedding_function import (
-    JinaEmbeddingFunction,
-)
-from chromadb.utils.embedding_functions.ollama_embedding_function import (
-    OllamaEmbeddingFunction,
-)
-from chromadb.utils.embedding_functions.onnx_mini_lm_l6_v2 import ONNXMiniLM_L6_V2
-from chromadb.utils.embedding_functions.open_clip_embedding_function import (
-    OpenCLIPEmbeddingFunction,
-)
-from chromadb.utils.embedding_functions.openai_embedding_function import (
-    OpenAIEmbeddingFunction,
-)
-from chromadb.utils.embedding_functions.roboflow_embedding_function import (
-    RoboflowEmbeddingFunction,
-)
-from chromadb.utils.embedding_functions.sentence_transformer_embedding_function import (
-    SentenceTransformerEmbeddingFunction,
-)
-from chromadb.utils.embedding_functions.text2vec_embedding_function import (
-    Text2VecEmbeddingFunction,
-)
-from typing_extensions import NotRequired
 
-from crewai.rag.embeddings.types import EmbeddingOptions
+from crewai.rag.core.base_embeddings_callable import EmbeddingFunction
+from crewai.rag.core.base_embeddings_provider import BaseEmbeddingsProvider
+from crewai.utilities.import_utils import import_and_validate_definition
 
-AllowedEmbeddingProviders = Literal[
+if TYPE_CHECKING:
-    "openai",
+    from chromadb.utils.embedding_functions.amazon_bedrock_embedding_function import (
-    "cohere",
+        AmazonBedrockEmbeddingFunction,
-    "ollama",
+    )
-    "huggingface",
+    from chromadb.utils.embedding_functions.cohere_embedding_function import (
-    "sentence-transformer",
+        CohereEmbeddingFunction,
-    "instructor",
+    )
-    "google-palm",
+    from chromadb.utils.embedding_functions.google_embedding_function import (
-    "google-generativeai",
+        GoogleGenerativeAiEmbeddingFunction,
-    "google-vertex",
+        GoogleVertexEmbeddingFunction,
-    "amazon-bedrock",
+    )
-    "jina",
+    from chromadb.utils.embedding_functions.huggingface_embedding_function import (
-    "roboflow",
+        HuggingFaceEmbeddingFunction,
-    "openclip",
+    )
-    "text2vec",
+    from chromadb.utils.embedding_functions.instructor_embedding_function import (
-    "onnx",
+        InstructorEmbeddingFunction,
-]
+    )
+    from chromadb.utils.embedding_functions.jina_embedding_function import (
+        JinaEmbeddingFunction,
+    )
+    from chromadb.utils.embedding_functions.ollama_embedding_function import (
+        OllamaEmbeddingFunction,
+    )
+    from chromadb.utils.embedding_functions.onnx_mini_lm_l6_v2 import ONNXMiniLM_L6_V2
+    from chromadb.utils.embedding_functions.open_clip_embedding_function import (
+        OpenCLIPEmbeddingFunction,
+    )
+    from chromadb.utils.embedding_functions.openai_embedding_function import (
+        OpenAIEmbeddingFunction,
+    )
+    from chromadb.utils.embedding_functions.roboflow_embedding_function import (
+        RoboflowEmbeddingFunction,
+    )
+    from chromadb.utils.embedding_functions.sentence_transformer_embedding_function import (
+        SentenceTransformerEmbeddingFunction,
+    )
+    from chromadb.utils.embedding_functions.text2vec_embedding_function import (
+        Text2VecEmbeddingFunction,
+    )
+
+    from crewai.rag.embeddings.providers.aws.types import BedrockProviderSpec
+    from crewai.rag.embeddings.providers.cohere.types import CohereProviderSpec
+    from crewai.rag.embeddings.providers.custom.types import CustomProviderSpec
+    from crewai.rag.embeddings.providers.google.types import (
+        GenerativeAiProviderSpec,
+        VertexAIProviderSpec,
+    )
+    from crewai.rag.embeddings.providers.huggingface.types import (
+        HuggingFaceProviderSpec,
+    )
+    from crewai.rag.embeddings.providers.ibm.embedding_callable import (
+        WatsonEmbeddingFunction,
+    )
+    from crewai.rag.embeddings.providers.ibm.types import WatsonProviderSpec
+    from crewai.rag.embeddings.providers.instructor.types import InstructorProviderSpec
+    from crewai.rag.embeddings.providers.jina.types import JinaProviderSpec
+    from crewai.rag.embeddings.providers.microsoft.types import AzureProviderSpec
+    from crewai.rag.embeddings.providers.ollama.types import OllamaProviderSpec
+    from crewai.rag.embeddings.providers.onnx.types import ONNXProviderSpec
+    from crewai.rag.embeddings.providers.openai.types import OpenAIProviderSpec
+    from crewai.rag.embeddings.providers.openclip.types import OpenCLIPProviderSpec
+    from crewai.rag.embeddings.providers.roboflow.types import RoboflowProviderSpec
+    from crewai.rag.embeddings.providers.sentence_transformer.types import (
+        SentenceTransformerProviderSpec,
+    )
+    from crewai.rag.embeddings.providers.text2vec.types import Text2VecProviderSpec
+    from crewai.rag.embeddings.providers.voyageai.embedding_callable import (
+        VoyageAIEmbeddingFunction,
+    )
+    from crewai.rag.embeddings.providers.voyageai.types import VoyageAIProviderSpec
+
+T = TypeVar("T", bound=EmbeddingFunction)
 
 
-class EmbedderConfig(TypedDict):
+PROVIDER_PATHS = {
-    """Configuration for embedding functions with nested format."""
+    "azure": "crewai.rag.embeddings.providers.microsoft.azure.AzureProvider",
-
+    "amazon-bedrock": "crewai.rag.embeddings.providers.aws.bedrock.BedrockProvider",
-    provider: AllowedEmbeddingProviders
+    "cohere": "crewai.rag.embeddings.providers.cohere.cohere_provider.CohereProvider",
-    config: NotRequired[dict[str, Any]]
+    "custom": "crewai.rag.embeddings.providers.custom.custom_provider.CustomProvider",
-
+    "google-generativeai": "crewai.rag.embeddings.providers.google.generative_ai.GenerativeAiProvider",
-
+    "google-vertex": "crewai.rag.embeddings.providers.google.vertex.VertexAIProvider",
-EMBEDDING_PROVIDERS: Final[
+    "huggingface": "crewai.rag.embeddings.providers.huggingface.huggingface_provider.HuggingFaceProvider",
-    dict[AllowedEmbeddingProviders, Callable[..., EmbeddingFunction]]
+    "instructor": "crewai.rag.embeddings.providers.instructor.instructor_provider.InstructorProvider",
-] = {
+    "jina": "crewai.rag.embeddings.providers.jina.jina_provider.JinaProvider",
-    "openai": OpenAIEmbeddingFunction,
+    "ollama": "crewai.rag.embeddings.providers.ollama.ollama_provider.OllamaProvider",
-    "cohere": CohereEmbeddingFunction,
+    "onnx": "crewai.rag.embeddings.providers.onnx.onnx_provider.ONNXProvider",
-    "ollama": OllamaEmbeddingFunction,
+    "openai": "crewai.rag.embeddings.providers.openai.openai_provider.OpenAIProvider",
-    "huggingface": HuggingFaceEmbeddingFunction,
+    "openclip": "crewai.rag.embeddings.providers.openclip.openclip_provider.OpenCLIPProvider",
-    "sentence-transformer": SentenceTransformerEmbeddingFunction,
+    "roboflow": "crewai.rag.embeddings.providers.roboflow.roboflow_provider.RoboflowProvider",
-    "instructor": InstructorEmbeddingFunction,
+    "sentence-transformer": "crewai.rag.embeddings.providers.sentence_transformer.sentence_transformer_provider.SentenceTransformerProvider",
-    "google-palm": GooglePalmEmbeddingFunction,
+    "text2vec": "crewai.rag.embeddings.providers.text2vec.text2vec_provider.Text2VecProvider",
-    "google-generativeai": GoogleGenerativeAiEmbeddingFunction,
+    "voyageai": "crewai.rag.embeddings.providers.voyageai.voyageai_provider.VoyageAIProvider",
-    "google-vertex": GoogleVertexEmbeddingFunction,
+    "watson": "crewai.rag.embeddings.providers.ibm.watson.WatsonProvider",
-    "amazon-bedrock": AmazonBedrockEmbeddingFunction,
-    "jina": JinaEmbeddingFunction,
-    "roboflow": RoboflowEmbeddingFunction,
-    "openclip": OpenCLIPEmbeddingFunction,
-    "text2vec": Text2VecEmbeddingFunction,
-    "onnx": ONNXMiniLM_L6_V2,
-}
-
-PROVIDER_ENV_MAPPING: Final[dict[AllowedEmbeddingProviders, tuple[str, str]]] = {
-    "openai": ("OPENAI_API_KEY", "api_key"),
-    "cohere": ("COHERE_API_KEY", "api_key"),
-    "huggingface": ("HUGGINGFACE_API_KEY", "api_key"),
-    "google-palm": ("GOOGLE_API_KEY", "api_key"),
-    "google-generativeai": ("GOOGLE_API_KEY", "api_key"),
-    "google-vertex": ("GOOGLE_API_KEY", "api_key"),
-    "jina": ("JINA_API_KEY", "api_key"),
-    "roboflow": ("ROBOFLOW_API_KEY", "api_key"),
 }
 
 
-def _inject_api_key_from_env(
+def build_embedder_from_provider(provider: BaseEmbeddingsProvider[T]) -> T:
-    provider: AllowedEmbeddingProviders, config_dict: MutableMapping[str, Any]
+    """Build an embedding function instance from a provider.
-) -> None:
-    """Inject API key or other required configuration from environment if not explicitly provided.
 
     Args:
-        provider: The embedding provider name
+        provider: The embedding provider configuration.
-        config_dict: The configuration dictionary to modify in-place
-
-    Raises:
-        ImportError: If required libraries for certain providers are not installed
-        ValueError: If AWS session creation fails for amazon-bedrock
-    """
-    if provider in PROVIDER_ENV_MAPPING:
-        env_var_name, config_key = PROVIDER_ENV_MAPPING[provider]
-        if config_key not in config_dict:
-            env_value = os.getenv(env_var_name)
-            if env_value:
-                config_dict[config_key] = env_value
-
-    if provider == "amazon-bedrock":
-        if "session" not in config_dict:
-            try:
-                import boto3  # type: ignore[import]
-
-                config_dict["session"] = boto3.Session()
-            except ImportError as e:
-                raise ImportError(
-                    "boto3 is required for amazon-bedrock embeddings. "
-                    "Install it with: uv add boto3"
-                ) from e
-            except Exception as e:
-                raise ValueError(
-                    f"Failed to create AWS session for amazon-bedrock. "
-                    f"Ensure AWS credentials are configured. Error: {e}"
-                ) from e
-
-
-def get_embedding_function(
-    config: EmbeddingOptions | EmbedderConfig | None = None,
-) -> EmbeddingFunction:
-    """Get embedding function - delegates to ChromaDB.
-
-    Args:
-        config: Optional configuration - either:
-            - EmbeddingOptions: Pydantic model with flat configuration
-            - EmbedderConfig: TypedDict with nested format {"provider": str, "config": dict}
-            - None: Uses default OpenAI configuration
 
     Returns:
-        EmbeddingFunction instance ready for use with ChromaDB
+        An instance of the specified embedding function type.
+    """
+    return provider.embedding_callable(
+        **provider.model_dump(exclude={"embedding_callable"})
+    )
 
-    Supported providers:
+
-        - openai: OpenAI embeddings
+@overload
-        - cohere: Cohere embeddings
+def build_embedder_from_dict(spec: AzureProviderSpec) -> OpenAIEmbeddingFunction: ...
-        - ollama: Ollama local embeddings
+
-        - huggingface: HuggingFace embeddings
+
-        - sentence-transformer: Local sentence transformers
+@overload
-        - instructor: Instructor embeddings for specialized tasks
+def build_embedder_from_dict(
-        - google-palm: Google PaLM embeddings
+    spec: BedrockProviderSpec,
-        - google-generativeai: Google Generative AI embeddings
+) -> AmazonBedrockEmbeddingFunction: ...
-        - google-vertex: Google Vertex AI embeddings
+
-        - amazon-bedrock: AWS Bedrock embeddings
+
-        - jina: Jina AI embeddings
+@overload
-        - roboflow: Roboflow embeddings for vision tasks
+def build_embedder_from_dict(spec: CohereProviderSpec) -> CohereEmbeddingFunction: ...
-        - openclip: OpenCLIP embeddings for multimodal tasks
+
-        - text2vec: Text2Vec embeddings
+
-        - onnx: ONNX MiniLM-L6-v2 (no API key needed, included with ChromaDB)
+@overload
+def build_embedder_from_dict(spec: CustomProviderSpec) -> EmbeddingFunction: ...
+
+
+@overload
+def build_embedder_from_dict(
+    spec: GenerativeAiProviderSpec,
+) -> GoogleGenerativeAiEmbeddingFunction: ...
+
+
+@overload
+def build_embedder_from_dict(
+    spec: HuggingFaceProviderSpec,
+) -> HuggingFaceEmbeddingFunction: ...
+
+
+@overload
+def build_embedder_from_dict(spec: OllamaProviderSpec) -> OllamaEmbeddingFunction: ...
+
+
+@overload
+def build_embedder_from_dict(spec: OpenAIProviderSpec) -> OpenAIEmbeddingFunction: ...
+
+
+@overload
+def build_embedder_from_dict(
+    spec: VertexAIProviderSpec,
+) -> GoogleVertexEmbeddingFunction: ...
+
+
+@overload
+def build_embedder_from_dict(
+    spec: VoyageAIProviderSpec,
+) -> VoyageAIEmbeddingFunction: ...
+
+
+@overload
+def build_embedder_from_dict(spec: WatsonProviderSpec) -> WatsonEmbeddingFunction: ...
+
+
+@overload
+def build_embedder_from_dict(
+    spec: SentenceTransformerProviderSpec,
+) -> SentenceTransformerEmbeddingFunction: ...
+
+
+@overload
+def build_embedder_from_dict(
+    spec: InstructorProviderSpec,
+) -> InstructorEmbeddingFunction: ...
+
+
+@overload
+def build_embedder_from_dict(spec: JinaProviderSpec) -> JinaEmbeddingFunction: ...
+
+
+@overload
+def build_embedder_from_dict(
+    spec: RoboflowProviderSpec,
+) -> RoboflowEmbeddingFunction: ...
+
+
+@overload
+def build_embedder_from_dict(
+    spec: OpenCLIPProviderSpec,
+) -> OpenCLIPEmbeddingFunction: ...
+
+
+@overload
+def build_embedder_from_dict(
+    spec: Text2VecProviderSpec,
+) -> Text2VecEmbeddingFunction: ...
+
+
+@overload
+def build_embedder_from_dict(spec: ONNXProviderSpec) -> ONNXMiniLM_L6_V2: ...
+
+
+def build_embedder_from_dict(spec):
+    """Build an embedding function instance from a dictionary specification.
+
+    Args:
+        spec: A dictionary with 'provider' and 'config' keys.
+              Example: {
+                  "provider": "openai",
+                  "config": {
+                      "api_key": "sk-...",
+                      "model_name": "text-embedding-3-small"
+                  }
+              }
+
+    Returns:
+        An instance of the appropriate embedding function.
+
+    Raises:
+        ValueError: If the provider is not recognized.
+    """
+    provider_name = spec["provider"]
+    if not provider_name:
+        raise ValueError("Missing 'provider' key in specification")
+
+    if provider_name not in PROVIDER_PATHS:
+        raise ValueError(
+            f"Unknown provider: {provider_name}. Available providers: {list(PROVIDER_PATHS.keys())}"
+        )
+
+    provider_path = PROVIDER_PATHS[provider_name]
+    try:
+        provider_class = import_and_validate_definition(provider_path)
+    except (ImportError, AttributeError, ValueError) as e:
+        raise ImportError(f"Failed to import provider {provider_name}: {e}") from e
+
+    provider_config = spec.get("config", {})
+
+    if provider_name == "custom" and "embedding_callable" not in provider_config:
+        raise ValueError("Custom provider requires 'embedding_callable' in config")
+
+    provider = provider_class(**provider_config)
+    return build_embedder_from_provider(provider)
+
+
+@overload
+def build_embedder(spec: BaseEmbeddingsProvider[T]) -> T: ...
+
+
+@overload
+def build_embedder(spec: AzureProviderSpec) -> OpenAIEmbeddingFunction: ...
+
+
+@overload
+def build_embedder(spec: BedrockProviderSpec) -> AmazonBedrockEmbeddingFunction: ...
+
+
+@overload
+def build_embedder(spec: CohereProviderSpec) -> CohereEmbeddingFunction: ...
+
+
+@overload
+def build_embedder(spec: CustomProviderSpec) -> EmbeddingFunction: ...
+
+
+@overload
+def build_embedder(
+    spec: GenerativeAiProviderSpec,
+) -> GoogleGenerativeAiEmbeddingFunction: ...
+
+
+@overload
+def build_embedder(spec: HuggingFaceProviderSpec) -> HuggingFaceEmbeddingFunction: ...
+
+
+@overload
+def build_embedder(spec: OllamaProviderSpec) -> OllamaEmbeddingFunction: ...
+
+
+@overload
+def build_embedder(spec: OpenAIProviderSpec) -> OpenAIEmbeddingFunction: ...
+
+
+@overload
+def build_embedder(spec: VertexAIProviderSpec) -> GoogleVertexEmbeddingFunction: ...
+
+
+@overload
+def build_embedder(spec: VoyageAIProviderSpec) -> VoyageAIEmbeddingFunction: ...
+
+
+@overload
+def build_embedder(spec: WatsonProviderSpec) -> WatsonEmbeddingFunction: ...
+
+
+@overload
+def build_embedder(
+    spec: SentenceTransformerProviderSpec,
+) -> SentenceTransformerEmbeddingFunction: ...
+
+
+@overload
+def build_embedder(spec: InstructorProviderSpec) -> InstructorEmbeddingFunction: ...
+
+
+@overload
+def build_embedder(spec: JinaProviderSpec) -> JinaEmbeddingFunction: ...
+
+
+@overload
+def build_embedder(spec: RoboflowProviderSpec) -> RoboflowEmbeddingFunction: ...
+
+
+@overload
+def build_embedder(spec: OpenCLIPProviderSpec) -> OpenCLIPEmbeddingFunction: ...
+
+
+@overload
+def build_embedder(spec: Text2VecProviderSpec) -> Text2VecEmbeddingFunction: ...
+
+
+@overload
+def build_embedder(spec: ONNXProviderSpec) -> ONNXMiniLM_L6_V2: ...
+
+
+def build_embedder(spec):
+    """Build an embedding function from either a provider spec or a provider instance.
+
+    Args:
+        spec: Either a provider specification dictionary or a provider instance.
+
+    Returns:
+        An embedding function instance. If a typed provider is passed, returns
+        the specific embedding function type.
 
     Examples:
-        # Use default OpenAI embedding
+        # From dictionary specification
-        >>> embedder = get_embedding_function()
+        embedder = build_embedder({
+            "provider": "openai",
+            "config": {"api_key": "sk-..."}
+        })
 
-        # Use Cohere with dict
+        # From provider instance
-        >>> embedder = get_embedding_function(EmbedderConfig(**{
+        provider = OpenAIProvider(api_key="sk-...")
-        ...     "provider": "cohere",
+        embedder = build_embedder(provider)
-        ...     "config": {
-        ...         "api_key": "your-key",
-        ...         "model_name": "embed-english-v3.0"
-        ...     }
-        ... }))
-
-        # Use with EmbeddingOptions
-        >>> embedder = get_embedding_function(
-        ...     EmbeddingOptions(provider="sentence-transformer", model_name="all-MiniLM-L6-v2")
-        ... )
-
-        # Use Azure OpenAI
-        >>> embedder = get_embedding_function(EmbedderConfig(**{
-        ...     "provider": "openai",
-        ...     "config": {
-        ...         "api_key": "your-azure-key",
-        ...         "api_base": "https://your-resource.openai.azure.com/",
-        ...         "api_type": "azure",
-        ...         "api_version": "2023-05-15",
-        ...         "model": "text-embedding-3-small",
-        ...         "deployment_id": "your-deployment-name"
-        ...     }
-        ... })
-
-        >>> embedder = get_embedding_function(EmbedderConfig(**{
-        ...     "provider": "onnx"
-        ... })
     """
-    if config is None:
+    if isinstance(spec, BaseEmbeddingsProvider):
-        return OpenAIEmbeddingFunction(
+        return build_embedder_from_provider(spec)
-            api_key=os.getenv("OPENAI_API_KEY"), model_name="text-embedding-3-small"
+    return build_embedder_from_dict(spec)
-        )
 
-    provider: AllowedEmbeddingProviders
-    config_dict: dict[str, Any]
 
-    if isinstance(config, EmbeddingOptions):
+# Backward compatibility alias
-        config_dict = config.model_dump(exclude_none=True)
+get_embedding_function = build_embedder
-        provider = config_dict["provider"]
-    else:
-        provider = config["provider"]
-        nested: dict[str, Any] = config.get("config", {})
-
-        if not nested and len(config) > 1:
-            raise ValueError(
-                "Invalid embedder configuration format. "
-                "Configuration must be nested under a 'config' key. "
-                "Example: {'provider': 'openai', 'config': {'api_key': '...', 'model': '...'}}"
-            )
-
-        config_dict = dict(nested)
-        if "model" in config_dict and "model_name" not in config_dict:
-            config_dict["model_name"] = config_dict.pop("model")
-
-    if provider not in EMBEDDING_PROVIDERS:
-        raise ValueError(
-            f"Unsupported provider: {provider}. "
-            f"Available providers: {list(EMBEDDING_PROVIDERS.keys())}"
-        )
-
-    _inject_api_key_from_env(provider, config_dict)
-
-    config_dict.pop("batch_size", None)
-
-    return EMBEDDING_PROVIDERS[provider](**config_dict)

src/crewai/rag/embeddings/providers/__init__.py

@@ -0,0 +1 @@
+"""Embedding provider implementations."""

src/crewai/rag/embeddings/providers/aws/__init__.py

@@ -0,0 +1,13 @@
+"""AWS embedding providers."""
+
+from crewai.rag.embeddings.providers.aws.bedrock import BedrockProvider
+from crewai.rag.embeddings.providers.aws.types import (
+    BedrockProviderConfig,
+    BedrockProviderSpec,
+)
+
+__all__ = [
+    "BedrockProvider",
+    "BedrockProviderConfig",
+    "BedrockProviderSpec",
+]

src/crewai/rag/embeddings/providers/aws/bedrock.py

@@ -0,0 +1,58 @@
+"""Amazon Bedrock embeddings provider."""
+
+from chromadb.utils.embedding_functions.amazon_bedrock_embedding_function import (
+    AmazonBedrockEmbeddingFunction,
+)
+from pydantic import Field
+
+from crewai.rag.core.base_embeddings_provider import BaseEmbeddingsProvider
+
+try:
+    from boto3.session import Session  # type: ignore[import-untyped]
+except ImportError as exc:
+    raise ImportError(
+        "boto3 is required for amazon-bedrock embeddings. Install it with: uv add boto3"
+    ) from exc
+
+
+def create_aws_session() -> Session:
+    """Create an AWS session for Bedrock.
+
+    Returns:
+        boto3.Session: AWS session object
+
+    Raises:
+        ImportError: If boto3 is not installed
+        ValueError: If AWS session creation fails
+    """
+    try:
+        import boto3  # type: ignore[import]
+
+        return boto3.Session()
+    except ImportError as e:
+        raise ImportError(
+            "boto3 is required for amazon-bedrock embeddings. "
+            "Install it with: uv add boto3"
+        ) from e
+    except Exception as e:
+        raise ValueError(
+            f"Failed to create AWS session for amazon-bedrock. "
+            f"Ensure AWS credentials are configured. Error: {e}"
+        ) from e
+
+
+class BedrockProvider(BaseEmbeddingsProvider[AmazonBedrockEmbeddingFunction]):
+    """Amazon Bedrock embeddings provider."""
+
+    embedding_callable: type[AmazonBedrockEmbeddingFunction] = Field(
+        default=AmazonBedrockEmbeddingFunction,
+        description="Amazon Bedrock embedding function class",
+    )
+    model_name: str = Field(
+        default="amazon.titan-embed-text-v1",
+        description="Model name to use for embeddings",
+        validation_alias="BEDROCK_MODEL_NAME",
+    )
+    session: Session = Field(
+        default_factory=create_aws_session, description="AWS session object"
+    )

src/crewai/rag/embeddings/providers/aws/types.py

@@ -0,0 +1,17 @@
+"""Type definitions for AWS embedding providers."""
+
+from typing import Annotated, Any, Literal, TypedDict
+
+
+class BedrockProviderConfig(TypedDict, total=False):
+    """Configuration for Bedrock provider."""
+
+    model_name: Annotated[str, "amazon.titan-embed-text-v1"]
+    session: Any
+
+
+class BedrockProviderSpec(TypedDict):
+    """Bedrock provider specification."""
+
+    provider: Literal["amazon-bedrock"]
+    config: BedrockProviderConfig

src/crewai/rag/embeddings/providers/cohere/__init__.py

@@ -0,0 +1,13 @@
+"""Cohere embedding providers."""
+
+from crewai.rag.embeddings.providers.cohere.cohere_provider import CohereProvider
+from crewai.rag.embeddings.providers.cohere.types import (
+    CohereProviderConfig,
+    CohereProviderSpec,
+)
+
+__all__ = [
+    "CohereProvider",
+    "CohereProviderConfig",
+    "CohereProviderSpec",
+]

src/crewai/rag/embeddings/providers/cohere/cohere_provider.py

@@ -0,0 +1,24 @@
+"""Cohere embeddings provider."""
+
+from chromadb.utils.embedding_functions.cohere_embedding_function import (
+    CohereEmbeddingFunction,
+)
+from pydantic import Field
+
+from crewai.rag.core.base_embeddings_provider import BaseEmbeddingsProvider
+
+
+class CohereProvider(BaseEmbeddingsProvider[CohereEmbeddingFunction]):
+    """Cohere embeddings provider."""
+
+    embedding_callable: type[CohereEmbeddingFunction] = Field(
+        default=CohereEmbeddingFunction, description="Cohere embedding function class"
+    )
+    api_key: str = Field(
+        description="Cohere API key", validation_alias="COHERE_API_KEY"
+    )
+    model_name: str = Field(
+        default="large",
+        description="Model name to use for embeddings",
+        validation_alias="COHERE_MODEL_NAME",
+    )

src/crewai/rag/embeddings/providers/cohere/types.py

@@ -0,0 +1,17 @@
+"""Type definitions for Cohere embedding providers."""
+
+from typing import Annotated, Literal, TypedDict
+
+
+class CohereProviderConfig(TypedDict, total=False):
+    """Configuration for Cohere provider."""
+
+    api_key: str
+    model_name: Annotated[str, "large"]
+
+
+class CohereProviderSpec(TypedDict):
+    """Cohere provider specification."""
+
+    provider: Literal["cohere"]
+    config: CohereProviderConfig

src/crewai/rag/embeddings/providers/custom/__init__.py

@@ -0,0 +1,13 @@
+"""Custom embedding providers."""
+
+from crewai.rag.embeddings.providers.custom.custom_provider import CustomProvider
+from crewai.rag.embeddings.providers.custom.types import (
+    CustomProviderConfig,
+    CustomProviderSpec,
+)
+
+__all__ = [
+    "CustomProvider",
+    "CustomProviderConfig",
+    "CustomProviderSpec",
+]

src/crewai/rag/embeddings/providers/custom/custom_provider.py

@@ -0,0 +1,19 @@
+"""Custom embeddings provider for user-defined embedding functions."""
+
+from pydantic import Field
+from pydantic_settings import SettingsConfigDict
+
+from crewai.rag.core.base_embeddings_provider import BaseEmbeddingsProvider
+from crewai.rag.embeddings.providers.custom.embedding_callable import (
+    CustomEmbeddingFunction,
+)
+
+
+class CustomProvider(BaseEmbeddingsProvider[CustomEmbeddingFunction]):
+    """Custom embeddings provider for user-defined embedding functions."""
+
+    embedding_callable: type[CustomEmbeddingFunction] = Field(
+        ..., description="Custom embedding function class"
+    )
+
+    model_config = SettingsConfigDict(extra="allow")

src/crewai/rag/embeddings/providers/custom/embedding_callable.py

@@ -0,0 +1,22 @@
+"""Custom embedding function base implementation."""
+
+from crewai.rag.core.base_embeddings_callable import EmbeddingFunction
+from crewai.rag.core.types import Documents, Embeddings
+
+
+class CustomEmbeddingFunction(EmbeddingFunction[Documents]):
+    """Base class for custom embedding functions.
+
+    This provides a concrete implementation that can be subclassed for custom embeddings.
+    """
+
+    def __call__(self, input: Documents) -> Embeddings:
+        """Convert input documents to embeddings.
+
+        Args:
+            input: List of documents to embed.
+
+        Returns:
+            List of numpy arrays representing the embeddings.
+        """
+        raise NotImplementedError("Subclasses must implement __call__ method")

src/crewai/rag/embeddings/providers/custom/types.py

@@ -0,0 +1,18 @@
+"""Type definitions for custom embedding providers."""
+
+from typing import Literal, TypedDict
+
+from chromadb.api.types import EmbeddingFunction
+
+
+class CustomProviderConfig(TypedDict, total=False):
+    """Configuration for Custom provider."""
+
+    embedding_callable: type[EmbeddingFunction]
+
+
+class CustomProviderSpec(TypedDict):
+    """Custom provider specification."""
+
+    provider: Literal["custom"]
+    config: CustomProviderConfig

src/crewai/rag/embeddings/providers/google/__init__.py

@@ -0,0 +1,23 @@
+"""Google embedding providers."""
+
+from crewai.rag.embeddings.providers.google.generative_ai import (
+    GenerativeAiProvider,
+)
+from crewai.rag.embeddings.providers.google.types import (
+    GenerativeAiProviderConfig,
+    GenerativeAiProviderSpec,
+    VertexAIProviderConfig,
+    VertexAIProviderSpec,
+)
+from crewai.rag.embeddings.providers.google.vertex import (
+    VertexAIProvider,
+)
+
+__all__ = [
+    "GenerativeAiProvider",
+    "GenerativeAiProviderConfig",
+    "GenerativeAiProviderSpec",
+    "VertexAIProvider",
+    "VertexAIProviderConfig",
+    "VertexAIProviderSpec",
+]

src/crewai/rag/embeddings/providers/google/generative_ai.py

@@ -0,0 +1,30 @@
+"""Google Generative AI embeddings provider."""
+
+from chromadb.utils.embedding_functions.google_embedding_function import (
+    GoogleGenerativeAiEmbeddingFunction,
+)
+from pydantic import Field
+
+from crewai.rag.core.base_embeddings_provider import BaseEmbeddingsProvider
+
+
+class GenerativeAiProvider(BaseEmbeddingsProvider[GoogleGenerativeAiEmbeddingFunction]):
+    """Google Generative AI embeddings provider."""
+
+    embedding_callable: type[GoogleGenerativeAiEmbeddingFunction] = Field(
+        default=GoogleGenerativeAiEmbeddingFunction,
+        description="Google Generative AI embedding function class",
+    )
+    model_name: str = Field(
+        default="models/embedding-001",
+        description="Model name to use for embeddings",
+        validation_alias="GOOGLE_GENERATIVE_AI_MODEL_NAME",
+    )
+    api_key: str = Field(
+        description="Google API key", validation_alias="GOOGLE_API_KEY"
+    )
+    task_type: str = Field(
+        default="RETRIEVAL_DOCUMENT",
+        description="Task type for embeddings",
+        validation_alias="GOOGLE_GENERATIVE_AI_TASK_TYPE",
+    )

src/crewai/rag/embeddings/providers/google/types.py

@@ -0,0 +1,34 @@
+"""Type definitions for Google embedding providers."""
+
+from typing import Annotated, Literal, TypedDict
+
+
+class GenerativeAiProviderConfig(TypedDict, total=False):
+    """Configuration for Google Generative AI provider."""
+
+    api_key: str
+    model_name: Annotated[str, "models/embedding-001"]
+    task_type: Annotated[str, "RETRIEVAL_DOCUMENT"]
+
+
+class GenerativeAiProviderSpec(TypedDict):
+    """Google Generative AI provider specification."""
+
+    provider: Literal["google-generativeai"]
+    config: GenerativeAiProviderConfig
+
+
+class VertexAIProviderConfig(TypedDict, total=False):
+    """Configuration for Vertex AI provider."""
+
+    api_key: str
+    model_name: Annotated[str, "textembedding-gecko"]
+    project_id: Annotated[str, "cloud-large-language-models"]
+    region: Annotated[str, "us-central1"]
+
+
+class VertexAIProviderSpec(TypedDict):
+    """Vertex AI provider specification."""
+
+    provider: Literal["google-vertex"]
+    config: VertexAIProviderConfig

src/crewai/rag/embeddings/providers/google/vertex.py

@@ -0,0 +1,35 @@
+"""Google Vertex AI embeddings provider."""
+
+from chromadb.utils.embedding_functions.google_embedding_function import (
+    GoogleVertexEmbeddingFunction,
+)
+from pydantic import Field
+
+from crewai.rag.core.base_embeddings_provider import BaseEmbeddingsProvider
+
+
+class VertexAIProvider(BaseEmbeddingsProvider[GoogleVertexEmbeddingFunction]):
+    """Google Vertex AI embeddings provider."""
+
+    embedding_callable: type[GoogleVertexEmbeddingFunction] = Field(
+        default=GoogleVertexEmbeddingFunction,
+        description="Vertex AI embedding function class",
+    )
+    model_name: str = Field(
+        default="textembedding-gecko",
+        description="Model name to use for embeddings",
+        validation_alias="GOOGLE_VERTEX_MODEL_NAME",
+    )
+    api_key: str = Field(
+        description="Google API key", validation_alias="GOOGLE_CLOUD_API_KEY"
+    )
+    project_id: str = Field(
+        default="cloud-large-language-models",
+        description="GCP project ID",
+        validation_alias="GOOGLE_CLOUD_PROJECT",
+    )
+    region: str = Field(
+        default="us-central1",
+        description="GCP region",
+        validation_alias="GOOGLE_CLOUD_REGION",
+    )

src/crewai/rag/embeddings/providers/huggingface/__init__.py

@@ -0,0 +1,15 @@
+"""HuggingFace embedding providers."""
+
+from crewai.rag.embeddings.providers.huggingface.huggingface_provider import (
+    HuggingFaceProvider,
+)
+from crewai.rag.embeddings.providers.huggingface.types import (
+    HuggingFaceProviderConfig,
+    HuggingFaceProviderSpec,
+)
+
+__all__ = [
+    "HuggingFaceProvider",
+    "HuggingFaceProviderConfig",
+    "HuggingFaceProviderSpec",
+]

src/crewai/rag/embeddings/providers/huggingface/huggingface_provider.py

@@ -0,0 +1,20 @@
+"""HuggingFace embeddings provider."""
+
+from chromadb.utils.embedding_functions.huggingface_embedding_function import (
+    HuggingFaceEmbeddingServer,
+)
+from pydantic import Field
+
+from crewai.rag.core.base_embeddings_provider import BaseEmbeddingsProvider
+
+
+class HuggingFaceProvider(BaseEmbeddingsProvider[HuggingFaceEmbeddingServer]):
+    """HuggingFace embeddings provider."""
+
+    embedding_callable: type[HuggingFaceEmbeddingServer] = Field(
+        default=HuggingFaceEmbeddingServer,
+        description="HuggingFace embedding function class",
+    )
+    url: str = Field(
+        description="HuggingFace API URL", validation_alias="HUGGINGFACE_URL"
+    )

src/crewai/rag/embeddings/providers/huggingface/types.py

@@ -0,0 +1,16 @@
+"""Type definitions for HuggingFace embedding providers."""
+
+from typing import Literal, TypedDict
+
+
+class HuggingFaceProviderConfig(TypedDict, total=False):
+    """Configuration for HuggingFace provider."""
+
+    url: str
+
+
+class HuggingFaceProviderSpec(TypedDict):
+    """HuggingFace provider specification."""
+
+    provider: Literal["huggingface"]
+    config: HuggingFaceProviderConfig

src/crewai/rag/embeddings/providers/ibm/__init__.py

@@ -0,0 +1,15 @@
+"""IBM embedding providers."""
+
+from crewai.rag.embeddings.providers.ibm.types import (
+    WatsonProviderConfig,
+    WatsonProviderSpec,
+)
+from crewai.rag.embeddings.providers.ibm.watson import (
+    WatsonProvider,
+)
+
+__all__ = [
+    "WatsonProvider",
+    "WatsonProviderConfig",
+    "WatsonProviderSpec",
+]

src/crewai/rag/embeddings/providers/ibm/embedding_callable.py

@@ -0,0 +1,144 @@
+"""IBM Watson embedding function implementation."""
+
+from typing import cast
+
+import ibm_watsonx_ai.foundation_models as watson_models  # type: ignore[import-not-found, import-untyped]
+from ibm_watsonx_ai import Credentials  # type: ignore[import-not-found, import-untyped]
+from ibm_watsonx_ai.metanames import (  # type: ignore[import-not-found, import-untyped]
+    EmbedTextParamsMetaNames as EmbedParams,
+)
+from typing_extensions import Unpack
+
+from crewai.rag.core.base_embeddings_callable import EmbeddingFunction
+from crewai.rag.core.types import Documents, Embeddings
+from crewai.rag.embeddings.providers.ibm.types import WatsonProviderConfig
+
+
+class WatsonEmbeddingFunction(EmbeddingFunction[Documents]):
+    """Embedding function for IBM Watson models."""
+
+    def __init__(self, **kwargs: Unpack[WatsonProviderConfig]) -> None:
+        """Initialize Watson embedding function.
+
+        Args:
+            **kwargs: Configuration parameters for Watson Embeddings and Credentials.
+        """
+        self._config = kwargs
+
+    def __call__(self, input: Documents) -> Embeddings:
+        """Generate embeddings for input documents.
+
+        Args:
+            input: List of documents to embed.
+
+        Returns:
+            List of embedding vectors.
+        """
+        if isinstance(input, str):
+            input = [input]
+
+        embeddings_config: dict = {
+            "model_id": self._config["model_id"],
+        }
+        if "params" in self._config and self._config["params"] is not None:
+            embeddings_config["params"] = self._config["params"]
+        if "project_id" in self._config and self._config["project_id"] is not None:
+            embeddings_config["project_id"] = self._config["project_id"]
+        if "space_id" in self._config and self._config["space_id"] is not None:
+            embeddings_config["space_id"] = self._config["space_id"]
+        if "api_client" in self._config and self._config["api_client"] is not None:
+            embeddings_config["api_client"] = self._config["api_client"]
+        if "verify" in self._config and self._config["verify"] is not None:
+            embeddings_config["verify"] = self._config["verify"]
+        if "persistent_connection" in self._config:
+            embeddings_config["persistent_connection"] = self._config[
+                "persistent_connection"
+            ]
+        if "batch_size" in self._config:
+            embeddings_config["batch_size"] = self._config["batch_size"]
+        if "concurrency_limit" in self._config:
+            embeddings_config["concurrency_limit"] = self._config["concurrency_limit"]
+        if "max_retries" in self._config and self._config["max_retries"] is not None:
+            embeddings_config["max_retries"] = self._config["max_retries"]
+        if "delay_time" in self._config and self._config["delay_time"] is not None:
+            embeddings_config["delay_time"] = self._config["delay_time"]
+        if (
+            "retry_status_codes" in self._config
+            and self._config["retry_status_codes"] is not None
+        ):
+            embeddings_config["retry_status_codes"] = self._config["retry_status_codes"]
+
+        if "credentials" in self._config and self._config["credentials"] is not None:
+            embeddings_config["credentials"] = self._config["credentials"]
+        else:
+            cred_config: dict = {}
+            if "url" in self._config and self._config["url"] is not None:
+                cred_config["url"] = self._config["url"]
+            if "api_key" in self._config and self._config["api_key"] is not None:
+                cred_config["api_key"] = self._config["api_key"]
+            if "name" in self._config and self._config["name"] is not None:
+                cred_config["name"] = self._config["name"]
+            if (
+                "iam_serviceid_crn" in self._config
+                and self._config["iam_serviceid_crn"] is not None
+            ):
+                cred_config["iam_serviceid_crn"] = self._config["iam_serviceid_crn"]
+            if (
+                "trusted_profile_id" in self._config
+                and self._config["trusted_profile_id"] is not None
+            ):
+                cred_config["trusted_profile_id"] = self._config["trusted_profile_id"]
+            if "token" in self._config and self._config["token"] is not None:
+                cred_config["token"] = self._config["token"]
+            if (
+                "projects_token" in self._config
+                and self._config["projects_token"] is not None
+            ):
+                cred_config["projects_token"] = self._config["projects_token"]
+            if "username" in self._config and self._config["username"] is not None:
+                cred_config["username"] = self._config["username"]
+            if "password" in self._config and self._config["password"] is not None:
+                cred_config["password"] = self._config["password"]
+            if (
+                "instance_id" in self._config
+                and self._config["instance_id"] is not None
+            ):
+                cred_config["instance_id"] = self._config["instance_id"]
+            if "version" in self._config and self._config["version"] is not None:
+                cred_config["version"] = self._config["version"]
+            if (
+                "bedrock_url" in self._config
+                and self._config["bedrock_url"] is not None
+            ):
+                cred_config["bedrock_url"] = self._config["bedrock_url"]
+            if (
+                "platform_url" in self._config
+                and self._config["platform_url"] is not None
+            ):
+                cred_config["platform_url"] = self._config["platform_url"]
+            if "proxies" in self._config and self._config["proxies"] is not None:
+                cred_config["proxies"] = self._config["proxies"]
+            if (
+                "verify" not in embeddings_config
+                and "verify" in self._config
+                and self._config["verify"] is not None
+            ):
+                cred_config["verify"] = self._config["verify"]
+
+            if cred_config:
+                embeddings_config["credentials"] = Credentials(**cred_config)
+
+        if "params" not in embeddings_config:
+            embeddings_config["params"] = {
+                EmbedParams.TRUNCATE_INPUT_TOKENS: 3,
+                EmbedParams.RETURN_OPTIONS: {"input_text": True},
+            }
+
+        embedding = watson_models.Embeddings(**embeddings_config)
+
+        try:
+            embeddings = embedding.embed_documents(input)
+            return cast(Embeddings, embeddings)
+        except Exception as e:
+            print(f"Error during Watson embedding: {e}")
+            raise

src/crewai/rag/embeddings/providers/ibm/types.py

@@ -0,0 +1,42 @@
+"""Type definitions for IBM Watson embedding providers."""
+
+from typing import Annotated, Any, Literal, TypedDict
+
+
+class WatsonProviderConfig(TypedDict, total=False):
+    """Configuration for Watson provider."""
+
+    model_id: str
+    url: str
+    params: dict[str, str | dict[str, str]]
+    credentials: Any
+    project_id: str
+    space_id: str
+    api_client: Any
+    verify: bool | str
+    persistent_connection: Annotated[bool, True]
+    batch_size: Annotated[int, 100]
+    concurrency_limit: Annotated[int, 10]
+    max_retries: int
+    delay_time: float
+    retry_status_codes: list[int]
+    api_key: str
+    name: str
+    iam_serviceid_crn: str
+    trusted_profile_id: str
+    token: str
+    projects_token: str
+    username: str
+    password: str
+    instance_id: str
+    version: str
+    bedrock_url: str
+    platform_url: str
+    proxies: dict
+
+
+class WatsonProviderSpec(TypedDict):
+    """Watson provider specification."""
+
+    provider: Literal["watson"]
+    config: WatsonProviderConfig

src/crewai/rag/embeddings/providers/ibm/watson.py

@@ -0,0 +1,126 @@
+"""IBM Watson embeddings provider."""
+
+from ibm_watsonx_ai import (  # type: ignore[import-not-found,import-untyped]
+    APIClient,
+    Credentials,
+)
+from pydantic import Field, model_validator
+from typing_extensions import Self
+
+from crewai.rag.core.base_embeddings_provider import BaseEmbeddingsProvider
+from crewai.rag.embeddings.providers.ibm.embedding_callable import (
+    WatsonEmbeddingFunction,
+)
+
+
+class WatsonProvider(BaseEmbeddingsProvider[WatsonEmbeddingFunction]):
+    """IBM Watson embeddings provider.
+
+    Note: Requires custom implementation as Watson uses a different interface.
+    """
+
+    embedding_callable: type[WatsonEmbeddingFunction] = Field(
+        default=WatsonEmbeddingFunction, description="Watson embedding function class"
+    )
+    model_id: str = Field(
+        description="Watson model ID", validation_alias="WATSON_MODEL_ID"
+    )
+    params: dict[str, str | dict[str, str]] | None = Field(
+        default=None, description="Additional parameters"
+    )
+    credentials: Credentials | None = Field(
+        default=None, description="Watson credentials"
+    )
+    project_id: str | None = Field(
+        default=None,
+        description="Watson project ID",
+        validation_alias="WATSON_PROJECT_ID",
+    )
+    space_id: str | None = Field(
+        default=None, description="Watson space ID", validation_alias="WATSON_SPACE_ID"
+    )
+    api_client: APIClient | None = Field(default=None, description="Watson API client")
+    verify: bool | str | None = Field(
+        default=None, description="SSL verification", validation_alias="WATSON_VERIFY"
+    )
+    persistent_connection: bool = Field(
+        default=True,
+        description="Use persistent connection",
+        validation_alias="WATSON_PERSISTENT_CONNECTION",
+    )
+    batch_size: int = Field(
+        default=100,
+        description="Batch size for processing",
+        validation_alias="WATSON_BATCH_SIZE",
+    )
+    concurrency_limit: int = Field(
+        default=10,
+        description="Concurrency limit",
+        validation_alias="WATSON_CONCURRENCY_LIMIT",
+    )
+    max_retries: int | None = Field(
+        default=None,
+        description="Maximum retries",
+        validation_alias="WATSON_MAX_RETRIES",
+    )
+    delay_time: float | None = Field(
+        default=None,
+        description="Delay time between retries",
+        validation_alias="WATSON_DELAY_TIME",
+    )
+    retry_status_codes: list[int] | None = Field(
+        default=None, description="HTTP status codes to retry on"
+    )
+    url: str = Field(description="Watson API URL", validation_alias="WATSON_URL")
+    api_key: str = Field(
+        description="Watson API key", validation_alias="WATSON_API_KEY"
+    )
+    name: str | None = Field(
+        default=None, description="Service name", validation_alias="WATSON_NAME"
+    )
+    iam_serviceid_crn: str | None = Field(
+        default=None,
+        description="IAM service ID CRN",
+        validation_alias="WATSON_IAM_SERVICEID_CRN",
+    )
+    trusted_profile_id: str | None = Field(
+        default=None,
+        description="Trusted profile ID",
+        validation_alias="WATSON_TRUSTED_PROFILE_ID",
+    )
+    token: str | None = Field(
+        default=None, description="Bearer token", validation_alias="WATSON_TOKEN"
+    )
+    projects_token: str | None = Field(
+        default=None,
+        description="Projects token",
+        validation_alias="WATSON_PROJECTS_TOKEN",
+    )
+    username: str | None = Field(
+        default=None, description="Username", validation_alias="WATSON_USERNAME"
+    )
+    password: str | None = Field(
+        default=None, description="Password", validation_alias="WATSON_PASSWORD"
+    )
+    instance_id: str | None = Field(
+        default=None,
+        description="Service instance ID",
+        validation_alias="WATSON_INSTANCE_ID",
+    )
+    version: str | None = Field(
+        default=None, description="API version", validation_alias="WATSON_VERSION"
+    )
+    bedrock_url: str | None = Field(
+        default=None, description="Bedrock URL", validation_alias="WATSON_BEDROCK_URL"
+    )
+    platform_url: str | None = Field(
+        default=None, description="Platform URL", validation_alias="WATSON_PLATFORM_URL"
+    )
+    proxies: dict | None = Field(default=None, description="Proxy configuration")
+
+    @model_validator(mode="after")
+    def validate_space_or_project(self) -> Self:
+        """Validate that either space_id or project_id is provided."""
+        if not self.space_id and not self.project_id:
+            raise ValueError("One of 'space_id' or 'project_id' must be provided")
+        return self

src/crewai/rag/embeddings/providers/instructor/__init__.py

@@ -0,0 +1,15 @@
+"""Instructor embedding providers."""
+
+from crewai.rag.embeddings.providers.instructor.instructor_provider import (
+    InstructorProvider,
+)
+from crewai.rag.embeddings.providers.instructor.types import (
+    InstructorProviderConfig,
+    InstructorProviderSpec,
+)
+
+__all__ = [
+    "InstructorProvider",
+    "InstructorProviderConfig",
+    "InstructorProviderSpec",
+]

src/crewai/rag/embeddings/providers/instructor/instructor_provider.py

@@ -0,0 +1,32 @@
+"""Instructor embeddings provider."""
+
+from chromadb.utils.embedding_functions.instructor_embedding_function import (
+    InstructorEmbeddingFunction,
+)
+from pydantic import Field
+
+from crewai.rag.core.base_embeddings_provider import BaseEmbeddingsProvider
+
+
+class InstructorProvider(BaseEmbeddingsProvider[InstructorEmbeddingFunction]):
+    """Instructor embeddings provider."""
+
+    embedding_callable: type[InstructorEmbeddingFunction] = Field(
+        default=InstructorEmbeddingFunction,
+        description="Instructor embedding function class",
+    )
+    model_name: str = Field(
+        default="hkunlp/instructor-base",
+        description="Model name to use",
+        validation_alias="INSTRUCTOR_MODEL_NAME",
+    )
+    device: str = Field(
+        default="cpu",
+        description="Device to run model on (cpu or cuda)",
+        validation_alias="INSTRUCTOR_DEVICE",
+    )
+    instruction: str | None = Field(
+        default=None,
+        description="Instruction for embeddings",
+        validation_alias="INSTRUCTOR_INSTRUCTION",
+    )

src/crewai/rag/embeddings/providers/instructor/types.py

@@ -0,0 +1,18 @@
+"""Type definitions for Instructor embedding providers."""
+
+from typing import Annotated, Literal, TypedDict
+
+
+class InstructorProviderConfig(TypedDict, total=False):
+    """Configuration for Instructor provider."""
+
+    model_name: Annotated[str, "hkunlp/instructor-base"]
+    device: Annotated[str, "cpu"]
+    instruction: str
+
+
+class InstructorProviderSpec(TypedDict):
+    """Instructor provider specification."""
+
+    provider: Literal["instructor"]
+    config: InstructorProviderConfig

src/crewai/rag/embeddings/providers/jina/__init__.py

@@ -0,0 +1,13 @@
+"""Jina embedding providers."""
+
+from crewai.rag.embeddings.providers.jina.jina_provider import JinaProvider
+from crewai.rag.embeddings.providers.jina.types import (
+    JinaProviderConfig,
+    JinaProviderSpec,
+)
+
+__all__ = [
+    "JinaProvider",
+    "JinaProviderConfig",
+    "JinaProviderSpec",
+]

src/crewai/rag/embeddings/providers/jina/jina_provider.py

@@ -0,0 +1,22 @@
+"""Jina embeddings provider."""
+
+from chromadb.utils.embedding_functions.jina_embedding_function import (
+    JinaEmbeddingFunction,
+)
+from pydantic import Field
+
+from crewai.rag.core.base_embeddings_provider import BaseEmbeddingsProvider
+
+
+class JinaProvider(BaseEmbeddingsProvider[JinaEmbeddingFunction]):
+    """Jina embeddings provider."""
+
+    embedding_callable: type[JinaEmbeddingFunction] = Field(
+        default=JinaEmbeddingFunction, description="Jina embedding function class"
+    )
+    api_key: str = Field(description="Jina API key", validation_alias="JINA_API_KEY")
+    model_name: str = Field(
+        default="jina-embeddings-v2-base-en",
+        description="Model name to use for embeddings",
+        validation_alias="JINA_MODEL_NAME",
+    )

src/crewai/rag/embeddings/providers/jina/types.py

@@ -0,0 +1,17 @@
+"""Type definitions for Jina embedding providers."""
+
+from typing import Annotated, Literal, TypedDict
+
+
+class JinaProviderConfig(TypedDict, total=False):
+    """Configuration for Jina provider."""
+
+    api_key: str
+    model_name: Annotated[str, "jina-embeddings-v2-base-en"]
+
+
+class JinaProviderSpec(TypedDict):
+    """Jina provider specification."""
+
+    provider: Literal["jina"]
+    config: JinaProviderConfig

src/crewai/rag/embeddings/providers/microsoft/__init__.py

@@ -0,0 +1,15 @@
+"""Microsoft embedding providers."""
+
+from crewai.rag.embeddings.providers.microsoft.azure import (
+    AzureProvider,
+)
+from crewai.rag.embeddings.providers.microsoft.types import (
+    AzureProviderConfig,
+    AzureProviderSpec,
+)
+
+__all__ = [
+    "AzureProvider",
+    "AzureProviderConfig",
+    "AzureProviderSpec",
+]

src/crewai/rag/embeddings/providers/microsoft/azure.py

@@ -0,0 +1,58 @@
+"""Azure OpenAI embeddings provider."""
+
+from typing import Any
+
+from chromadb.utils.embedding_functions.openai_embedding_function import (
+    OpenAIEmbeddingFunction,
+)
+from pydantic import Field
+
+from crewai.rag.core.base_embeddings_provider import BaseEmbeddingsProvider
+
+
+class AzureProvider(BaseEmbeddingsProvider[OpenAIEmbeddingFunction]):
+    """Azure OpenAI embeddings provider."""
+
+    embedding_callable: type[OpenAIEmbeddingFunction] = Field(
+        default=OpenAIEmbeddingFunction,
+        description="Azure OpenAI embedding function class",
+    )
+    api_key: str = Field(description="Azure API key", validation_alias="OPENAI_API_KEY")
+    api_base: str | None = Field(
+        default=None,
+        description="Azure endpoint URL",
+        validation_alias="OPENAI_API_BASE",
+    )
+    api_type: str = Field(
+        default="azure",
+        description="API type for Azure",
+        validation_alias="OPENAI_API_TYPE",
+    )
+    api_version: str | None = Field(
+        default=None,
+        description="Azure API version",
+        validation_alias="OPENAI_API_VERSION",
+    )
+    model_name: str = Field(
+        default="text-embedding-ada-002",
+        description="Model name to use for embeddings",
+        validation_alias="OPENAI_MODEL_NAME",
+    )
+    default_headers: dict[str, Any] | None = Field(
+        default=None, description="Default headers for API requests"
+    )
+    dimensions: int | None = Field(
+        default=None,
+        description="Embedding dimensions",
+        validation_alias="OPENAI_DIMENSIONS",
+    )
+    deployment_id: str | None = Field(
+        default=None,
+        description="Azure deployment ID",
+        validation_alias="OPENAI_DEPLOYMENT_ID",
+    )
+    organization_id: str | None = Field(
+        default=None,
+        description="Organization ID",
+        validation_alias="OPENAI_ORGANIZATION_ID",
+    )

src/crewai/rag/embeddings/providers/microsoft/types.py

@@ -0,0 +1,24 @@
+"""Type definitions for Microsoft Azure embedding providers."""
+
+from typing import Annotated, Any, Literal, TypedDict
+
+
+class AzureProviderConfig(TypedDict, total=False):
+    """Configuration for Azure provider."""
+
+    api_key: str
+    api_base: str
+    api_type: Annotated[str, "azure"]
+    api_version: str
+    model_name: Annotated[str, "text-embedding-ada-002"]
+    default_headers: dict[str, Any]
+    dimensions: int
+    deployment_id: str
+    organization_id: str
+
+
+class AzureProviderSpec(TypedDict):
+    """Azure provider specification."""
+
+    provider: Literal["azure"]
+    config: AzureProviderConfig

src/crewai/rag/embeddings/providers/ollama/__init__.py

@@ -0,0 +1,15 @@
+"""Ollama embedding providers."""
+
+from crewai.rag.embeddings.providers.ollama.ollama_provider import (
+    OllamaProvider,
+)
+from crewai.rag.embeddings.providers.ollama.types import (
+    OllamaProviderConfig,
+    OllamaProviderSpec,
+)
+
+__all__ = [
+    "OllamaProvider",
+    "OllamaProviderConfig",
+    "OllamaProviderSpec",
+]

src/crewai/rag/embeddings/providers/ollama/ollama_provider.py

@@ -0,0 +1,25 @@
+"""Ollama embeddings provider."""
+
+from chromadb.utils.embedding_functions.ollama_embedding_function import (
+    OllamaEmbeddingFunction,
+)
+from pydantic import Field
+
+from crewai.rag.core.base_embeddings_provider import BaseEmbeddingsProvider
+
+
+class OllamaProvider(BaseEmbeddingsProvider[OllamaEmbeddingFunction]):
+    """Ollama embeddings provider."""
+
+    embedding_callable: type[OllamaEmbeddingFunction] = Field(
+        default=OllamaEmbeddingFunction, description="Ollama embedding function class"
+    )
+    url: str = Field(
+        default="http://localhost:11434/api/embeddings",
+        description="Ollama API endpoint URL",
+        validation_alias="OLLAMA_URL",
+    )
+    model_name: str = Field(
+        description="Model name to use for embeddings",
+        validation_alias="OLLAMA_MODEL_NAME",
+    )

src/crewai/rag/embeddings/providers/ollama/types.py

@@ -0,0 +1,17 @@
+"""Type definitions for Ollama embedding providers."""
+
+from typing import Annotated, Literal, TypedDict
+
+
+class OllamaProviderConfig(TypedDict, total=False):
+    """Configuration for Ollama provider."""
+
+    url: Annotated[str, "http://localhost:11434/api/embeddings"]
+    model_name: str
+
+
+class OllamaProviderSpec(TypedDict):
+    """Ollama provider specification."""
+
+    provider: Literal["ollama"]
+    config: OllamaProviderConfig

src/crewai/rag/embeddings/providers/onnx/__init__.py

@@ -0,0 +1,13 @@
+"""ONNX embedding providers."""
+
+from crewai.rag.embeddings.providers.onnx.onnx_provider import ONNXProvider
+from crewai.rag.embeddings.providers.onnx.types import (
+    ONNXProviderConfig,
+    ONNXProviderSpec,
+)
+
+__all__ = [
+    "ONNXProvider",
+    "ONNXProviderConfig",
+    "ONNXProviderSpec",
+]

src/crewai/rag/embeddings/providers/onnx/onnx_provider.py

@@ -0,0 +1,19 @@
+"""ONNX embeddings provider."""
+
+from chromadb.utils.embedding_functions.onnx_mini_lm_l6_v2 import ONNXMiniLM_L6_V2
+from pydantic import Field
+
+from crewai.rag.core.base_embeddings_provider import BaseEmbeddingsProvider
+
+
+class ONNXProvider(BaseEmbeddingsProvider[ONNXMiniLM_L6_V2]):
+    """ONNX embeddings provider."""
+
+    embedding_callable: type[ONNXMiniLM_L6_V2] = Field(
+        default=ONNXMiniLM_L6_V2, description="ONNX MiniLM embedding function class"
+    )
+    preferred_providers: list[str] | None = Field(
+        default=None,
+        description="Preferred ONNX execution providers",
+        validation_alias="ONNX_PREFERRED_PROVIDERS",
+    )

src/crewai/rag/embeddings/providers/onnx/types.py

@@ -0,0 +1,16 @@
+"""Type definitions for ONNX embedding providers."""
+
+from typing import Literal, TypedDict
+
+
+class ONNXProviderConfig(TypedDict, total=False):
+    """Configuration for ONNX provider."""
+
+    preferred_providers: list[str]
+
+
+class ONNXProviderSpec(TypedDict):
+    """ONNX provider specification."""
+
+    provider: Literal["onnx"]
+    config: ONNXProviderConfig

src/crewai/rag/embeddings/providers/openai/__init__.py

@@ -0,0 +1,15 @@
+"""OpenAI embedding providers."""
+
+from crewai.rag.embeddings.providers.openai.openai_provider import (
+    OpenAIProvider,
+)
+from crewai.rag.embeddings.providers.openai.types import (
+    OpenAIProviderConfig,
+    OpenAIProviderSpec,
+)
+
+__all__ = [
+    "OpenAIProvider",
+    "OpenAIProviderConfig",
+    "OpenAIProviderSpec",
+]

src/crewai/rag/embeddings/providers/openai/openai_provider.py

@@ -0,0 +1,58 @@
+"""OpenAI embeddings provider."""
+
+from typing import Any
+
+from chromadb.utils.embedding_functions.openai_embedding_function import (
+    OpenAIEmbeddingFunction,
+)
+from pydantic import Field
+
+from crewai.rag.core.base_embeddings_provider import BaseEmbeddingsProvider
+
+
+class OpenAIProvider(BaseEmbeddingsProvider[OpenAIEmbeddingFunction]):
+    """OpenAI embeddings provider."""
+
+    embedding_callable: type[OpenAIEmbeddingFunction] = Field(
+        default=OpenAIEmbeddingFunction,
+        description="OpenAI embedding function class",
+    )
+    api_key: str = Field(
+        description="OpenAI API key", validation_alias="OPENAI_API_KEY"
+    )
+    model_name: str = Field(
+        default="text-embedding-ada-002",
+        description="Model name to use for embeddings",
+        validation_alias="OPENAI_MODEL_NAME",
+    )
+    api_base: str | None = Field(
+        default=None,
+        description="Base URL for API requests",
+        validation_alias="OPENAI_API_BASE",
+    )
+    api_type: str | None = Field(
+        default=None,
+        description="API type (e.g., 'azure')",
+        validation_alias="OPENAI_API_TYPE",
+    )
+    api_version: str | None = Field(
+        default=None, description="API version", validation_alias="OPENAI_API_VERSION"
+    )
+    default_headers: dict[str, Any] | None = Field(
+        default=None, description="Default headers for API requests"
+    )
+    dimensions: int | None = Field(
+        default=None,
+        description="Embedding dimensions",
+        validation_alias="OPENAI_DIMENSIONS",
+    )
+    deployment_id: str | None = Field(
+        default=None,
+        description="Azure deployment ID",
+        validation_alias="OPENAI_DEPLOYMENT_ID",
+    )
+    organization_id: str | None = Field(
+        default=None,
+        description="OpenAI organization ID",
+        validation_alias="OPENAI_ORGANIZATION_ID",
+    )

src/crewai/rag/embeddings/providers/openai/types.py

@@ -0,0 +1,24 @@
+"""Type definitions for OpenAI embedding providers."""
+
+from typing import Annotated, Any, Literal, TypedDict
+
+
+class OpenAIProviderConfig(TypedDict, total=False):
+    """Configuration for OpenAI provider."""
+
+    api_key: str
+    model_name: Annotated[str, "text-embedding-ada-002"]
+    api_base: str
+    api_type: str
+    api_version: str
+    default_headers: dict[str, Any]
+    dimensions: int
+    deployment_id: str
+    organization_id: str
+
+
+class OpenAIProviderSpec(TypedDict):
+    """OpenAI provider specification."""
+
+    provider: Literal["openai"]
+    config: OpenAIProviderConfig

src/crewai/rag/embeddings/providers/openclip/__init__.py

@@ -0,0 +1,15 @@
+"""OpenCLIP embedding providers."""
+
+from crewai.rag.embeddings.providers.openclip.openclip_provider import (
+    OpenCLIPProvider,
+)
+from crewai.rag.embeddings.providers.openclip.types import (
+    OpenCLIPProviderConfig,
+    OpenCLIPProviderSpec,
+)
+
+__all__ = [
+    "OpenCLIPProvider",
+    "OpenCLIPProviderConfig",
+    "OpenCLIPProviderSpec",
+]

src/crewai/rag/embeddings/providers/openclip/openclip_provider.py

@@ -0,0 +1,32 @@
+"""OpenCLIP embeddings provider."""
+
+from chromadb.utils.embedding_functions.open_clip_embedding_function import (
+    OpenCLIPEmbeddingFunction,
+)
+from pydantic import Field
+
+from crewai.rag.core.base_embeddings_provider import BaseEmbeddingsProvider
+
+
+class OpenCLIPProvider(BaseEmbeddingsProvider[OpenCLIPEmbeddingFunction]):
+    """OpenCLIP embeddings provider."""
+
+    embedding_callable: type[OpenCLIPEmbeddingFunction] = Field(
+        default=OpenCLIPEmbeddingFunction,
+        description="OpenCLIP embedding function class",
+    )
+    model_name: str = Field(
+        default="ViT-B-32",
+        description="Model name to use",
+        validation_alias="OPENCLIP_MODEL_NAME",
+    )
+    checkpoint: str = Field(
+        default="laion2b_s34b_b79k",
+        description="Model checkpoint",
+        validation_alias="OPENCLIP_CHECKPOINT",
+    )
+    device: str | None = Field(
+        default="cpu",
+        description="Device to run model on",
+        validation_alias="OPENCLIP_DEVICE",
+    )

src/crewai/rag/embeddings/providers/openclip/types.py

@@ -0,0 +1,18 @@
+"""Type definitions for OpenCLIP embedding providers."""
+
+from typing import Annotated, Literal, TypedDict
+
+
+class OpenCLIPProviderConfig(TypedDict, total=False):
+    """Configuration for OpenCLIP provider."""
+
+    model_name: Annotated[str, "ViT-B-32"]
+    checkpoint: Annotated[str, "laion2b_s34b_b79k"]
+    device: Annotated[str, "cpu"]
+
+
+class OpenCLIPProviderSpec(TypedDict):
+    """OpenCLIP provider specification."""
+
+    provider: Literal["openclip"]
+    config: OpenCLIPProviderConfig

src/crewai/rag/embeddings/providers/roboflow/__init__.py

@@ -0,0 +1,15 @@
+"""Roboflow embedding providers."""
+
+from crewai.rag.embeddings.providers.roboflow.roboflow_provider import (
+    RoboflowProvider,
+)
+from crewai.rag.embeddings.providers.roboflow.types import (
+    RoboflowProviderConfig,
+    RoboflowProviderSpec,
+)
+
+__all__ = [
+    "RoboflowProvider",
+    "RoboflowProviderConfig",
+    "RoboflowProviderSpec",
+]

src/crewai/rag/embeddings/providers/roboflow/roboflow_provider.py

@@ -0,0 +1,25 @@
+"""Roboflow embeddings provider."""
+
+from chromadb.utils.embedding_functions.roboflow_embedding_function import (
+    RoboflowEmbeddingFunction,
+)
+from pydantic import Field
+
+from crewai.rag.core.base_embeddings_provider import BaseEmbeddingsProvider
+
+
+class RoboflowProvider(BaseEmbeddingsProvider[RoboflowEmbeddingFunction]):
+    """Roboflow embeddings provider."""
+
+    embedding_callable: type[RoboflowEmbeddingFunction] = Field(
+        default=RoboflowEmbeddingFunction,
+        description="Roboflow embedding function class",
+    )
+    api_key: str = Field(
+        default="", description="Roboflow API key", validation_alias="ROBOFLOW_API_KEY"
+    )
+    api_url: str = Field(
+        default="https://infer.roboflow.com",
+        description="Roboflow API URL",
+        validation_alias="ROBOFLOW_API_URL",
+    )

src/crewai/rag/embeddings/providers/roboflow/types.py

@@ -0,0 +1,17 @@
+"""Type definitions for Roboflow embedding providers."""
+
+from typing import Annotated, Literal, TypedDict
+
+
+class RoboflowProviderConfig(TypedDict, total=False):
+    """Configuration for Roboflow provider."""
+
+    api_key: Annotated[str, ""]
+    api_url: Annotated[str, "https://infer.roboflow.com"]
+
+
+class RoboflowProviderSpec(TypedDict):
+    """Roboflow provider specification."""
+
+    provider: Literal["roboflow"]
+    config: RoboflowProviderConfig

src/crewai/rag/embeddings/providers/sentence_transformer/__init__.py

@@ -0,0 +1,15 @@
+"""SentenceTransformer embedding providers."""
+
+from crewai.rag.embeddings.providers.sentence_transformer.sentence_transformer_provider import (
+    SentenceTransformerProvider,
+)
+from crewai.rag.embeddings.providers.sentence_transformer.types import (
+    SentenceTransformerProviderConfig,
+    SentenceTransformerProviderSpec,
+)
+
+__all__ = [
+    "SentenceTransformerProvider",
+    "SentenceTransformerProviderConfig",
+    "SentenceTransformerProviderSpec",
+]

src/crewai/rag/embeddings/providers/sentence_transformer/sentence_transformer_provider.py

@@ -0,0 +1,34 @@
+"""SentenceTransformer embeddings provider."""
+
+from chromadb.utils.embedding_functions.sentence_transformer_embedding_function import (
+    SentenceTransformerEmbeddingFunction,
+)
+from pydantic import Field
+
+from crewai.rag.core.base_embeddings_provider import BaseEmbeddingsProvider
+
+
+class SentenceTransformerProvider(
+    BaseEmbeddingsProvider[SentenceTransformerEmbeddingFunction]
+):
+    """SentenceTransformer embeddings provider."""
+
+    embedding_callable: type[SentenceTransformerEmbeddingFunction] = Field(
+        default=SentenceTransformerEmbeddingFunction,
+        description="SentenceTransformer embedding function class",
+    )
+    model_name: str = Field(
+        default="all-MiniLM-L6-v2",
+        description="Model name to use",
+        validation_alias="SENTENCE_TRANSFORMER_MODEL_NAME",
+    )
+    device: str = Field(
+        default="cpu",
+        description="Device to run model on (cpu or cuda)",
+        validation_alias="SENTENCE_TRANSFORMER_DEVICE",
+    )
+    normalize_embeddings: bool = Field(
+        default=False,
+        description="Whether to normalize embeddings",
+        validation_alias="SENTENCE_TRANSFORMER_NORMALIZE_EMBEDDINGS",
+    )

src/crewai/rag/embeddings/providers/sentence_transformer/types.py

@@ -0,0 +1,18 @@
+"""Type definitions for SentenceTransformer embedding providers."""
+
+from typing import Annotated, Literal, TypedDict
+
+
+class SentenceTransformerProviderConfig(TypedDict, total=False):
+    """Configuration for SentenceTransformer provider."""
+
+    model_name: Annotated[str, "all-MiniLM-L6-v2"]
+    device: Annotated[str, "cpu"]
+    normalize_embeddings: Annotated[bool, False]
+
+
+class SentenceTransformerProviderSpec(TypedDict):
+    """SentenceTransformer provider specification."""
+
+    provider: Literal["sentence-transformer"]
+    config: SentenceTransformerProviderConfig

src/crewai/rag/embeddings/providers/text2vec/__init__.py

@@ -0,0 +1,15 @@
+"""Text2Vec embedding providers."""
+
+from crewai.rag.embeddings.providers.text2vec.text2vec_provider import (
+    Text2VecProvider,
+)
+from crewai.rag.embeddings.providers.text2vec.types import (
+    Text2VecProviderConfig,
+    Text2VecProviderSpec,
+)
+
+__all__ = [
+    "Text2VecProvider",
+    "Text2VecProviderConfig",
+    "Text2VecProviderSpec",
+]

src/crewai/rag/embeddings/providers/text2vec/text2vec_provider.py

@@ -0,0 +1,22 @@
+"""Text2Vec embeddings provider."""
+
+from chromadb.utils.embedding_functions.text2vec_embedding_function import (
+    Text2VecEmbeddingFunction,
+)
+from pydantic import Field
+
+from crewai.rag.core.base_embeddings_provider import BaseEmbeddingsProvider
+
+
+class Text2VecProvider(BaseEmbeddingsProvider[Text2VecEmbeddingFunction]):
+    """Text2Vec embeddings provider."""
+
+    embedding_callable: type[Text2VecEmbeddingFunction] = Field(
+        default=Text2VecEmbeddingFunction,
+        description="Text2Vec embedding function class",
+    )
+    model_name: str = Field(
+        default="shibing624/text2vec-base-chinese",
+        description="Model name to use",
+        validation_alias="TEXT2VEC_MODEL_NAME",
+    )

src/crewai/rag/embeddings/providers/text2vec/types.py

@@ -0,0 +1,16 @@
+"""Type definitions for Text2Vec embedding providers."""
+
+from typing import Annotated, Literal, TypedDict
+
+
+class Text2VecProviderConfig(TypedDict, total=False):
+    """Configuration for Text2Vec provider."""
+
+    model_name: Annotated[str, "shibing624/text2vec-base-chinese"]
+
+
+class Text2VecProviderSpec(TypedDict):
+    """Text2Vec provider specification."""
+
+    provider: Literal["text2vec"]
+    config: Text2VecProviderConfig

src/crewai/rag/embeddings/providers/voyageai/__init__.py

@@ -0,0 +1,15 @@
+"""VoyageAI embedding providers."""
+
+from crewai.rag.embeddings.providers.voyageai.types import (
+    VoyageAIProviderConfig,
+    VoyageAIProviderSpec,
+)
+from crewai.rag.embeddings.providers.voyageai.voyageai_provider import (
+    VoyageAIProvider,
+)
+
+__all__ = [
+    "VoyageAIProvider",
+    "VoyageAIProviderConfig",
+    "VoyageAIProviderSpec",
+]

src/crewai/rag/embeddings/providers/voyageai/embedding_callable.py

@@ -0,0 +1,50 @@
+"""VoyageAI embedding function implementation."""
+
+from typing import cast
+
+import voyageai
+from typing_extensions import Unpack
+
+from crewai.rag.core.base_embeddings_callable import EmbeddingFunction
+from crewai.rag.core.types import Documents, Embeddings
+from crewai.rag.embeddings.providers.voyageai.types import VoyageAIProviderConfig
+
+
+class VoyageAIEmbeddingFunction(EmbeddingFunction[Documents]):
+    """Embedding function for VoyageAI models."""
+
+    def __init__(self, **kwargs: Unpack[VoyageAIProviderConfig]) -> None:
+        """Initialize VoyageAI embedding function.
+
+        Args:
+            **kwargs: Configuration parameters for VoyageAI.
+        """
+        self._config = kwargs
+        self._client = voyageai.Client(
+            api_key=kwargs["api_key"],
+            max_retries=kwargs.get("max_retries", 0),
+            timeout=kwargs.get("timeout"),
+        )
+
+    def __call__(self, input: Documents) -> Embeddings:
+        """Generate embeddings for input documents.
+
+        Args:
+            input: List of documents to embed.
+
+        Returns:
+            List of embedding vectors.
+        """
+        if isinstance(input, str):
+            input = [input]
+
+        result = self._client.embed(
+            texts=input,
+            model=self._config.get("model", "voyage-2"),
+            input_type=self._config.get("input_type"),
+            truncation=self._config.get("truncation", True),
+            output_dtype=self._config.get("output_dtype"),
+            output_dimension=self._config.get("output_dimension"),
+        )
+
+        return cast(Embeddings, result.embeddings)

src/crewai/rag/embeddings/providers/voyageai/types.py

@@ -0,0 +1,23 @@
+"""Type definitions for VoyageAI embedding providers."""
+
+from typing import Annotated, Literal, TypedDict
+
+
+class VoyageAIProviderConfig(TypedDict, total=False):
+    """Configuration for VoyageAI provider."""
+
+    api_key: str
+    model: Annotated[str, "voyage-2"]
+    input_type: str
+    truncation: Annotated[bool, True]
+    output_dtype: str
+    output_dimension: int
+    max_retries: Annotated[int, 0]
+    timeout: float
+
+
+class VoyageAIProviderSpec(TypedDict):
+    """VoyageAI provider specification."""
+
+    provider: Literal["voyageai"]
+    config: VoyageAIProviderConfig

src/crewai/rag/embeddings/providers/voyageai/voyageai_provider.py

@@ -0,0 +1,55 @@
+"""Voyage AI embeddings provider."""
+
+from pydantic import Field
+
+from crewai.rag.core.base_embeddings_provider import BaseEmbeddingsProvider
+from crewai.rag.embeddings.providers.voyageai.embedding_callable import (
+    VoyageAIEmbeddingFunction,
+)
+
+
+class VoyageAIProvider(BaseEmbeddingsProvider[VoyageAIEmbeddingFunction]):
+    """Voyage AI embeddings provider."""
+
+    embedding_callable: type[VoyageAIEmbeddingFunction] = Field(
+        default=VoyageAIEmbeddingFunction,
+        description="Voyage AI embedding function class",
+    )
+    model: str = Field(
+        default="voyage-2",
+        description="Model to use for embeddings",
+        validation_alias="VOYAGEAI_MODEL",
+    )
+    api_key: str = Field(
+        description="Voyage AI API key", validation_alias="VOYAGEAI_API_KEY"
+    )
+    input_type: str | None = Field(
+        default=None,
+        description="Input type for embeddings",
+        validation_alias="VOYAGEAI_INPUT_TYPE",
+    )
+    truncation: bool = Field(
+        default=True,
+        description="Whether to truncate inputs",
+        validation_alias="VOYAGEAI_TRUNCATION",
+    )
+    output_dtype: str | None = Field(
+        default=None,
+        description="Output data type",
+        validation_alias="VOYAGEAI_OUTPUT_DTYPE",
+    )
+    output_dimension: int | None = Field(
+        default=None,
+        description="Output dimension",
+        validation_alias="VOYAGEAI_OUTPUT_DIMENSION",
+    )
+    max_retries: int = Field(
+        default=0,
+        description="Maximum retries for API calls",
+        validation_alias="VOYAGEAI_MAX_RETRIES",
+    )
+    timeout: float | None = Field(
+        default=None,
+        description="Timeout for API calls",
+        validation_alias="VOYAGEAI_TIMEOUT",
+    )

src/crewai/rag/embeddings/types.py

@@ -2,61 +2,67 @@
 
 from typing import Literal
 
-from pydantic import BaseModel, Field, SecretStr
+from crewai.rag.embeddings.providers.aws.types import BedrockProviderSpec
+from crewai.rag.embeddings.providers.cohere.types import CohereProviderSpec
+from crewai.rag.embeddings.providers.custom.types import CustomProviderSpec
+from crewai.rag.embeddings.providers.google.types import (
+    GenerativeAiProviderSpec,
+    VertexAIProviderSpec,
+)
+from crewai.rag.embeddings.providers.huggingface.types import HuggingFaceProviderSpec
+from crewai.rag.embeddings.providers.ibm.types import WatsonProviderSpec
+from crewai.rag.embeddings.providers.instructor.types import InstructorProviderSpec
+from crewai.rag.embeddings.providers.jina.types import JinaProviderSpec
+from crewai.rag.embeddings.providers.microsoft.types import AzureProviderSpec
+from crewai.rag.embeddings.providers.ollama.types import OllamaProviderSpec
+from crewai.rag.embeddings.providers.onnx.types import ONNXProviderSpec
+from crewai.rag.embeddings.providers.openai.types import OpenAIProviderSpec
+from crewai.rag.embeddings.providers.openclip.types import OpenCLIPProviderSpec
+from crewai.rag.embeddings.providers.roboflow.types import RoboflowProviderSpec
+from crewai.rag.embeddings.providers.sentence_transformer.types import (
+    SentenceTransformerProviderSpec,
+)
+from crewai.rag.embeddings.providers.text2vec.types import Text2VecProviderSpec
+from crewai.rag.embeddings.providers.voyageai.types import VoyageAIProviderSpec
 
-from crewai.rag.types import EmbeddingFunction
+ProviderSpec = (
+    AzureProviderSpec
+    | BedrockProviderSpec
+    | CohereProviderSpec
+    | CustomProviderSpec
+    | GenerativeAiProviderSpec
+    | HuggingFaceProviderSpec
+    | InstructorProviderSpec
+    | JinaProviderSpec
+    | OllamaProviderSpec
+    | ONNXProviderSpec
+    | OpenAIProviderSpec
+    | OpenCLIPProviderSpec
+    | RoboflowProviderSpec
+    | SentenceTransformerProviderSpec
+    | Text2VecProviderSpec
+    | VertexAIProviderSpec
+    | VoyageAIProviderSpec
+    | WatsonProviderSpec
+)
 
-EmbeddingProvider = Literal[
+AllowedEmbeddingProviders = Literal[
-    "openai",
+    "azure",
+    "amazon-bedrock",
     "cohere",
-    "ollama",
+    "custom",
-    "huggingface",
-    "sentence-transformer",
-    "instructor",
-    "google-palm",
     "google-generativeai",
     "google-vertex",
-    "amazon-bedrock",
+    "huggingface",
+    "instructor",
     "jina",
-    "roboflow",
+    "ollama",
-    "openclip",
-    "text2vec",
     "onnx",
+    "openai",
+    "openclip",
+    "roboflow",
+    "sentence-transformer",
+    "text2vec",
+    "voyageai",
+    "watson",
 ]
-"""Supported embedding providers.
-
-These correspond to the embedding functions available in ChromaDB's
-embedding_functions module. Each provider has specific requirements
-and configuration options.
-"""
-
-
-class EmbeddingOptions(BaseModel):
-    """Configuration options for embedding providers.
-
-    Generic attributes that can be passed to get_embedding_function
-    to configure various embedding providers.
-    """
-
-    provider: EmbeddingProvider = Field(
-        ..., description="Embedding provider name (e.g., 'openai', 'cohere', 'onnx')"
-    )
-    model_name: str | None = Field(
-        default=None, description="Model name for the embedding provider"
-    )
-    api_key: SecretStr | None = Field(
-        default=None, description="API key for the embedding provider"
-    )
-
-
-class EmbeddingConfig(BaseModel):
-    """Configuration wrapper for embedding functions.
-
-    Accepts either a pre-configured EmbeddingFunction or EmbeddingOptions
-    to create one. This provides flexibility in how embeddings are configured.
-
-    Attributes:
-        function: Either a callable EmbeddingFunction or EmbeddingOptions to create one
-    """
-
-    function: EmbeddingFunction | EmbeddingOptions

src/crewai/rag/storage/base_rag_storage.py

@@ -1,8 +1,8 @@
 from abc import ABC, abstractmethod
 from typing import Any
 
-from crewai.rag.embeddings.factory import EmbedderConfig
+from crewai.rag.core.base_embeddings_provider import BaseEmbeddingsProvider
-from crewai.rag.embeddings.types import EmbeddingOptions
+from crewai.rag.embeddings.types import ProviderSpec
 
 
 class BaseRAGStorage(ABC):
@@ -16,7 +16,7 @@ class BaseRAGStorage(ABC):
         self,
         type: str,
         allow_reset: bool = True,
-        embedder_config: EmbeddingOptions | EmbedderConfig | None = None,
+        embedder_config: ProviderSpec | BaseEmbeddingsProvider | None = None,
         crew: Any = None,
     ):
         self.type = type

src/crewai/rag/types.py

@@ -24,8 +24,7 @@ class BaseRecord(TypedDict, total=False):
     )
 
 
-DenseVector: TypeAlias = list[float]
+Embeddings: TypeAlias = list[list[float]]
-IntVector: TypeAlias = list[int]
 
 EmbeddingFunction: TypeAlias = Callable[..., Any]
 

tests/knowledge/test_knowledge_storage_integration.py

@@ -11,7 +11,7 @@ from crewai.knowledge.storage.knowledge_storage import (  # type: ignore[import-
 
 @patch("crewai.knowledge.storage.knowledge_storage.get_rag_client")
 @patch("crewai.knowledge.storage.knowledge_storage.create_client")
-@patch("crewai.knowledge.storage.knowledge_storage.get_embedding_function")
+@patch("crewai.knowledge.storage.knowledge_storage.build_embedder")
 def test_knowledge_storage_uses_rag_client(
     mock_get_embedding: MagicMock,
     mock_create_client: MagicMock,
@@ -122,7 +122,7 @@ def test_search_error_handling(mock_get_client: MagicMock) -> None:
 
 
 @patch("crewai.knowledge.storage.knowledge_storage.get_rag_client")
-@patch("crewai.knowledge.storage.knowledge_storage.get_embedding_function")
+@patch("crewai.knowledge.storage.knowledge_storage.build_embedder")
 def test_embedding_configuration_flow(
     mock_get_embedding: MagicMock, mock_get_client: MagicMock
 ) -> None:

tests/rag/embeddings/test_embedding_factory.py

@@ -1,83 +1,89 @@
-"""Enhanced tests for embedding function factory."""
+"""Tests for embedding function factory."""
 
 from unittest.mock import MagicMock, patch
 
 import pytest
-from pydantic import SecretStr
 
-from crewai.rag.embeddings.factory import (  # type: ignore[import-untyped]
+from crewai.rag.embeddings.factory import build_embedder
-    get_embedding_function,
-)
-from crewai.rag.embeddings.types import EmbeddingOptions  # type: ignore[import-untyped]
 
 
-def test_get_embedding_function_default() -> None:
+class TestEmbeddingFactory:
-    """Test default embedding function when no config provided."""
+    """Test embedding factory functions."""
-    with patch("crewai.rag.embeddings.factory.OpenAIEmbeddingFunction") as mock_openai:
-        mock_instance = MagicMock()
-        mock_openai.return_value = mock_instance
 
-        with patch(
+    @patch("crewai.rag.embeddings.factory.import_and_validate_definition")
-            "crewai.rag.embeddings.factory.os.getenv", return_value="test-api-key"
+    def test_build_embedder_openai(self, mock_import):
-        ):
+        """Test building OpenAI embedder."""
-            result = get_embedding_function()
+        mock_provider_class = MagicMock()
+        mock_provider_instance = MagicMock()
+        mock_embedding_function = MagicMock()
 
-        mock_openai.assert_called_once_with(
+        mock_import.return_value = mock_provider_class
-            api_key="test-api-key", model_name="text-embedding-3-small"
+        mock_provider_class.return_value = mock_provider_instance
-        )
+        mock_provider_instance.embedding_callable.return_value = mock_embedding_function
-        assert result == mock_instance
-
-
-def test_get_embedding_function_with_embedding_options() -> None:
-    """Test embedding function creation with EmbeddingOptions object."""
-    with patch("crewai.rag.embeddings.factory.EMBEDDING_PROVIDERS") as mock_providers:
-        mock_instance = MagicMock()
-        mock_openai = MagicMock(return_value=mock_instance)
-        mock_providers.__getitem__.return_value = mock_openai
-        mock_providers.__contains__.return_value = True
-
-        options = EmbeddingOptions(
-            provider="openai",
-            api_key=SecretStr("test-key"),
-            model_name="text-embedding-3-large",
-        )
-
-        result = get_embedding_function(options)
-
-        call_kwargs = mock_openai.call_args.kwargs
-        assert "api_key" in call_kwargs
-        assert call_kwargs["api_key"].get_secret_value() == "test-key"
-        assert "model_name" in call_kwargs
-        assert call_kwargs["model_name"] == "text-embedding-3-large"
-        assert result == mock_instance
-
-
-def test_get_embedding_function_sentence_transformer() -> None:
-    """Test sentence transformer embedding function."""
-    with patch("crewai.rag.embeddings.factory.EMBEDDING_PROVIDERS") as mock_providers:
-        mock_instance = MagicMock()
-        mock_st = MagicMock(return_value=mock_instance)
-        mock_providers.__getitem__.return_value = mock_st
-        mock_providers.__contains__.return_value = True
 
         config = {
-            "provider": "sentence-transformer",
+            "provider": "openai",
-            "config": {"model_name": "all-MiniLM-L6-v2"},
+            "config": {
+                "api_key": "test-key",
+                "model_name": "text-embedding-3-small",
+            },
         }
 
-        result = get_embedding_function(config)
+        build_embedder(config)
 
-        mock_st.assert_called_once_with(model_name="all-MiniLM-L6-v2")
+        mock_import.assert_called_once_with(
-        assert result == mock_instance
+            "crewai.rag.embeddings.providers.openai.openai_provider.OpenAIProvider"
+        )
+        mock_provider_class.assert_called_once()
 
+        call_kwargs = mock_provider_class.call_args.kwargs
+        assert call_kwargs["api_key"] == "test-key"
+        assert call_kwargs["model_name"] == "text-embedding-3-small"
 
-def test_get_embedding_function_ollama() -> None:
+    @patch("crewai.rag.embeddings.factory.import_and_validate_definition")
-    """Test Ollama embedding function."""
+    def test_build_embedder_azure(self, mock_import):
-    with patch("crewai.rag.embeddings.factory.EMBEDDING_PROVIDERS") as mock_providers:
+        """Test building Azure embedder."""
-        mock_instance = MagicMock()
+        mock_provider_class = MagicMock()
-        mock_ollama = MagicMock(return_value=mock_instance)
+        mock_provider_instance = MagicMock()
-        mock_providers.__getitem__.return_value = mock_ollama
+        mock_embedding_function = MagicMock()
-        mock_providers.__contains__.return_value = True
+
+        mock_import.return_value = mock_provider_class
+        mock_provider_class.return_value = mock_provider_instance
+        mock_provider_instance.embedding_callable.return_value = mock_embedding_function
+
+        config = {
+            "provider": "azure",
+            "config": {
+                "api_key": "test-azure-key",
+                "api_base": "https://test.openai.azure.com/",
+                "api_type": "azure",
+                "api_version": "2023-05-15",
+                "model_name": "text-embedding-3-small",
+                "deployment_id": "test-deployment",
+            },
+        }
+
+        build_embedder(config)
+
+        mock_import.assert_called_once_with(
+            "crewai.rag.embeddings.providers.microsoft.azure.AzureProvider"
+        )
+
+        call_kwargs = mock_provider_class.call_args.kwargs
+        assert call_kwargs["api_key"] == "test-azure-key"
+        assert call_kwargs["api_base"] == "https://test.openai.azure.com/"
+        assert call_kwargs["api_type"] == "azure"
+
+    @patch("crewai.rag.embeddings.factory.import_and_validate_definition")
+    def test_build_embedder_ollama(self, mock_import):
+        """Test building Ollama embedder."""
+        mock_provider_class = MagicMock()
+        mock_provider_instance = MagicMock()
+        mock_embedding_function = MagicMock()
+
+        mock_import.return_value = mock_provider_class
+        mock_provider_class.return_value = mock_provider_instance
+        mock_provider_instance.embedding_callable.return_value = mock_embedding_function
 
         config = {
             "provider": "ollama",
@@ -87,512 +93,152 @@ def test_get_embedding_function_ollama() -> None:
             },
         }
 
-        result = get_embedding_function(config)
+        build_embedder(config)
 
-        mock_ollama.assert_called_once_with(
+        mock_import.assert_called_once_with(
-            model_name="nomic-embed-text", url="http://localhost:11434"
+            "crewai.rag.embeddings.providers.ollama.ollama_provider.OllamaProvider"
         )
-        assert result == mock_instance
 
+    @patch("crewai.rag.embeddings.factory.import_and_validate_definition")
+    def test_build_embedder_cohere(self, mock_import):
+        """Test building Cohere embedder."""
+        mock_provider_class = MagicMock()
+        mock_provider_instance = MagicMock()
+        mock_embedding_function = MagicMock()
 
-def test_get_embedding_function_cohere() -> None:
+        mock_import.return_value = mock_provider_class
-    """Test Cohere embedding function."""
+        mock_provider_class.return_value = mock_provider_instance
-    with patch("crewai.rag.embeddings.factory.EMBEDDING_PROVIDERS") as mock_providers:
+        mock_provider_instance.embedding_callable.return_value = mock_embedding_function
-        mock_instance = MagicMock()
-        mock_cohere = MagicMock(return_value=mock_instance)
-        mock_providers.__getitem__.return_value = mock_cohere
-        mock_providers.__contains__.return_value = True
 
         config = {
             "provider": "cohere",
-            "config": {"api_key": "cohere-key", "model_name": "embed-english-v3.0"},
-        }
-
-        result = get_embedding_function(config)
-
-        mock_cohere.assert_called_once_with(
-            api_key="cohere-key", model_name="embed-english-v3.0"
-        )
-        assert result == mock_instance
-
-
-def test_get_embedding_function_huggingface() -> None:
-    """Test HuggingFace embedding function."""
-    with patch("crewai.rag.embeddings.factory.EMBEDDING_PROVIDERS") as mock_providers:
-        mock_instance = MagicMock()
-        mock_hf = MagicMock(return_value=mock_instance)
-        mock_providers.__getitem__.return_value = mock_hf
-        mock_providers.__contains__.return_value = True
-
-        config = {
-            "provider": "huggingface",
             "config": {
-                "api_key": "hf-token",
+                "api_key": "cohere-key",
-                "model_name": "sentence-transformers/all-MiniLM-L6-v2",
+                "model_name": "embed-english-v3.0",
             },
         }
 
-        result = get_embedding_function(config)
+        build_embedder(config)
 
-        mock_hf.assert_called_once_with(
+        mock_import.assert_called_once_with(
-            api_key="hf-token", model_name="sentence-transformers/all-MiniLM-L6-v2"
+            "crewai.rag.embeddings.providers.cohere.cohere_provider.CohereProvider"
         )
-        assert result == mock_instance
 
+    @patch("crewai.rag.embeddings.factory.import_and_validate_definition")
+    def test_build_embedder_voyageai(self, mock_import):
+        """Test building VoyageAI embedder."""
+        mock_provider_class = MagicMock()
+        mock_provider_instance = MagicMock()
+        mock_embedding_function = MagicMock()
 
-def test_get_embedding_function_onnx() -> None:
+        mock_import.return_value = mock_provider_class
-    """Test ONNX embedding function."""
+        mock_provider_class.return_value = mock_provider_instance
-    with patch("crewai.rag.embeddings.factory.EMBEDDING_PROVIDERS") as mock_providers:
+        mock_provider_instance.embedding_callable.return_value = mock_embedding_function
-        mock_instance = MagicMock()
-        mock_onnx = MagicMock(return_value=mock_instance)
-        mock_providers.__getitem__.return_value = mock_onnx
-        mock_providers.__contains__.return_value = True
 
-        config = {"provider": "onnx"}
-
-        result = get_embedding_function(config)
-
-        mock_onnx.assert_called_once()
-        assert result == mock_instance
-
-
-def test_get_embedding_function_google_palm() -> None:
-    """Test Google PaLM embedding function."""
-    with patch("crewai.rag.embeddings.factory.EMBEDDING_PROVIDERS") as mock_providers:
-        mock_instance = MagicMock()
-        mock_palm = MagicMock(return_value=mock_instance)
-        mock_providers.__getitem__.return_value = mock_palm
-        mock_providers.__contains__.return_value = True
-
-        config = {"provider": "google-palm", "config": {"api_key": "palm-key"}}
-
-        result = get_embedding_function(config)
-
-        mock_palm.assert_called_once_with(api_key="palm-key")
-        assert result == mock_instance
-
-
-def test_get_embedding_function_amazon_bedrock() -> None:
-    """Test Amazon Bedrock embedding function with explicit session."""
-    with patch("crewai.rag.embeddings.factory.EMBEDDING_PROVIDERS") as mock_providers:
-        mock_instance = MagicMock()
-        mock_bedrock = MagicMock(return_value=mock_instance)
-        mock_providers.__getitem__.return_value = mock_bedrock
-        mock_providers.__contains__.return_value = True
-
-        # Provide an explicit session to avoid boto3 import
-        mock_session = MagicMock()
         config = {
-            "provider": "amazon-bedrock",
+            "provider": "voyageai",
             "config": {
-                "session": mock_session,
+                "api_key": "voyage-key",
-                "region_name": "us-west-2",
+                "model": "voyage-2",
-                "model_name": "amazon.titan-embed-text-v1",
             },
         }
 
-        result = get_embedding_function(config)
+        build_embedder(config)
 
-        mock_bedrock.assert_called_once_with(
+        mock_import.assert_called_once_with(
-            session=mock_session,
+            "crewai.rag.embeddings.providers.voyageai.voyageai_provider.VoyageAIProvider"
-            region_name="us-west-2",
-            model_name="amazon.titan-embed-text-v1",
         )
-        assert result == mock_instance
 
+    @patch("crewai.rag.embeddings.factory.import_and_validate_definition")
+    def test_build_embedder_watson(self, mock_import):
+        """Test building Watson embedder."""
+        mock_provider_class = MagicMock()
+        mock_provider_instance = MagicMock()
+        mock_embedding_function = MagicMock()
 
-def test_get_embedding_function_jina() -> None:
+        mock_import.return_value = mock_provider_class
-    """Test Jina embedding function."""
+        mock_provider_class.return_value = mock_provider_instance
-    with patch("crewai.rag.embeddings.factory.EMBEDDING_PROVIDERS") as mock_providers:
+        mock_provider_instance.embedding_callable.return_value = mock_embedding_function
-        mock_instance = MagicMock()
-        mock_jina = MagicMock(return_value=mock_instance)
-        mock_providers.__getitem__.return_value = mock_jina
-        mock_providers.__contains__.return_value = True
 
         config = {
-            "provider": "jina",
+            "provider": "watson",
             "config": {
-                "api_key": "jina-key",
+                "model_id": "ibm/slate-125m-english-rtrvr",
-                "model_name": "jina-embeddings-v2-base-en",
+                "api_key": "watson-key",
+                "url": "https://us-south.ml.cloud.ibm.com",
+                "project_id": "test-project",
             },
         }
 
-        result = get_embedding_function(config)
+        build_embedder(config)
 
-        mock_jina.assert_called_once_with(
+        mock_import.assert_called_once_with(
-            api_key="jina-key", model_name="jina-embeddings-v2-base-en"
+            "crewai.rag.embeddings.providers.ibm.watson.WatsonProvider"
-        )
-        assert result == mock_instance
-
-
-def test_get_embedding_function_unsupported_provider() -> None:
-    """Test handling of unsupported provider."""
-    config = {"provider": "unsupported-provider"}
-
-    with pytest.raises(ValueError, match="Unsupported provider: unsupported-provider"):
-        get_embedding_function(config)
-
-
-def test_get_embedding_function_config_modification() -> None:
-    """Test that original config dict is not modified."""
-    original_config = {
-        "provider": "openai",
-        "config": {"api_key": "test-key", "model": "text-embedding-3-small"},
-    }
-    config_copy = original_config.copy()
-
-    with patch("crewai.rag.embeddings.factory.EMBEDDING_PROVIDERS") as mock_providers:
-        mock_instance = MagicMock()
-        mock_openai = MagicMock(return_value=mock_instance)
-        mock_providers.__getitem__.return_value = mock_openai
-        mock_providers.__contains__.return_value = True
-
-        get_embedding_function(config_copy)
-
-    assert config_copy == original_config
-
-
-def test_get_embedding_function_exclude_none_values() -> None:
-    """Test that None values are excluded from embedding function calls."""
-    with patch("crewai.rag.embeddings.factory.EMBEDDING_PROVIDERS") as mock_providers:
-        mock_instance = MagicMock()
-        mock_openai = MagicMock(return_value=mock_instance)
-        mock_providers.__getitem__.return_value = mock_openai
-        mock_providers.__contains__.return_value = True
-
-        options = EmbeddingOptions(
-            provider="openai", api_key=SecretStr("test-key"), model_name=None
         )
 
-        result = get_embedding_function(options)
+    def test_build_embedder_unknown_provider(self):
+        """Test error handling for unknown provider."""
+        config = {"provider": "unknown-provider", "config": {}}
 
-        call_kwargs = mock_openai.call_args.kwargs
+        with pytest.raises(ValueError, match="Unknown provider: unknown-provider"):
-        assert "api_key" in call_kwargs
+            build_embedder(config)
-        assert call_kwargs["api_key"].get_secret_value() == "test-key"
-        assert "model_name" not in call_kwargs
-        assert result == mock_instance
 
+    def test_build_embedder_missing_provider(self):
+        """Test error handling for missing provider key."""
+        config = {"config": {"api_key": "test-key"}}
 
-def test_get_embedding_function_instructor() -> None:
+        with pytest.raises(KeyError):
-    """Test Instructor embedding function."""
+            build_embedder(config)
-    with patch("crewai.rag.embeddings.factory.EMBEDDING_PROVIDERS") as mock_providers:
+
-        mock_instance = MagicMock()
+    @patch("crewai.rag.embeddings.factory.import_and_validate_definition")
-        mock_instructor = MagicMock(return_value=mock_instance)
+    def test_build_embedder_import_error(self, mock_import):
-        mock_providers.__getitem__.return_value = mock_instructor
+        """Test error handling when provider import fails."""
-        mock_providers.__contains__.return_value = True
+        mock_import.side_effect = ImportError("Module not found")
+
+        config = {"provider": "openai", "config": {"api_key": "test-key"}}
+
+        with pytest.raises(ImportError, match="Failed to import provider openai"):
+            build_embedder(config)
+
+    @patch("crewai.rag.embeddings.factory.import_and_validate_definition")
+    def test_build_embedder_custom_provider(self, mock_import):
+        """Test building custom embedder."""
+        mock_provider_class = MagicMock()
+        mock_provider_instance = MagicMock()
+        mock_embedding_callable = MagicMock()
+
+        mock_import.return_value = mock_provider_class
+        mock_provider_class.return_value = mock_provider_instance
+        mock_provider_instance.embedding_callable = mock_embedding_callable
 
         config = {
-            "provider": "instructor",
+            "provider": "custom",
-            "config": {"model_name": "hkunlp/instructor-large"},
+            "config": {"embedding_callable": mock_embedding_callable},
         }
 
-        result = get_embedding_function(config)
+        build_embedder(config)
 
-        mock_instructor.assert_called_once_with(model_name="hkunlp/instructor-large")
+        mock_import.assert_called_once_with(
-        assert result == mock_instance
+            "crewai.rag.embeddings.providers.custom.custom_provider.CustomProvider"
-
-
-def test_get_embedding_function_google_generativeai() -> None:
-    """Test Google Generative AI embedding function."""
-    with patch("crewai.rag.embeddings.factory.EMBEDDING_PROVIDERS") as mock_providers:
-        mock_instance = MagicMock()
-        mock_google = MagicMock(return_value=mock_instance)
-        mock_providers.__getitem__.return_value = mock_google
-        mock_providers.__contains__.return_value = True
-
-        config = {
-            "provider": "google-generativeai",
-            "config": {"api_key": "google-key", "model_name": "models/embedding-001"},
-        }
-
-        result = get_embedding_function(config)
-
-        mock_google.assert_called_once_with(
-            api_key="google-key", model_name="models/embedding-001"
         )
-        assert result == mock_instance
 
+        call_kwargs = mock_provider_class.call_args.kwargs
+        assert call_kwargs["embedding_callable"] == mock_embedding_callable
 
-def test_get_embedding_function_google_vertex() -> None:
+    @patch("crewai.rag.embeddings.factory.import_and_validate_definition")
-    """Test Google Vertex AI embedding function."""
+    @patch("crewai.rag.embeddings.factory.build_embedder_from_provider")
-    with patch("crewai.rag.embeddings.factory.EMBEDDING_PROVIDERS") as mock_providers:
+    def test_build_embedder_with_provider_instance(
-        mock_instance = MagicMock()
+        self, mock_build_from_provider, mock_import
-        mock_vertex = MagicMock(return_value=mock_instance)
+    ):
-        mock_providers.__getitem__.return_value = mock_vertex
+        """Test building embedder from provider instance."""
-        mock_providers.__contains__.return_value = True
+        from crewai.rag.core.base_embeddings_provider import BaseEmbeddingsProvider
 
-        config = {
+        mock_provider = MagicMock(spec=BaseEmbeddingsProvider)
-            "provider": "google-vertex",
+        mock_embedding_function = MagicMock()
-            "config": {
+        mock_build_from_provider.return_value = mock_embedding_function
-                "api_key": "vertex-key",
-                "project_id": "my-project",
-                "region": "us-central1",
-            },
-        }
 
-        result = get_embedding_function(config)
+        result = build_embedder(mock_provider)
 
-        mock_vertex.assert_called_once_with(
+        mock_build_from_provider.assert_called_once_with(mock_provider)
-            api_key="vertex-key", project_id="my-project", region="us-central1"
+        assert result == mock_embedding_function
-        )
+        mock_import.assert_not_called()
-        assert result == mock_instance
-
-
-def test_get_embedding_function_roboflow() -> None:
-    """Test Roboflow embedding function."""
-    with patch("crewai.rag.embeddings.factory.EMBEDDING_PROVIDERS") as mock_providers:
-        mock_instance = MagicMock()
-        mock_roboflow = MagicMock(return_value=mock_instance)
-        mock_providers.__getitem__.return_value = mock_roboflow
-        mock_providers.__contains__.return_value = True
-
-        config = {
-            "provider": "roboflow",
-            "config": {
-                "api_key": "roboflow-key",
-                "api_url": "https://infer.roboflow.com",
-            },
-        }
-
-        result = get_embedding_function(config)
-
-        mock_roboflow.assert_called_once_with(
-            api_key="roboflow-key", api_url="https://infer.roboflow.com"
-        )
-        assert result == mock_instance
-
-
-def test_get_embedding_function_openclip() -> None:
-    """Test OpenCLIP embedding function."""
-    with patch("crewai.rag.embeddings.factory.EMBEDDING_PROVIDERS") as mock_providers:
-        mock_instance = MagicMock()
-        mock_openclip = MagicMock(return_value=mock_instance)
-        mock_providers.__getitem__.return_value = mock_openclip
-        mock_providers.__contains__.return_value = True
-
-        config = {
-            "provider": "openclip",
-            "config": {"model_name": "ViT-B-32", "checkpoint": "laion2b_s34b_b79k"},
-        }
-
-        result = get_embedding_function(config)
-
-        mock_openclip.assert_called_once_with(
-            model_name="ViT-B-32", checkpoint="laion2b_s34b_b79k"
-        )
-        assert result == mock_instance
-
-
-def test_get_embedding_function_text2vec() -> None:
-    """Test Text2Vec embedding function."""
-    with patch("crewai.rag.embeddings.factory.EMBEDDING_PROVIDERS") as mock_providers:
-        mock_instance = MagicMock()
-        mock_text2vec = MagicMock(return_value=mock_instance)
-        mock_providers.__getitem__.return_value = mock_text2vec
-        mock_providers.__contains__.return_value = True
-
-        config = {
-            "provider": "text2vec",
-            "config": {"model_name": "shibing624/text2vec-base-chinese"},
-        }
-
-        result = get_embedding_function(config)
-
-        mock_text2vec.assert_called_once_with(
-            model_name="shibing624/text2vec-base-chinese"
-        )
-        assert result == mock_instance
-
-
-def test_model_to_model_name_conversion() -> None:
-    """Test that 'model' field is converted to 'model_name' for nested config."""
-    with patch("crewai.rag.embeddings.factory.EMBEDDING_PROVIDERS") as mock_providers:
-        mock_instance = MagicMock()
-        mock_openai = MagicMock(return_value=mock_instance)
-        mock_providers.__getitem__.return_value = mock_openai
-        mock_providers.__contains__.return_value = True
-
-        config = {
-            "provider": "openai",
-            "config": {"api_key": "test-key", "model": "text-embedding-3-small"},
-        }
-
-        result = get_embedding_function(config)
-
-        mock_openai.assert_called_once_with(
-            api_key="test-key", model_name="text-embedding-3-small"
-        )
-        assert result == mock_instance
-
-
-def test_api_key_injection_from_env_openai() -> None:
-    """Test that OpenAI API key is injected from environment when not provided."""
-    with patch("crewai.rag.embeddings.factory.EMBEDDING_PROVIDERS") as mock_providers:
-        mock_instance = MagicMock()
-        mock_openai = MagicMock(return_value=mock_instance)
-        mock_providers.__getitem__.return_value = mock_openai
-        mock_providers.__contains__.return_value = True
-
-        with patch("crewai.rag.embeddings.factory.os.getenv") as mock_getenv:
-            mock_getenv.return_value = "env-openai-key"
-
-            config = {
-                "provider": "openai",
-                "config": {"model": "text-embedding-3-small"},
-            }
-
-            result = get_embedding_function(config)
-
-            mock_getenv.assert_called_with("OPENAI_API_KEY")
-            mock_openai.assert_called_once_with(
-                api_key="env-openai-key", model_name="text-embedding-3-small"
-            )
-            assert result == mock_instance
-
-
-def test_api_key_injection_from_env_cohere() -> None:
-    """Test that Cohere API key is injected from environment when not provided."""
-    with patch("crewai.rag.embeddings.factory.EMBEDDING_PROVIDERS") as mock_providers:
-        mock_instance = MagicMock()
-        mock_cohere = MagicMock(return_value=mock_instance)
-        mock_providers.__getitem__.return_value = mock_cohere
-        mock_providers.__contains__.return_value = True
-
-        with patch("crewai.rag.embeddings.factory.os.getenv") as mock_getenv:
-            mock_getenv.return_value = "env-cohere-key"
-
-            config = {
-                "provider": "cohere",
-                "config": {"model_name": "embed-english-v3.0"},
-            }
-
-            result = get_embedding_function(config)
-
-            mock_getenv.assert_called_with("COHERE_API_KEY")
-            mock_cohere.assert_called_once_with(
-                api_key="env-cohere-key", model_name="embed-english-v3.0"
-            )
-            assert result == mock_instance
-
-
-def test_api_key_not_injected_when_provided() -> None:
-    """Test that API key from config takes precedence over environment."""
-    with patch("crewai.rag.embeddings.factory.EMBEDDING_PROVIDERS") as mock_providers:
-        mock_instance = MagicMock()
-        mock_openai = MagicMock(return_value=mock_instance)
-        mock_providers.__getitem__.return_value = mock_openai
-        mock_providers.__contains__.return_value = True
-
-        with patch("crewai.rag.embeddings.factory.os.getenv") as mock_getenv:
-            mock_getenv.return_value = "env-key"
-
-            config = {
-                "provider": "openai",
-                "config": {"api_key": "config-key", "model": "text-embedding-3-small"},
-            }
-
-            result = get_embedding_function(config)
-
-            mock_openai.assert_called_once_with(
-                api_key="config-key", model_name="text-embedding-3-small"
-            )
-            assert result == mock_instance
-
-
-def test_amazon_bedrock_session_injection() -> None:
-    """Test that boto3 session is automatically created for amazon-bedrock."""
-    with patch("crewai.rag.embeddings.factory.EMBEDDING_PROVIDERS") as mock_providers:
-        mock_instance = MagicMock()
-        mock_bedrock = MagicMock(return_value=mock_instance)
-        mock_providers.__getitem__.return_value = mock_bedrock
-        mock_providers.__contains__.return_value = True
-
-        mock_boto3 = MagicMock()
-        with patch.dict("sys.modules", {"boto3": mock_boto3}):
-            mock_session = MagicMock()
-            mock_boto3.Session.return_value = mock_session
-
-            config = {
-                "provider": "amazon-bedrock",
-                "config": {"model_name": "amazon.titan-embed-text-v1"},
-            }
-
-            result = get_embedding_function(config)
-
-            mock_boto3.Session.assert_called_once()
-            mock_bedrock.assert_called_once_with(
-                session=mock_session, model_name="amazon.titan-embed-text-v1"
-            )
-            assert result == mock_instance
-
-
-def test_amazon_bedrock_session_not_injected_when_provided() -> None:
-    """Test that provided session is used for amazon-bedrock."""
-    with patch("crewai.rag.embeddings.factory.EMBEDDING_PROVIDERS") as mock_providers:
-        mock_instance = MagicMock()
-        mock_bedrock = MagicMock(return_value=mock_instance)
-        mock_providers.__getitem__.return_value = mock_bedrock
-        mock_providers.__contains__.return_value = True
-
-        existing_session = MagicMock()
-        config = {
-            "provider": "amazon-bedrock",
-            "config": {
-                "session": existing_session,
-                "model_name": "amazon.titan-embed-text-v1",
-            },
-        }
-
-        result = get_embedding_function(config)
-
-        mock_bedrock.assert_called_once_with(
-            session=existing_session, model_name="amazon.titan-embed-text-v1"
-        )
-        assert result == mock_instance
-
-
-def test_amazon_bedrock_boto3_import_error() -> None:
-    """Test error handling when boto3 is not installed."""
-    with patch("crewai.rag.embeddings.factory.EMBEDDING_PROVIDERS") as mock_providers:
-        mock_providers.__contains__.return_value = True
-
-        with patch.dict("sys.modules", {"boto3": None}):
-            config = {
-                "provider": "amazon-bedrock",
-                "config": {"model_name": "amazon.titan-embed-text-v1"},
-            }
-
-            with pytest.raises(
-                ImportError, match="boto3 is required for amazon-bedrock"
-            ):
-                get_embedding_function(config)
-
-
-def test_amazon_bedrock_session_creation_error() -> None:
-    """Test error handling when AWS session creation fails."""
-    with patch("crewai.rag.embeddings.factory.EMBEDDING_PROVIDERS") as mock_providers:
-        mock_providers.__contains__.return_value = True
-
-        mock_boto3 = MagicMock()
-        with patch.dict("sys.modules", {"boto3": mock_boto3}):
-            mock_boto3.Session.side_effect = Exception("AWS credentials not configured")
-
-            config = {
-                "provider": "amazon-bedrock",
-                "config": {"model_name": "amazon.titan-embed-text-v1"},
-            }
-
-            with pytest.raises(ValueError, match="Failed to create AWS session"):
-                get_embedding_function(config)
-
-
-def test_invalid_config_format() -> None:
-    """Test error handling for invalid config format."""
-    config = {
-        "provider": "openai",
-        "api_key": "test-key",
-        "model": "text-embedding-3-small",
-    }
-
-    with pytest.raises(ValueError, match="Invalid embedder configuration format"):
-        get_embedding_function(config)

tests/rag/embeddings/test_factory_azure.py

@@ -4,76 +4,119 @@ from unittest.mock import MagicMock, patch
 
 import pytest
 
-from crewai.rag.embeddings.factory import EmbedderConfig, get_embedding_function
+from crewai.rag.embeddings.factory import build_embedder
 
 
 class TestAzureEmbedderFactory:
     """Test Azure embedder configuration with factory function."""
 
-    @patch("crewai.rag.embeddings.factory.EMBEDDING_PROVIDERS")
+    @patch("crewai.rag.embeddings.factory.import_and_validate_definition")
-    def test_azure_with_nested_config(self, mock_providers):
+    def test_azure_with_nested_config(self, mock_import):
         """Test Azure configuration with nested config key."""
+        mock_provider_class = MagicMock()
+        mock_provider_instance = MagicMock()
+        mock_embedding_function = MagicMock()
 
-        mock_embedding = MagicMock()
+        mock_import.return_value = mock_provider_class
-        mock_openai_func = MagicMock(return_value=mock_embedding)
+        mock_provider_class.return_value = mock_provider_instance
-        mock_providers.__getitem__.return_value = mock_openai_func
+        mock_provider_instance.embedding_callable.return_value = mock_embedding_function
-        mock_providers.__contains__.return_value = True
 
-        embedder_config = EmbedderConfig(
+        embedder_config = {
-            provider="openai",
+            "provider": "azure",
-            config={
+            "config": {
                 "api_key": "test-azure-key",
                 "api_base": "https://test.openai.azure.com/",
                 "api_type": "azure",
                 "api_version": "2023-05-15",
-                "model": "text-embedding-3-small",
+                "model_name": "text-embedding-3-small",
                 "deployment_id": "test-deployment",
             },
-        )
-
-        result = get_embedding_function(embedder_config)
-
-        mock_openai_func.assert_called_once_with(
-            api_key="test-azure-key",
-            api_base="https://test.openai.azure.com/",
-            api_type="azure",
-            api_version="2023-05-15",
-            model_name="text-embedding-3-small",
-            deployment_id="test-deployment",
-        )
-        assert result == mock_embedding
-
-    @patch("crewai.rag.embeddings.factory.EMBEDDING_PROVIDERS")
-    def test_regular_openai_with_nested_config(self, mock_providers):
-        """Test regular OpenAI configuration with nested config."""
-
-        mock_embedding = MagicMock()
-        mock_openai_func = MagicMock(return_value=mock_embedding)
-        mock_providers.__getitem__.return_value = mock_openai_func
-        mock_providers.__contains__.return_value = True
-
-        embedder_config = EmbedderConfig(
-            provider="openai",
-            config={"api_key": "test-openai-key", "model": "text-embedding-3-large"},
-        )
-
-        result = get_embedding_function(embedder_config)
-
-        mock_openai_func.assert_called_once_with(
-            api_key="test-openai-key", model_name="text-embedding-3-large"
-        )
-        assert result == mock_embedding
-
-    def test_flat_format_raises_error(self):
-        """Test that flat format raises an error."""
-        embedder_config = {
-            "provider": "openai",
-            "api_key": "test-key",
-            "model_name": "text-embedding-3-small",
         }
 
-        with pytest.raises(ValueError) as exc_info:
+        result = build_embedder(embedder_config)
-            get_embedding_function(embedder_config)
 
-        assert "Invalid embedder configuration format" in str(exc_info.value)
+        mock_import.assert_called_once_with(
-        assert "nested under a 'config' key" in str(exc_info.value)
+            "crewai.rag.embeddings.providers.microsoft.azure.AzureProvider"
+        )
+
+        call_kwargs = mock_provider_class.call_args.kwargs
+        assert call_kwargs["api_key"] == "test-azure-key"
+        assert call_kwargs["api_base"] == "https://test.openai.azure.com/"
+        assert call_kwargs["api_type"] == "azure"
+        assert call_kwargs["api_version"] == "2023-05-15"
+        assert call_kwargs["model_name"] == "text-embedding-3-small"
+        assert call_kwargs["deployment_id"] == "test-deployment"
+
+        assert result == mock_embedding_function
+
+    @patch("crewai.rag.embeddings.factory.import_and_validate_definition")
+    def test_regular_openai_with_nested_config(self, mock_import):
+        """Test regular OpenAI configuration with nested config."""
+        mock_provider_class = MagicMock()
+        mock_provider_instance = MagicMock()
+        mock_embedding_function = MagicMock()
+
+        mock_import.return_value = mock_provider_class
+        mock_provider_class.return_value = mock_provider_instance
+        mock_provider_instance.embedding_callable.return_value = mock_embedding_function
+
+        embedder_config = {
+            "provider": "openai",
+            "config": {"api_key": "test-openai-key", "model": "text-embedding-3-large"},
+        }
+
+        result = build_embedder(embedder_config)
+
+        mock_import.assert_called_once_with(
+            "crewai.rag.embeddings.providers.openai.openai_provider.OpenAIProvider"
+        )
+
+        call_kwargs = mock_provider_class.call_args.kwargs
+        assert call_kwargs["api_key"] == "test-openai-key"
+        assert call_kwargs["model"] == "text-embedding-3-large"
+
+        assert result == mock_embedding_function
+
+    @patch("crewai.rag.embeddings.factory.import_and_validate_definition")
+    def test_azure_provider_with_minimal_config(self, mock_import):
+        """Test Azure provider with minimal required configuration."""
+        mock_provider_class = MagicMock()
+        mock_provider_instance = MagicMock()
+        mock_embedding_function = MagicMock()
+
+        mock_import.return_value = mock_provider_class
+        mock_provider_class.return_value = mock_provider_instance
+        mock_provider_instance.embedding_callable.return_value = mock_embedding_function
+
+        embedder_config = {
+            "provider": "azure",
+            "config": {
+                "api_key": "test-key",
+                "api_base": "https://test.openai.azure.com/",
+            },
+        }
+
+        build_embedder(embedder_config)
+
+        mock_import.assert_called_once_with(
+            "crewai.rag.embeddings.providers.microsoft.azure.AzureProvider"
+        )
+
+        call_kwargs = mock_provider_class.call_args.kwargs
+        assert call_kwargs["api_key"] == "test-key"
+        assert call_kwargs["api_base"] == "https://test.openai.azure.com/"
+
+    @patch("crewai.rag.embeddings.factory.import_and_validate_definition")
+    def test_azure_import_error(self, mock_import):
+        """Test handling of import errors for Azure provider."""
+        mock_import.side_effect = ImportError("Failed to import Azure provider")
+
+        embedder_config = {
+            "provider": "azure",
+            "config": {"api_key": "test-key"},
+        }
+
+        with pytest.raises(ImportError) as exc_info:
+            build_embedder(embedder_config)
+
+        assert "Failed to import provider azure" in str(exc_info.value)

tests/rag/test_error_handling.py

@@ -55,7 +55,7 @@ def test_knowledge_storage_invalid_embedding_config(mock_get_client: MagicMock)
     mock_get_client.return_value = MagicMock()
 
     with patch(
-        "crewai.knowledge.storage.knowledge_storage.get_embedding_function"
+        "crewai.knowledge.storage.knowledge_storage.build_embedder"
     ) as mock_get_embedding:
         mock_get_embedding.side_effect = ValueError(
             "Unsupported provider: invalid_provider"

tests/utilities/test_azure_embedder_config.py

@@ -1,82 +0,0 @@
-"""Test Azure embedder configuration with nested format only."""
-
-from unittest.mock import MagicMock, patch
-
-from crewai.rag.embeddings.configurator import EmbeddingConfigurator
-
-
-class TestAzureEmbedderConfiguration:
-    """Test Azure embedder configuration with nested format."""
-
-    @patch(
-        "chromadb.utils.embedding_functions.openai_embedding_function.OpenAIEmbeddingFunction"
-    )
-    def test_azure_openai_with_nested_config(self, mock_openai_func):
-        """Test Azure configuration using OpenAI provider with nested config key."""
-        mock_embedding = MagicMock()
-        mock_openai_func.return_value = mock_embedding
-
-        configurator = EmbeddingConfigurator()
-
-        embedder_config = {
-            "provider": "openai",
-            "config": {
-                "api_key": "test-azure-key",
-                "api_base": "https://test.openai.azure.com/",
-                "api_type": "azure",
-                "api_version": "2023-05-15",
-                "model": "text-embedding-3-small",
-                "deployment_id": "test-deployment",
-            },
-        }
-
-        result = configurator.configure_embedder(embedder_config)
-
-        mock_openai_func.assert_called_once_with(
-            api_key="test-azure-key",
-            model_name="text-embedding-3-small",
-            api_base="https://test.openai.azure.com/",
-            api_type="azure",
-            api_version="2023-05-15",
-            default_headers=None,
-            dimensions=None,
-            deployment_id="test-deployment",
-            organization_id=None,
-        )
-        assert result == mock_embedding
-
-    @patch(
-        "chromadb.utils.embedding_functions.openai_embedding_function.OpenAIEmbeddingFunction"
-    )
-    def test_azure_provider_with_nested_config(self, mock_openai_func):
-        """Test using 'azure' as provider with nested config."""
-        mock_embedding = MagicMock()
-        mock_openai_func.return_value = mock_embedding
-
-        configurator = EmbeddingConfigurator()
-
-        embedder_config = {
-            "provider": "azure",
-            "config": {
-                "api_key": "test-azure-key",
-                "api_base": "https://test.openai.azure.com/",
-                "api_version": "2023-05-15",
-                "model": "text-embedding-3-small",
-                "deployment_id": "test-deployment",
-            },
-        }
-
-        result = configurator.configure_embedder(embedder_config)
-
-        mock_openai_func.assert_called_once_with(
-            api_key="test-azure-key",
-            api_base="https://test.openai.azure.com/",
-            api_type="azure",
-            api_version="2023-05-15",
-            model_name="text-embedding-3-small",
-            default_headers=None,
-            dimensions=None,
-            deployment_id="test-deployment",
-            organization_id=None,
-        )
-        assert result == mock_embedding

tests/utilities/test_embedding_configuration.py

@@ -1,25 +0,0 @@
-from unittest.mock import patch
-
-import pytest
-
-from crewai.rag.embeddings.configurator import EmbeddingConfigurator
-
-
-def test_configure_embedder_importerror():
-    configurator = EmbeddingConfigurator()
-    
-    embedder_config = {
-        'provider': 'openai',
-        'config': {
-            'model': 'text-embedding-ada-002',
-        }
-    }
-    
-    with patch('chromadb.utils.embedding_functions.openai_embedding_function.OpenAIEmbeddingFunction') as mock_openai:
-        mock_openai.side_effect = ImportError("Module not found.")
-        
-        with pytest.raises(ImportError) as exc_info:
-            configurator.configure_embedder(embedder_config)
-
-        assert str(exc_info.value) == "Module not found."
-        mock_openai.assert_called_once()

uv.lock

@@ -142,6 +142,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/1b/8e/78ee35774201f38d5e1ba079c9958f7629b1fd079459aea9467441dbfbf5/aiohttp-3.12.15-cp313-cp313-win_amd64.whl", hash = "sha256:1a649001580bdb37c6fdb1bebbd7e3bc688e8ec2b5c6f52edbb664662b17dc84", size = 449067, upload-time = "2025-07-29T05:51:52.549Z" },
 ]
 
+[[package]]
+name = "aiolimiter"
+version = "1.2.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/f1/23/b52debf471f7a1e42e362d959a3982bdcb4fe13a5d46e63d28868807a79c/aiolimiter-1.2.1.tar.gz", hash = "sha256:e02a37ea1a855d9e832252a105420ad4d15011505512a1a1d814647451b5cca9", size = 7185, upload-time = "2024-12-08T15:31:51.496Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/f3/ba/df6e8e1045aebc4778d19b8a3a9bc1808adb1619ba94ca354d9ba17d86c3/aiolimiter-1.2.1-py3-none-any.whl", hash = "sha256:d3f249e9059a20badcb56b61601a83556133655c11d1eb3dd3e04ff069e5f3c7", size = 6711, upload-time = "2024-12-08T15:31:49.874Z" },
+]
+
 [[package]]
 name = "aiosignal"
 version = "1.4.0"
@@ -371,6 +380,34 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/10/cb/f2ad4230dc2eb1a74edf38f1a38b9b52277f75bef262d8908e60d957e13c/blinker-1.9.0-py3-none-any.whl", hash = "sha256:ba0efaa9080b619ff2f3459d1d500c57bddea4a6b424b60a91141db6fd2f08bc", size = 8458, upload-time = "2024-11-08T17:25:46.184Z" },
 ]
 
+[[package]]
+name = "boto3"
+version = "1.40.39"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "botocore" },
+    { name = "jmespath" },
+    { name = "s3transfer" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/fe/5b/2b79e27e19b5dc0360e07cb40c6364dd8f7104fe7b4016ae65a527a2535d/boto3-1.40.39.tar.gz", hash = "sha256:27ca06d4d6f838b056b4935c9eceb92c8d125dbe0e895c5583bcf7130627dcd2", size = 111587, upload-time = "2025-09-25T19:20:02.534Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/f1/7e/72b4f38c85ea879b27f90ad0d51f26b26e320bbc86b75664c0cf409d3d84/boto3-1.40.39-py3-none-any.whl", hash = "sha256:e2cab5606269fe9f428981892aa592b7e0c087a038774475fa4cd6c8b5fe0a99", size = 139345, upload-time = "2025-09-25T19:20:00.381Z" },
+]
+
+[[package]]
+name = "botocore"
+version = "1.40.39"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "jmespath" },
+    { name = "python-dateutil" },
+    { name = "urllib3" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/d8/30/44883126961d895ff8b69b8f7d1b2c60e9a348e38d4354ee597b69b8b5f8/botocore-1.40.39.tar.gz", hash = "sha256:c6efc55cac341811ba90c693d20097db6e2ce903451d94496bccd3f672b1709d", size = 14356776, upload-time = "2025-09-25T19:19:49.842Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/b2/57/2400d0cf030650b02a25a2aeb87729e51cb2aa8d97a2b4d9fec05c671f0b/botocore-1.40.39-py3-none-any.whl", hash = "sha256:144e0e887a9fc198c6772f660fc006028bd1a9ce5eea3caddd848db3e421bc79", size = 14025786, upload-time = "2025-09-25T19:19:46.177Z" },
+]
+
 [[package]]
 name = "browserbase"
 version = "1.4.0"
@@ -680,6 +717,9 @@ dependencies = [
 aisuite = [
     { name = "aisuite" },
 ]
+aws = [
+    { name = "boto3" },
+]
 docling = [
     { name = "docling" },
 ]
@@ -704,6 +744,12 @@ qdrant = [
 tools = [
     { name = "crewai-tools" },
 ]
+voyageai = [
+    { name = "voyageai" },
+]
+watson = [
+    { name = "ibm-watsonx-ai" },
+]
 
 [package.dev-dependencies]
 dev = [
@@ -730,10 +776,12 @@ requires-dist = [
     { name = "aisuite", marker = "extra == 'aisuite'", specifier = ">=0.1.10" },
     { name = "appdirs", specifier = ">=1.4.4" },
     { name = "blinker", specifier = ">=1.9.0" },
+    { name = "boto3", marker = "extra == 'aws'", specifier = ">=1.40.38" },
     { name = "chromadb", specifier = ">=0.5.23" },
     { name = "click", specifier = ">=8.1.7" },
     { name = "crewai-tools", marker = "extra == 'tools'", specifier = "~=0.73.0" },
     { name = "docling", marker = "extra == 'docling'", specifier = ">=2.12.0" },
+    { name = "ibm-watsonx-ai", marker = "extra == 'watson'", specifier = ">=1.3.39" },
     { name = "instructor", specifier = ">=1.3.3" },
     { name = "json-repair", specifier = "==0.25.2" },
     { name = "json5", specifier = ">=0.10.0" },
@@ -763,8 +811,9 @@ requires-dist = [
     { name = "tomli", specifier = ">=2.0.2" },
     { name = "tomli-w", specifier = ">=1.1.0" },
     { name = "uv", specifier = ">=0.4.25" },
+    { name = "voyageai", marker = "extra == 'voyageai'", specifier = ">=0.3.5" },
 ]
-provides-extras = ["aisuite", "docling", "embeddings", "mem0", "openpyxl", "pandas", "pdfplumber", "qdrant", "tools"]
+provides-extras = ["aisuite", "aws", "docling", "embeddings", "mem0", "openpyxl", "pandas", "pdfplumber", "qdrant", "tools", "voyageai", "watson"]
 
 [package.metadata.requires-dev]
 dev = [
@@ -1608,6 +1657,59 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/48/30/47d0bf6072f7252e6521f3447ccfa40b421b6824517f82854703d0f5a98b/hyperframe-6.1.0-py3-none-any.whl", hash = "sha256:b03380493a519fce58ea5af42e4a42317bf9bd425596f7a0835ffce80f1a42e5", size = 13007, upload-time = "2025-01-22T21:41:47.295Z" },
 ]
 
+[[package]]
+name = "ibm-cos-sdk"
+version = "2.14.3"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "ibm-cos-sdk-core" },
+    { name = "ibm-cos-sdk-s3transfer" },
+    { name = "jmespath" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/98/b8/b99f17ece72d4bccd7e75539b9a294d0f73ace5c6c475d8f2631afd6f65b/ibm_cos_sdk-2.14.3.tar.gz", hash = "sha256:643b6f2aa1683adad7f432df23407d11ae5adb9d9ad01214115bee77dc64364a", size = 58831, upload-time = "2025-08-01T06:35:51.722Z" }
+
+[[package]]
+name = "ibm-cos-sdk-core"
+version = "2.14.3"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "jmespath" },
+    { name = "python-dateutil" },
+    { name = "requests" },
+    { name = "urllib3" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/7e/45/80c23aa1e13175a9deefe43cbf8e853a3d3bfc8dfa8b6d6fe83e5785fe21/ibm_cos_sdk_core-2.14.3.tar.gz", hash = "sha256:85dee7790c92e8db69bf39dae4c02cac211e3c1d81bb86e64fa2d1e929674623", size = 1103637, upload-time = "2025-08-01T06:35:41.645Z" }
+
+[[package]]
+name = "ibm-cos-sdk-s3transfer"
+version = "2.14.3"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "ibm-cos-sdk-core" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/f3/ff/c9baf0997266d398ae08347951a2970e5e96ed6232ed0252f649f2b9a7eb/ibm_cos_sdk_s3transfer-2.14.3.tar.gz", hash = "sha256:2251ebfc4a46144401e431f4a5d9f04c262a0d6f95c88a8e71071da056e55f72", size = 139594, upload-time = "2025-08-01T06:35:46.403Z" }
+
+[[package]]
+name = "ibm-watsonx-ai"
+version = "1.3.39"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "cachetools" },
+    { name = "certifi" },
+    { name = "httpx" },
+    { name = "ibm-cos-sdk" },
+    { name = "lomond" },
+    { name = "packaging" },
+    { name = "pandas" },
+    { name = "requests" },
+    { name = "tabulate" },
+    { name = "urllib3" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/4f/a1/ce3aee11d3fabee21960cf2ee0b67698079ce12970f02f90fffbe6e3796c/ibm_watsonx_ai-1.3.39.tar.gz", hash = "sha256:357a7d823948655035e4de6265519bf6e377a497f22ec2d26270a9327b71eb5a", size = 788146, upload-time = "2025-09-24T11:59:48.606Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/ab/fd/dd70433f5487d75de82a3658768f7fe31323779217dba05e9278f12b85cd/ibm_watsonx_ai-1.3.39-py3-none-any.whl", hash = "sha256:4f6b08efdd1c40f554a3d9e96cb798e8f86e8e03897765672d3b1850bfa20e00", size = 1203329, upload-time = "2025-09-24T11:59:46.956Z" },
+]
+
 [[package]]
 name = "identify"
 version = "2.6.14"
@@ -1860,6 +1962,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/01/16/f5a0135ccd968b480daad0e6ab34b0c7c5ba3bc447e5088152696140dcb3/jiter-0.10.0-cp313-cp313t-win_amd64.whl", hash = "sha256:d7bfed2fe1fe0e4dda6ef682cee888ba444b21e7a6553e03252e4feb6cf0adca", size = 207278, upload-time = "2025-05-18T19:04:23.627Z" },
 ]
 
+[[package]]
+name = "jmespath"
+version = "1.0.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/00/2a/e867e8531cf3e36b41201936b7fa7ba7b5702dbef42922193f05c8976cd6/jmespath-1.0.1.tar.gz", hash = "sha256:90261b206d6defd58fdd5e85f478bf633a2901798906be2ad389150c5c60edbe", size = 25843, upload-time = "2022-06-17T18:00:12.224Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/31/b4/b9b800c45527aadd64d5b442f9b932b00648617eb5d63d2c7a6587b7cafc/jmespath-1.0.1-py3-none-any.whl", hash = "sha256:02e2e4cc71b5bcab88332eebf907519190dd9e6e82107fa7f83b1003a6252980", size = 20256, upload-time = "2022-06-17T18:00:10.251Z" },
+]
+
 [[package]]
 name = "json-repair"
 version = "0.25.2"
@@ -1890,6 +2001,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/68/32/290ca20eb3a2b97ffa6ba1791fcafacb3cd2f41f539c96eb54cfc3cfcf47/jsonlines-3.1.0-py3-none-any.whl", hash = "sha256:632f5e38f93dfcb1ac8c4e09780b92af3a55f38f26e7c47ae85109d420b6ad39", size = 8592, upload-time = "2022-07-01T16:38:02.082Z" },
 ]
 
+[[package]]
+name = "jsonpatch"
+version = "1.33"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "jsonpointer" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/42/78/18813351fe5d63acad16aec57f94ec2b70a09e53ca98145589e185423873/jsonpatch-1.33.tar.gz", hash = "sha256:9fcd4009c41e6d12348b4a0ff2563ba56a2923a7dfee731d004e212e1ee5030c", size = 21699, upload-time = "2023-06-26T12:07:29.144Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/73/07/02e16ed01e04a374e644b575638ec7987ae846d25ad97bcc9945a3ee4b0e/jsonpatch-1.33-py2.py3-none-any.whl", hash = "sha256:0ae28c0cd062bbd8b8ecc26d7d164fbbea9652a1a3693f3b956c1eae5145dade", size = 12898, upload-time = "2023-06-16T21:01:28.466Z" },
+]
+
 [[package]]
 name = "jsonpickle"
 version = "4.1.1"
@@ -1899,6 +2022,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/c1/73/04df8a6fa66d43a9fd45c30f283cc4afff17da671886e451d52af60bdc7e/jsonpickle-4.1.1-py3-none-any.whl", hash = "sha256:bb141da6057898aa2438ff268362b126826c812a1721e31cf08a6e142910dc91", size = 47125, upload-time = "2025-06-02T20:36:08.647Z" },
 ]
 
+[[package]]
+name = "jsonpointer"
+version = "3.0.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/6a/0a/eebeb1fa92507ea94016a2a790b93c2ae41a7e18778f85471dc54475ed25/jsonpointer-3.0.0.tar.gz", hash = "sha256:2b2d729f2091522d61c3b31f82e11870f60b68f43fbc705cb76bf4b832af59ef", size = 9114, upload-time = "2024-06-10T19:24:42.462Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/71/92/5e77f98553e9e75130c78900d000368476aed74276eb8ae8796f65f00918/jsonpointer-3.0.0-py2.py3-none-any.whl", hash = "sha256:13e088adc14fca8b6aa8177c044e12701e6ad4b28ff10e65f2267a90109c9942", size = 7595, upload-time = "2024-06-10T19:24:40.698Z" },
+]
+
 [[package]]
 name = "jsonref"
 version = "1.1.0"
@@ -2012,6 +2144,54 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/0d/fb/dce4757f257cb4e11e13b71ce502dc5d1caf51f1e5cccfdae85bf23960a0/lancedb-0.25.1-cp39-abi3-win_amd64.whl", hash = "sha256:2c6effc10c8263ea84261f49d5ff1957c18814ed7e3eaa5094d71b1aa0573871", size = 38390878, upload-time = "2025-09-23T22:55:24.687Z" },
 ]
 
+[[package]]
+name = "langchain-core"
+version = "0.3.76"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "jsonpatch" },
+    { name = "langsmith" },
+    { name = "packaging" },
+    { name = "pydantic" },
+    { name = "pyyaml" },
+    { name = "tenacity" },
+    { name = "typing-extensions" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/4f/4d/5e2ea7754ee0a1f524c412801c6ba9ad49318ecb58b0d524903c3d9efe0a/langchain_core-0.3.76.tar.gz", hash = "sha256:71136a122dd1abae2c289c5809d035cf12b5f2bb682d8a4c1078cd94feae7419", size = 573568, upload-time = "2025-09-10T14:49:39.863Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/77/b5/501c0ffcb09c734457ceaa86bc7b1dd37b6a261147bd653add03b838aacb/langchain_core-0.3.76-py3-none-any.whl", hash = "sha256:46e0eb48c7ac532432d51f8ca1ece1804c82afe9ae3dcf027b867edadf82b3ec", size = 447508, upload-time = "2025-09-10T14:49:38.179Z" },
+]
+
+[[package]]
+name = "langchain-text-splitters"
+version = "0.3.11"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "langchain-core" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/11/43/dcda8fd25f0b19cb2835f2f6bb67f26ad58634f04ac2d8eae00526b0fa55/langchain_text_splitters-0.3.11.tar.gz", hash = "sha256:7a50a04ada9a133bbabb80731df7f6ddac51bc9f1b9cab7fa09304d71d38a6cc", size = 46458, upload-time = "2025-08-31T23:02:58.316Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/58/0d/41a51b40d24ff0384ec4f7ab8dd3dcea8353c05c973836b5e289f1465d4f/langchain_text_splitters-0.3.11-py3-none-any.whl", hash = "sha256:cf079131166a487f1372c8ab5d0bfaa6c0a4291733d9c43a34a16ac9bcd6a393", size = 33845, upload-time = "2025-08-31T23:02:57.195Z" },
+]
+
+[[package]]
+name = "langsmith"
+version = "0.4.31"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "httpx" },
+    { name = "orjson", marker = "platform_python_implementation != 'PyPy'" },
+    { name = "packaging" },
+    { name = "pydantic" },
+    { name = "requests" },
+    { name = "requests-toolbelt" },
+    { name = "zstandard" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/55/f5/edbdf89a162ee025348b3b2080fb3b88f4a1040a5a186f32d34aca913994/langsmith-0.4.31.tar.gz", hash = "sha256:5fb3729e22bd9a225391936cb9d1080322e6c375bb776514af06b56d6c46ed3e", size = 959698, upload-time = "2025-09-25T04:18:19.55Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/3e/8e/e7a43d907a147e1f87eebdd6737483f9feba52a5d4b20f69d0bd6f2fa22f/langsmith-0.4.31-py3-none-any.whl", hash = "sha256:64f340bdead21defe5f4a6ca330c11073e35444989169f669508edf45a19025f", size = 386347, upload-time = "2025-09-25T04:18:16.69Z" },
+]
+
 [[package]]
 name = "latex2mathml"
 version = "3.78.1"
@@ -2068,6 +2248,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/0c/29/0348de65b8cc732daa3e33e67806420b2ae89bdce2b04af740289c5c6c8c/loguru-0.7.3-py3-none-any.whl", hash = "sha256:31a33c10c8e1e10422bfd431aeb5d351c7cf7fa671e3c4df004162264b28220c", size = 61595, upload-time = "2024-12-06T11:20:54.538Z" },
 ]
 
+[[package]]
+name = "lomond"
+version = "0.3.3"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "six" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/c0/9e/ef7813c910d4a893f2bc763ce9246269f55cc68db21dc1327e376d6a2d02/lomond-0.3.3.tar.gz", hash = "sha256:427936596b144b4ec387ead99aac1560b77c8a78107d3d49415d3abbe79acbd3", size = 28789, upload-time = "2018-09-21T15:17:43.297Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/0f/b1/02eebed49c754b01b17de7705caa8c4ceecfb4f926cdafc220c863584360/lomond-0.3.3-py2.py3-none-any.whl", hash = "sha256:df1dd4dd7b802a12b71907ab1abb08b8ce9950195311207579379eb3b1553de7", size = 35512, upload-time = "2018-09-21T15:17:38.686Z" },
+]
+
 [[package]]
 name = "lxml"
 version = "5.4.0"
@@ -3245,7 +3437,7 @@ wheels = [
 
 [[package]]
 name = "pandas"
-version = "2.3.2"
+version = "2.2.3"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.11'" },
@@ -3254,42 +3446,42 @@ dependencies = [
     { name = "pytz" },
     { name = "tzdata" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/79/8e/0e90233ac205ad182bd6b422532695d2b9414944a280488105d598c70023/pandas-2.3.2.tar.gz", hash = "sha256:ab7b58f8f82706890924ccdfb5f48002b83d2b5a3845976a9fb705d36c34dcdb", size = 4488684, upload-time = "2025-08-21T10:28:29.257Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/9c/d6/9f8431bacc2e19dca897724cd097b1bb224a6ad5433784a44b587c7c13af/pandas-2.2.3.tar.gz", hash = "sha256:4f18ba62b61d7e192368b84517265a99b4d7ee8912f8708660fb4a366cc82667", size = 4399213, upload-time = "2024-09-20T13:10:04.827Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/2e/16/a8eeb70aad84ccbf14076793f90e0031eded63c1899aeae9fdfbf37881f4/pandas-2.3.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:52bc29a946304c360561974c6542d1dd628ddafa69134a7131fdfd6a5d7a1a35", size = 11539648, upload-time = "2025-08-21T10:26:36.236Z" },
+    { url = "https://files.pythonhosted.org/packages/aa/70/c853aec59839bceed032d52010ff5f1b8d87dc3114b762e4ba2727661a3b/pandas-2.2.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:1948ddde24197a0f7add2bdc4ca83bf2b1ef84a1bc8ccffd95eda17fd836ecb5", size = 12580827, upload-time = "2024-09-20T13:08:42.347Z" },
-    { url = "https://files.pythonhosted.org/packages/47/f1/c5bdaea13bf3708554d93e948b7ea74121ce6e0d59537ca4c4f77731072b/pandas-2.3.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:220cc5c35ffaa764dd5bb17cf42df283b5cb7fdf49e10a7b053a06c9cb48ee2b", size = 10786923, upload-time = "2025-08-21T10:26:40.518Z" },
+    { url = "https://files.pythonhosted.org/packages/99/f2/c4527768739ffa4469b2b4fff05aa3768a478aed89a2f271a79a40eee984/pandas-2.2.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:381175499d3802cde0eabbaf6324cce0c4f5d52ca6f8c377c29ad442f50f6348", size = 11303897, upload-time = "2024-09-20T13:08:45.807Z" },
-    { url = "https://files.pythonhosted.org/packages/bb/10/811fa01476d29ffed692e735825516ad0e56d925961819e6126b4ba32147/pandas-2.3.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:42c05e15111221384019897df20c6fe893b2f697d03c811ee67ec9e0bb5a3424", size = 11726241, upload-time = "2025-08-21T10:26:43.175Z" },
+    { url = "https://files.pythonhosted.org/packages/ed/12/86c1747ea27989d7a4064f806ce2bae2c6d575b950be087837bdfcabacc9/pandas-2.2.3-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:d9c45366def9a3dd85a6454c0e7908f2b3b8e9c138f5dc38fed7ce720d8453ed", size = 66480908, upload-time = "2024-09-20T18:37:13.513Z" },
-    { url = "https://files.pythonhosted.org/packages/c4/6a/40b043b06e08df1ea1b6d20f0e0c2f2c4ec8c4f07d1c92948273d943a50b/pandas-2.3.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cc03acc273c5515ab69f898df99d9d4f12c4d70dbfc24c3acc6203751d0804cf", size = 12349533, upload-time = "2025-08-21T10:26:46.611Z" },
+    { url = "https://files.pythonhosted.org/packages/44/50/7db2cd5e6373ae796f0ddad3675268c8d59fb6076e66f0c339d61cea886b/pandas-2.2.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:86976a1c5b25ae3f8ccae3a5306e443569ee3c3faf444dfd0f41cda24667ad57", size = 13064210, upload-time = "2024-09-20T13:08:48.325Z" },
-    { url = "https://files.pythonhosted.org/packages/e2/ea/2e081a2302e41a9bca7056659fdd2b85ef94923723e41665b42d65afd347/pandas-2.3.2-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:d25c20a03e8870f6339bcf67281b946bd20b86f1a544ebbebb87e66a8d642cba", size = 13202407, upload-time = "2025-08-21T10:26:49.068Z" },
+    { url = "https://files.pythonhosted.org/packages/61/61/a89015a6d5536cb0d6c3ba02cebed51a95538cf83472975275e28ebf7d0c/pandas-2.2.3-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:b8661b0238a69d7aafe156b7fa86c44b881387509653fdf857bebc5e4008ad42", size = 16754292, upload-time = "2024-09-20T19:01:54.443Z" },
-    { url = "https://files.pythonhosted.org/packages/f4/12/7ff9f6a79e2ee8869dcf70741ef998b97ea20050fe25f83dc759764c1e32/pandas-2.3.2-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:21bb612d148bb5860b7eb2c10faacf1a810799245afd342cf297d7551513fbb6", size = 13837212, upload-time = "2025-08-21T10:26:51.832Z" },
+    { url = "https://files.pythonhosted.org/packages/ce/0d/4cc7b69ce37fac07645a94e1d4b0880b15999494372c1523508511b09e40/pandas-2.2.3-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:37e0aced3e8f539eccf2e099f65cdb9c8aa85109b0be6e93e2baff94264bdc6f", size = 14416379, upload-time = "2024-09-20T13:08:50.882Z" },
-    { url = "https://files.pythonhosted.org/packages/d8/df/5ab92fcd76455a632b3db34a746e1074d432c0cdbbd28d7cd1daba46a75d/pandas-2.3.2-cp310-cp310-win_amd64.whl", hash = "sha256:b62d586eb25cb8cb70a5746a378fc3194cb7f11ea77170d59f889f5dfe3cec7a", size = 11338099, upload-time = "2025-08-21T10:26:54.382Z" },
+    { url = "https://files.pythonhosted.org/packages/31/9e/6ebb433de864a6cd45716af52a4d7a8c3c9aaf3a98368e61db9e69e69a9c/pandas-2.2.3-cp310-cp310-win_amd64.whl", hash = "sha256:56534ce0746a58afaf7942ba4863e0ef81c9c50d3f0ae93e9497d6a41a057645", size = 11598471, upload-time = "2024-09-20T13:08:53.332Z" },
-    { url = "https://files.pythonhosted.org/packages/7a/59/f3e010879f118c2d400902d2d871c2226cef29b08c09fb8dc41111730400/pandas-2.3.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:1333e9c299adcbb68ee89a9bb568fc3f20f9cbb419f1dd5225071e6cddb2a743", size = 11563308, upload-time = "2025-08-21T10:26:56.656Z" },
+    { url = "https://files.pythonhosted.org/packages/a8/44/d9502bf0ed197ba9bf1103c9867d5904ddcaf869e52329787fc54ed70cc8/pandas-2.2.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:66108071e1b935240e74525006034333f98bcdb87ea116de573a6a0dccb6c039", size = 12602222, upload-time = "2024-09-20T13:08:56.254Z" },
-    { url = "https://files.pythonhosted.org/packages/38/18/48f10f1cc5c397af59571d638d211f494dba481f449c19adbd282aa8f4ca/pandas-2.3.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:76972bcbd7de8e91ad5f0ca884a9f2c477a2125354af624e022c49e5bd0dfff4", size = 10820319, upload-time = "2025-08-21T10:26:59.162Z" },
+    { url = "https://files.pythonhosted.org/packages/52/11/9eac327a38834f162b8250aab32a6781339c69afe7574368fffe46387edf/pandas-2.2.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:7c2875855b0ff77b2a64a0365e24455d9990730d6431b9e0ee18ad8acee13dbd", size = 11321274, upload-time = "2024-09-20T13:08:58.645Z" },
-    { url = "https://files.pythonhosted.org/packages/95/3b/1e9b69632898b048e223834cd9702052bcf06b15e1ae716eda3196fb972e/pandas-2.3.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b98bdd7c456a05eef7cd21fd6b29e3ca243591fe531c62be94a2cc987efb5ac2", size = 11790097, upload-time = "2025-08-21T10:27:02.204Z" },
+    { url = "https://files.pythonhosted.org/packages/45/fb/c4beeb084718598ba19aa9f5abbc8aed8b42f90930da861fcb1acdb54c3a/pandas-2.2.3-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:cd8d0c3be0515c12fed0bdbae072551c8b54b7192c7b1fda0ba56059a0179698", size = 15579836, upload-time = "2024-09-20T19:01:57.571Z" },
-    { url = "https://files.pythonhosted.org/packages/8b/ef/0e2ffb30b1f7fbc9a588bd01e3c14a0d96854d09a887e15e30cc19961227/pandas-2.3.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1d81573b3f7db40d020983f78721e9bfc425f411e616ef019a10ebf597aedb2e", size = 12397958, upload-time = "2025-08-21T10:27:05.409Z" },
+    { url = "https://files.pythonhosted.org/packages/cd/5f/4dba1d39bb9c38d574a9a22548c540177f78ea47b32f99c0ff2ec499fac5/pandas-2.2.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c124333816c3a9b03fbeef3a9f230ba9a737e9e5bb4060aa2107a86cc0a497fc", size = 13058505, upload-time = "2024-09-20T13:09:01.501Z" },
-    { url = "https://files.pythonhosted.org/packages/23/82/e6b85f0d92e9afb0e7f705a51d1399b79c7380c19687bfbf3d2837743249/pandas-2.3.2-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:e190b738675a73b581736cc8ec71ae113d6c3768d0bd18bffa5b9a0927b0b6ea", size = 13225600, upload-time = "2025-08-21T10:27:07.791Z" },
+    { url = "https://files.pythonhosted.org/packages/b9/57/708135b90391995361636634df1f1130d03ba456e95bcf576fada459115a/pandas-2.2.3-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:63cc132e40a2e084cf01adf0775b15ac515ba905d7dcca47e9a251819c575ef3", size = 16744420, upload-time = "2024-09-20T19:02:00.678Z" },
-    { url = "https://files.pythonhosted.org/packages/e8/f1/f682015893d9ed51611948bd83683670842286a8edd4f68c2c1c3b231eef/pandas-2.3.2-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:c253828cb08f47488d60f43c5fc95114c771bbfff085da54bfc79cb4f9e3a372", size = 13879433, upload-time = "2025-08-21T10:27:10.347Z" },
+    { url = "https://files.pythonhosted.org/packages/86/4a/03ed6b7ee323cf30404265c284cee9c65c56a212e0a08d9ee06984ba2240/pandas-2.2.3-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:29401dbfa9ad77319367d36940cd8a0b3a11aba16063e39632d98b0e931ddf32", size = 14440457, upload-time = "2024-09-20T13:09:04.105Z" },
-    { url = "https://files.pythonhosted.org/packages/a7/e7/ae86261695b6c8a36d6a4c8d5f9b9ede8248510d689a2f379a18354b37d7/pandas-2.3.2-cp311-cp311-win_amd64.whl", hash = "sha256:9467697b8083f9667b212633ad6aa4ab32436dcbaf4cd57325debb0ddef2012f", size = 11336557, upload-time = "2025-08-21T10:27:12.983Z" },
+    { url = "https://files.pythonhosted.org/packages/ed/8c/87ddf1fcb55d11f9f847e3c69bb1c6f8e46e2f40ab1a2d2abadb2401b007/pandas-2.2.3-cp311-cp311-win_amd64.whl", hash = "sha256:3fc6873a41186404dad67245896a6e440baacc92f5b716ccd1bc9ed2995ab2c5", size = 11617166, upload-time = "2024-09-20T13:09:06.917Z" },
-    { url = "https://files.pythonhosted.org/packages/ec/db/614c20fb7a85a14828edd23f1c02db58a30abf3ce76f38806155d160313c/pandas-2.3.2-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:3fbb977f802156e7a3f829e9d1d5398f6192375a3e2d1a9ee0803e35fe70a2b9", size = 11587652, upload-time = "2025-08-21T10:27:15.888Z" },
+    { url = "https://files.pythonhosted.org/packages/17/a3/fb2734118db0af37ea7433f57f722c0a56687e14b14690edff0cdb4b7e58/pandas-2.2.3-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:b1d432e8d08679a40e2a6d8b2f9770a5c21793a6f9f47fdd52c5ce1948a5a8a9", size = 12529893, upload-time = "2024-09-20T13:09:09.655Z" },
-    { url = "https://files.pythonhosted.org/packages/99/b0/756e52f6582cade5e746f19bad0517ff27ba9c73404607c0306585c201b3/pandas-2.3.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:1b9b52693123dd234b7c985c68b709b0b009f4521000d0525f2b95c22f15944b", size = 10717686, upload-time = "2025-08-21T10:27:18.486Z" },
+    { url = "https://files.pythonhosted.org/packages/e1/0c/ad295fd74bfac85358fd579e271cded3ac969de81f62dd0142c426b9da91/pandas-2.2.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:a5a1595fe639f5988ba6a8e5bc9649af3baf26df3998a0abe56c02609392e0a4", size = 11363475, upload-time = "2024-09-20T13:09:14.718Z" },
-    { url = "https://files.pythonhosted.org/packages/37/4c/dd5ccc1e357abfeee8353123282de17997f90ff67855f86154e5a13b81e5/pandas-2.3.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0bd281310d4f412733f319a5bc552f86d62cddc5f51d2e392c8787335c994175", size = 11278722, upload-time = "2025-08-21T10:27:21.149Z" },
+    { url = "https://files.pythonhosted.org/packages/c6/2a/4bba3f03f7d07207481fed47f5b35f556c7441acddc368ec43d6643c5777/pandas-2.2.3-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:5de54125a92bb4d1c051c0659e6fcb75256bf799a732a87184e5ea503965bce3", size = 15188645, upload-time = "2024-09-20T19:02:03.88Z" },
-    { url = "https://files.pythonhosted.org/packages/d3/a4/f7edcfa47e0a88cda0be8b068a5bae710bf264f867edfdf7b71584ace362/pandas-2.3.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:96d31a6b4354e3b9b8a2c848af75d31da390657e3ac6f30c05c82068b9ed79b9", size = 11987803, upload-time = "2025-08-21T10:27:23.767Z" },
+    { url = "https://files.pythonhosted.org/packages/38/f8/d8fddee9ed0d0c0f4a2132c1dfcf0e3e53265055da8df952a53e7eaf178c/pandas-2.2.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fffb8ae78d8af97f849404f21411c95062db1496aeb3e56f146f0355c9989319", size = 12739445, upload-time = "2024-09-20T13:09:17.621Z" },
-    { url = "https://files.pythonhosted.org/packages/f6/61/1bce4129f93ab66f1c68b7ed1c12bac6a70b1b56c5dab359c6bbcd480b52/pandas-2.3.2-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:df4df0b9d02bb873a106971bb85d448378ef14b86ba96f035f50bbd3688456b4", size = 12766345, upload-time = "2025-08-21T10:27:26.6Z" },
+    { url = "https://files.pythonhosted.org/packages/20/e8/45a05d9c39d2cea61ab175dbe6a2de1d05b679e8de2011da4ee190d7e748/pandas-2.2.3-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:6dfcb5ee8d4d50c06a51c2fffa6cff6272098ad6540aed1a76d15fb9318194d8", size = 16359235, upload-time = "2024-09-20T19:02:07.094Z" },
-    { url = "https://files.pythonhosted.org/packages/8e/46/80d53de70fee835531da3a1dae827a1e76e77a43ad22a8cd0f8142b61587/pandas-2.3.2-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:213a5adf93d020b74327cb2c1b842884dbdd37f895f42dcc2f09d451d949f811", size = 13439314, upload-time = "2025-08-21T10:27:29.213Z" },
+    { url = "https://files.pythonhosted.org/packages/1d/99/617d07a6a5e429ff90c90da64d428516605a1ec7d7bea494235e1c3882de/pandas-2.2.3-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:062309c1b9ea12a50e8ce661145c6aab431b1e99530d3cd60640e255778bd43a", size = 14056756, upload-time = "2024-09-20T13:09:20.474Z" },
-    { url = "https://files.pythonhosted.org/packages/28/30/8114832daff7489f179971dbc1d854109b7f4365a546e3ea75b6516cea95/pandas-2.3.2-cp312-cp312-win_amd64.whl", hash = "sha256:8c13b81a9347eb8c7548f53fd9a4f08d4dfe996836543f805c987bafa03317ae", size = 10983326, upload-time = "2025-08-21T10:27:31.901Z" },
+    { url = "https://files.pythonhosted.org/packages/29/d4/1244ab8edf173a10fd601f7e13b9566c1b525c4f365d6bee918e68381889/pandas-2.2.3-cp312-cp312-win_amd64.whl", hash = "sha256:59ef3764d0fe818125a5097d2ae867ca3fa64df032331b7e0917cf5d7bf66b13", size = 11504248, upload-time = "2024-09-20T13:09:23.137Z" },
-    { url = "https://files.pythonhosted.org/packages/27/64/a2f7bf678af502e16b472527735d168b22b7824e45a4d7e96a4fbb634b59/pandas-2.3.2-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:0c6ecbac99a354a051ef21c5307601093cb9e0f4b1855984a084bfec9302699e", size = 11531061, upload-time = "2025-08-21T10:27:34.647Z" },
+    { url = "https://files.pythonhosted.org/packages/64/22/3b8f4e0ed70644e85cfdcd57454686b9057c6c38d2f74fe4b8bc2527214a/pandas-2.2.3-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:f00d1345d84d8c86a63e476bb4955e46458b304b9575dcf71102b5c705320015", size = 12477643, upload-time = "2024-09-20T13:09:25.522Z" },
-    { url = "https://files.pythonhosted.org/packages/54/4c/c3d21b2b7769ef2f4c2b9299fcadd601efa6729f1357a8dbce8dd949ed70/pandas-2.3.2-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:c6f048aa0fd080d6a06cc7e7537c09b53be6642d330ac6f54a600c3ace857ee9", size = 10668666, upload-time = "2025-08-21T10:27:37.203Z" },
+    { url = "https://files.pythonhosted.org/packages/e4/93/b3f5d1838500e22c8d793625da672f3eec046b1a99257666c94446969282/pandas-2.2.3-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:3508d914817e153ad359d7e069d752cdd736a247c322d932eb89e6bc84217f28", size = 11281573, upload-time = "2024-09-20T13:09:28.012Z" },
-    { url = "https://files.pythonhosted.org/packages/50/e2/f775ba76ecfb3424d7f5862620841cf0edb592e9abd2d2a5387d305fe7a8/pandas-2.3.2-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0064187b80a5be6f2f9c9d6bdde29372468751dfa89f4211a3c5871854cfbf7a", size = 11332835, upload-time = "2025-08-21T10:27:40.188Z" },
+    { url = "https://files.pythonhosted.org/packages/f5/94/6c79b07f0e5aab1dcfa35a75f4817f5c4f677931d4234afcd75f0e6a66ca/pandas-2.2.3-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:22a9d949bfc9a502d320aa04e5d02feab689d61da4e7764b62c30b991c42c5f0", size = 15196085, upload-time = "2024-09-20T19:02:10.451Z" },
-    { url = "https://files.pythonhosted.org/packages/8f/52/0634adaace9be2d8cac9ef78f05c47f3a675882e068438b9d7ec7ef0c13f/pandas-2.3.2-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4ac8c320bded4718b298281339c1a50fb00a6ba78cb2a63521c39bec95b0209b", size = 12057211, upload-time = "2025-08-21T10:27:43.117Z" },
+    { url = "https://files.pythonhosted.org/packages/e8/31/aa8da88ca0eadbabd0a639788a6da13bb2ff6edbbb9f29aa786450a30a91/pandas-2.2.3-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f3a255b2c19987fbbe62a9dfd6cff7ff2aa9ccab3fc75218fd4b7530f01efa24", size = 12711809, upload-time = "2024-09-20T13:09:30.814Z" },
-    { url = "https://files.pythonhosted.org/packages/0b/9d/2df913f14b2deb9c748975fdb2491da1a78773debb25abbc7cbc67c6b549/pandas-2.3.2-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:114c2fe4f4328cf98ce5716d1532f3ab79c5919f95a9cfee81d9140064a2e4d6", size = 12749277, upload-time = "2025-08-21T10:27:45.474Z" },
+    { url = "https://files.pythonhosted.org/packages/ee/7c/c6dbdb0cb2a4344cacfb8de1c5808ca885b2e4dcfde8008266608f9372af/pandas-2.2.3-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:800250ecdadb6d9c78eae4990da62743b857b470883fa27f652db8bdde7f6659", size = 16356316, upload-time = "2024-09-20T19:02:13.825Z" },
-    { url = "https://files.pythonhosted.org/packages/87/af/da1a2417026bd14d98c236dba88e39837182459d29dcfcea510b2ac9e8a1/pandas-2.3.2-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:48fa91c4dfb3b2b9bfdb5c24cd3567575f4e13f9636810462ffed8925352be5a", size = 13415256, upload-time = "2025-08-21T10:27:49.885Z" },
+    { url = "https://files.pythonhosted.org/packages/57/b7/8b757e7d92023b832869fa8881a992696a0bfe2e26f72c9ae9f255988d42/pandas-2.2.3-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:6374c452ff3ec675a8f46fd9ab25c4ad0ba590b71cf0656f8b6daa5202bca3fb", size = 14022055, upload-time = "2024-09-20T13:09:33.462Z" },
-    { url = "https://files.pythonhosted.org/packages/22/3c/f2af1ce8840ef648584a6156489636b5692c162771918aa95707c165ad2b/pandas-2.3.2-cp313-cp313-win_amd64.whl", hash = "sha256:12d039facec710f7ba305786837d0225a3444af7bbd9c15c32ca2d40d157ed8b", size = 10982579, upload-time = "2025-08-21T10:28:08.435Z" },
+    { url = "https://files.pythonhosted.org/packages/3b/bc/4b18e2b8c002572c5a441a64826252ce5da2aa738855747247a971988043/pandas-2.2.3-cp313-cp313-win_amd64.whl", hash = "sha256:61c5ad4043f791b61dd4752191d9f07f0ae412515d59ba8f005832a532f8736d", size = 11481175, upload-time = "2024-09-20T13:09:35.871Z" },
-    { url = "https://files.pythonhosted.org/packages/f3/98/8df69c4097a6719e357dc249bf437b8efbde808038268e584421696cbddf/pandas-2.3.2-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:c624b615ce97864eb588779ed4046186f967374185c047070545253a52ab2d57", size = 12028163, upload-time = "2025-08-21T10:27:52.232Z" },
+    { url = "https://files.pythonhosted.org/packages/76/a3/a5d88146815e972d40d19247b2c162e88213ef51c7c25993942c39dbf41d/pandas-2.2.3-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:3b71f27954685ee685317063bf13c7709a7ba74fc996b84fc6821c59b0f06468", size = 12615650, upload-time = "2024-09-20T13:09:38.685Z" },
-    { url = "https://files.pythonhosted.org/packages/0e/23/f95cbcbea319f349e10ff90db488b905c6883f03cbabd34f6b03cbc3c044/pandas-2.3.2-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:0cee69d583b9b128823d9514171cabb6861e09409af805b54459bd0c821a35c2", size = 11391860, upload-time = "2025-08-21T10:27:54.673Z" },
+    { url = "https://files.pythonhosted.org/packages/9c/8c/f0fd18f6140ddafc0c24122c8a964e48294acc579d47def376fef12bcb4a/pandas-2.2.3-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:38cf8125c40dae9d5acc10fa66af8ea6fdf760b2714ee482ca691fc66e6fcb18", size = 11290177, upload-time = "2024-09-20T13:09:41.141Z" },
-    { url = "https://files.pythonhosted.org/packages/ad/1b/6a984e98c4abee22058aa75bfb8eb90dce58cf8d7296f8bc56c14bc330b0/pandas-2.3.2-cp313-cp313t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2319656ed81124982900b4c37f0e0c58c015af9a7bbc62342ba5ad07ace82ba9", size = 11309830, upload-time = "2025-08-21T10:27:56.957Z" },
+    { url = "https://files.pythonhosted.org/packages/ed/f9/e995754eab9c0f14c6777401f7eece0943840b7a9fc932221c19d1abee9f/pandas-2.2.3-cp313-cp313t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:ba96630bc17c875161df3818780af30e43be9b166ce51c9a18c1feae342906c2", size = 14651526, upload-time = "2024-09-20T19:02:16.905Z" },
-    { url = "https://files.pythonhosted.org/packages/15/d5/f0486090eb18dd8710bf60afeaf638ba6817047c0c8ae5c6a25598665609/pandas-2.3.2-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b37205ad6f00d52f16b6d09f406434ba928c1a1966e2771006a9033c736d30d2", size = 11883216, upload-time = "2025-08-21T10:27:59.302Z" },
+    { url = "https://files.pythonhosted.org/packages/25/b0/98d6ae2e1abac4f35230aa756005e8654649d305df9a28b16b9ae4353bff/pandas-2.2.3-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1db71525a1538b30142094edb9adc10be3f3e176748cd7acc2240c2f2e5aa3a4", size = 11871013, upload-time = "2024-09-20T13:09:44.39Z" },
-    { url = "https://files.pythonhosted.org/packages/10/86/692050c119696da19e20245bbd650d8dfca6ceb577da027c3a73c62a047e/pandas-2.3.2-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:837248b4fc3a9b83b9c6214699a13f069dc13510a6a6d7f9ba33145d2841a012", size = 12699743, upload-time = "2025-08-21T10:28:02.447Z" },
+    { url = "https://files.pythonhosted.org/packages/cc/57/0f72a10f9db6a4628744c8e8f0df4e6e21de01212c7c981d31e50ffc8328/pandas-2.2.3-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:15c0e1e02e93116177d29ff83e8b1619c93ddc9c49083f237d4312337a61165d", size = 15711620, upload-time = "2024-09-20T19:02:20.639Z" },
-    { url = "https://files.pythonhosted.org/packages/cd/d7/612123674d7b17cf345aad0a10289b2a384bff404e0463a83c4a3a59d205/pandas-2.3.2-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:d2c3554bd31b731cd6490d94a28f3abb8dd770634a9e06eb6d2911b9827db370", size = 13186141, upload-time = "2025-08-21T10:28:05.377Z" },
+    { url = "https://files.pythonhosted.org/packages/ab/5f/b38085618b950b79d2d9164a711c52b10aefc0ae6833b96f626b7021b2ed/pandas-2.2.3-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:ad5b65698ab28ed8d7f18790a0dc58005c7629f227be9ecc1072aa74c0c1d43a", size = 13098436, upload-time = "2024-09-20T13:09:48.112Z" },
 ]
 
 [[package]]
@@ -4530,6 +4722,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/3b/5d/63d4ae3b9daea098d5d6f5da83984853c1bbacd5dc826764b249fe119d24/requests_oauthlib-2.0.0-py2.py3-none-any.whl", hash = "sha256:7dd8a5c40426b779b0868c404bdef9768deccf22749cde15852df527e6269b36", size = 24179, upload-time = "2024-03-22T20:32:28.055Z" },
 ]
 
+[[package]]
+name = "requests-toolbelt"
+version = "1.0.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "requests" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/f3/61/d7545dafb7ac2230c70d38d31cbfe4cc64f7144dc41f6e4e4b78ecd9f5bb/requests-toolbelt-1.0.0.tar.gz", hash = "sha256:7681a0a3d047012b5bdc0ee37d7f8f07ebe76ab08caeccfc3921ce23c88d5bc6", size = 206888, upload-time = "2023-05-01T04:11:33.229Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/3f/51/d4db610ef29373b879047326cbf6fa98b6c1969d6f6dc423279de2b1be2c/requests_toolbelt-1.0.0-py2.py3-none-any.whl", hash = "sha256:cccfdd665f0a24fcf4726e690f65639d272bb0637b9b92dfd91a5568ccf6bd06", size = 54481, upload-time = "2023-05-01T04:11:28.427Z" },
+]
+
 [[package]]
 name = "rich"
 version = "14.1.0"
@@ -4703,6 +4907,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/fd/04/afc078a12cf68592345b1e2d6ecdff837d286bac023d7a22c54c7a698c5b/ruff-0.13.1-py3-none-win_arm64.whl", hash = "sha256:c0bae9ffd92d54e03c2bf266f466da0a65e145f298ee5b5846ed435f6a00518a", size = 12437893, upload-time = "2025-09-18T19:52:41.283Z" },
 ]
 
+[[package]]
+name = "s3transfer"
+version = "0.14.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "botocore" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/62/74/8d69dcb7a9efe8baa2046891735e5dfe433ad558ae23d9e3c14c633d1d58/s3transfer-0.14.0.tar.gz", hash = "sha256:eff12264e7c8b4985074ccce27a3b38a485bb7f7422cc8046fee9be4983e4125", size = 151547, upload-time = "2025-09-09T19:23:31.089Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/48/f0/ae7ca09223a81a1d890b2557186ea015f6e0502e9b8cb8e1813f1d8cfa4e/s3transfer-0.14.0-py3-none-any.whl", hash = "sha256:ea3b790c7077558ed1f02a3072fb3cb992bbbd253392f4b6e9e8976941c7d456", size = 85712, upload-time = "2025-09-09T19:23:30.041Z" },
+]
+
 [[package]]
 name = "safetensors"
 version = "0.6.2"
@@ -5746,6 +5962,27 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/76/06/04c8e804f813cf972e3262f3f8584c232de64f0cde9f703b46cf53a45090/virtualenv-20.34.0-py3-none-any.whl", hash = "sha256:341f5afa7eee943e4984a9207c025feedd768baff6753cd660c857ceb3e36026", size = 5983279, upload-time = "2025-08-13T14:24:05.111Z" },
 ]
 
+[[package]]
+name = "voyageai"
+version = "0.3.5"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "aiohttp" },
+    { name = "aiolimiter" },
+    { name = "langchain-text-splitters" },
+    { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.11'" },
+    { name = "numpy", version = "2.3.3", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.11'" },
+    { name = "pillow" },
+    { name = "pydantic" },
+    { name = "requests" },
+    { name = "tenacity" },
+    { name = "tokenizers" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/51/9b/e40f90793c1d03610b6109852791f752fcb257989a96701258278f874e00/voyageai-0.3.5.tar.gz", hash = "sha256:963e0d71611af529fa0e496db232a4f660b5f73bce7af1ab288a7f59df7512da", size = 20414, upload-time = "2025-09-11T00:28:26.29Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/8a/9d/709f5c7fc80a7bf11952fbccfca2bc5525bd5d345521795358819bd01d02/voyageai-0.3.5-py3-none-any.whl", hash = "sha256:1f70fcf3532d7e0bbc4332b1831a6fc1f714f268eeddc8b2859b81bf06a82411", size = 28257, upload-time = "2025-09-11T00:28:24.62Z" },
+]
+
 [[package]]
 name = "watchfiles"
 version = "1.1.0"
@@ -6090,3 +6327,78 @@ sdist = { url = "https://files.pythonhosted.org/packages/e3/02/0f2892c661036d50e
 wheels = [
     { url = "https://files.pythonhosted.org/packages/2e/54/647ade08bf0db230bfea292f893923872fd20be6ac6f53b2b936ba839d75/zipp-3.23.0-py3-none-any.whl", hash = "sha256:071652d6115ed432f5ce1d34c336c0adfd6a884660d1e9712a256d3d3bd4b14e", size = 10276, upload-time = "2025-06-08T17:06:38.034Z" },
 ]
+
+[[package]]
+name = "zstandard"
+version = "0.25.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/fd/aa/3e0508d5a5dd96529cdc5a97011299056e14c6505b678fd58938792794b1/zstandard-0.25.0.tar.gz", hash = "sha256:7713e1179d162cf5c7906da876ec2ccb9c3a9dcbdffef0cc7f70c3667a205f0b", size = 711513, upload-time = "2025-09-14T22:15:54.002Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/56/7a/28efd1d371f1acd037ac64ed1c5e2b41514a6cc937dd6ab6a13ab9f0702f/zstandard-0.25.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:e59fdc271772f6686e01e1b3b74537259800f57e24280be3f29c8a0deb1904dd", size = 795256, upload-time = "2025-09-14T22:15:56.415Z" },
+    { url = "https://files.pythonhosted.org/packages/96/34/ef34ef77f1ee38fc8e4f9775217a613b452916e633c4f1d98f31db52c4a5/zstandard-0.25.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:4d441506e9b372386a5271c64125f72d5df6d2a8e8a2a45a0ae09b03cb781ef7", size = 640565, upload-time = "2025-09-14T22:15:58.177Z" },
+    { url = "https://files.pythonhosted.org/packages/9d/1b/4fdb2c12eb58f31f28c4d28e8dc36611dd7205df8452e63f52fb6261d13e/zstandard-0.25.0-cp310-cp310-manylinux2010_i686.manylinux2014_i686.manylinux_2_12_i686.manylinux_2_17_i686.whl", hash = "sha256:ab85470ab54c2cb96e176f40342d9ed41e58ca5733be6a893b730e7af9c40550", size = 5345306, upload-time = "2025-09-14T22:16:00.165Z" },
+    { url = "https://files.pythonhosted.org/packages/73/28/a44bdece01bca027b079f0e00be3b6bd89a4df180071da59a3dd7381665b/zstandard-0.25.0-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:e05ab82ea7753354bb054b92e2f288afb750e6b439ff6ca78af52939ebbc476d", size = 5055561, upload-time = "2025-09-14T22:16:02.22Z" },
+    { url = "https://files.pythonhosted.org/packages/e9/74/68341185a4f32b274e0fc3410d5ad0750497e1acc20bd0f5b5f64ce17785/zstandard-0.25.0-cp310-cp310-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:78228d8a6a1c177a96b94f7e2e8d012c55f9c760761980da16ae7546a15a8e9b", size = 5402214, upload-time = "2025-09-14T22:16:04.109Z" },
+    { url = "https://files.pythonhosted.org/packages/8b/67/f92e64e748fd6aaffe01e2b75a083c0c4fd27abe1c8747fee4555fcee7dd/zstandard-0.25.0-cp310-cp310-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:2b6bd67528ee8b5c5f10255735abc21aa106931f0dbaf297c7be0c886353c3d0", size = 5449703, upload-time = "2025-09-14T22:16:06.312Z" },
+    { url = "https://files.pythonhosted.org/packages/fd/e5/6d36f92a197c3c17729a2125e29c169f460538a7d939a27eaaa6dcfcba8e/zstandard-0.25.0-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:4b6d83057e713ff235a12e73916b6d356e3084fd3d14ced499d84240f3eecee0", size = 5556583, upload-time = "2025-09-14T22:16:08.457Z" },
+    { url = "https://files.pythonhosted.org/packages/d7/83/41939e60d8d7ebfe2b747be022d0806953799140a702b90ffe214d557638/zstandard-0.25.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:9174f4ed06f790a6869b41cba05b43eeb9a35f8993c4422ab853b705e8112bbd", size = 5045332, upload-time = "2025-09-14T22:16:10.444Z" },
+    { url = "https://files.pythonhosted.org/packages/b3/87/d3ee185e3d1aa0133399893697ae91f221fda79deb61adbe998a7235c43f/zstandard-0.25.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:25f8f3cd45087d089aef5ba3848cd9efe3ad41163d3400862fb42f81a3a46701", size = 5572283, upload-time = "2025-09-14T22:16:12.128Z" },
+    { url = "https://files.pythonhosted.org/packages/0a/1d/58635ae6104df96671076ac7d4ae7816838ce7debd94aecf83e30b7121b0/zstandard-0.25.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:3756b3e9da9b83da1796f8809dd57cb024f838b9eeafde28f3cb472012797ac1", size = 4959754, upload-time = "2025-09-14T22:16:14.225Z" },
+    { url = "https://files.pythonhosted.org/packages/75/d6/57e9cb0a9983e9a229dd8fd2e6e96593ef2aa82a3907188436f22b111ccd/zstandard-0.25.0-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:81dad8d145d8fd981b2962b686b2241d3a1ea07733e76a2f15435dfb7fb60150", size = 5266477, upload-time = "2025-09-14T22:16:16.343Z" },
+    { url = "https://files.pythonhosted.org/packages/d1/a9/ee891e5edf33a6ebce0a028726f0bbd8567effe20fe3d5808c42323e8542/zstandard-0.25.0-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:a5a419712cf88862a45a23def0ae063686db3d324cec7edbe40509d1a79a0aab", size = 5440914, upload-time = "2025-09-14T22:16:18.453Z" },
+    { url = "https://files.pythonhosted.org/packages/58/08/a8522c28c08031a9521f27abc6f78dbdee7312a7463dd2cfc658b813323b/zstandard-0.25.0-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:e7360eae90809efd19b886e59a09dad07da4ca9ba096752e61a2e03c8aca188e", size = 5819847, upload-time = "2025-09-14T22:16:20.559Z" },
+    { url = "https://files.pythonhosted.org/packages/6f/11/4c91411805c3f7b6f31c60e78ce347ca48f6f16d552fc659af6ec3b73202/zstandard-0.25.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:75ffc32a569fb049499e63ce68c743155477610532da1eb38e7f24bf7cd29e74", size = 5363131, upload-time = "2025-09-14T22:16:22.206Z" },
+    { url = "https://files.pythonhosted.org/packages/ef/d6/8c4bd38a3b24c4c7676a7a3d8de85d6ee7a983602a734b9f9cdefb04a5d6/zstandard-0.25.0-cp310-cp310-win32.whl", hash = "sha256:106281ae350e494f4ac8a80470e66d1fe27e497052c8d9c3b95dc4cf1ade81aa", size = 436469, upload-time = "2025-09-14T22:16:25.002Z" },
+    { url = "https://files.pythonhosted.org/packages/93/90/96d50ad417a8ace5f841b3228e93d1bb13e6ad356737f42e2dde30d8bd68/zstandard-0.25.0-cp310-cp310-win_amd64.whl", hash = "sha256:ea9d54cc3d8064260114a0bbf3479fc4a98b21dffc89b3459edd506b69262f6e", size = 506100, upload-time = "2025-09-14T22:16:23.569Z" },
+    { url = "https://files.pythonhosted.org/packages/2a/83/c3ca27c363d104980f1c9cee1101cc8ba724ac8c28a033ede6aab89585b1/zstandard-0.25.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:933b65d7680ea337180733cf9e87293cc5500cc0eb3fc8769f4d3c88d724ec5c", size = 795254, upload-time = "2025-09-14T22:16:26.137Z" },
+    { url = "https://files.pythonhosted.org/packages/ac/4d/e66465c5411a7cf4866aeadc7d108081d8ceba9bc7abe6b14aa21c671ec3/zstandard-0.25.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:a3f79487c687b1fc69f19e487cd949bf3aae653d181dfb5fde3bf6d18894706f", size = 640559, upload-time = "2025-09-14T22:16:27.973Z" },
+    { url = "https://files.pythonhosted.org/packages/12/56/354fe655905f290d3b147b33fe946b0f27e791e4b50a5f004c802cb3eb7b/zstandard-0.25.0-cp311-cp311-manylinux2010_i686.manylinux2014_i686.manylinux_2_12_i686.manylinux_2_17_i686.whl", hash = "sha256:0bbc9a0c65ce0eea3c34a691e3c4b6889f5f3909ba4822ab385fab9057099431", size = 5348020, upload-time = "2025-09-14T22:16:29.523Z" },
+    { url = "https://files.pythonhosted.org/packages/3b/13/2b7ed68bd85e69a2069bcc72141d378f22cae5a0f3b353a2c8f50ef30c1b/zstandard-0.25.0-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:01582723b3ccd6939ab7b3a78622c573799d5d8737b534b86d0e06ac18dbde4a", size = 5058126, upload-time = "2025-09-14T22:16:31.811Z" },
+    { url = "https://files.pythonhosted.org/packages/c9/dd/fdaf0674f4b10d92cb120ccff58bbb6626bf8368f00ebfd2a41ba4a0dc99/zstandard-0.25.0-cp311-cp311-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:5f1ad7bf88535edcf30038f6919abe087f606f62c00a87d7e33e7fc57cb69fcc", size = 5405390, upload-time = "2025-09-14T22:16:33.486Z" },
+    { url = "https://files.pythonhosted.org/packages/0f/67/354d1555575bc2490435f90d67ca4dd65238ff2f119f30f72d5cde09c2ad/zstandard-0.25.0-cp311-cp311-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:06acb75eebeedb77b69048031282737717a63e71e4ae3f77cc0c3b9508320df6", size = 5452914, upload-time = "2025-09-14T22:16:35.277Z" },
+    { url = "https://files.pythonhosted.org/packages/bb/1f/e9cfd801a3f9190bf3e759c422bbfd2247db9d7f3d54a56ecde70137791a/zstandard-0.25.0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:9300d02ea7c6506f00e627e287e0492a5eb0371ec1670ae852fefffa6164b072", size = 5559635, upload-time = "2025-09-14T22:16:37.141Z" },
+    { url = "https://files.pythonhosted.org/packages/21/88/5ba550f797ca953a52d708c8e4f380959e7e3280af029e38fbf47b55916e/zstandard-0.25.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:bfd06b1c5584b657a2892a6014c2f4c20e0db0208c159148fa78c65f7e0b0277", size = 5048277, upload-time = "2025-09-14T22:16:38.807Z" },
+    { url = "https://files.pythonhosted.org/packages/46/c0/ca3e533b4fa03112facbe7fbe7779cb1ebec215688e5df576fe5429172e0/zstandard-0.25.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:f373da2c1757bb7f1acaf09369cdc1d51d84131e50d5fa9863982fd626466313", size = 5574377, upload-time = "2025-09-14T22:16:40.523Z" },
+    { url = "https://files.pythonhosted.org/packages/12/9b/3fb626390113f272abd0799fd677ea33d5fc3ec185e62e6be534493c4b60/zstandard-0.25.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:6c0e5a65158a7946e7a7affa6418878ef97ab66636f13353b8502d7ea03c8097", size = 4961493, upload-time = "2025-09-14T22:16:43.3Z" },
+    { url = "https://files.pythonhosted.org/packages/cb/d3/23094a6b6a4b1343b27ae68249daa17ae0651fcfec9ed4de09d14b940285/zstandard-0.25.0-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:c8e167d5adf59476fa3e37bee730890e389410c354771a62e3c076c86f9f7778", size = 5269018, upload-time = "2025-09-14T22:16:45.292Z" },
+    { url = "https://files.pythonhosted.org/packages/8c/a7/bb5a0c1c0f3f4b5e9d5b55198e39de91e04ba7c205cc46fcb0f95f0383c1/zstandard-0.25.0-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:98750a309eb2f020da61e727de7d7ba3c57c97cf6213f6f6277bb7fb42a8e065", size = 5443672, upload-time = "2025-09-14T22:16:47.076Z" },
+    { url = "https://files.pythonhosted.org/packages/27/22/503347aa08d073993f25109c36c8d9f029c7d5949198050962cb568dfa5e/zstandard-0.25.0-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:22a086cff1b6ceca18a8dd6096ec631e430e93a8e70a9ca5efa7561a00f826fa", size = 5822753, upload-time = "2025-09-14T22:16:49.316Z" },
+    { url = "https://files.pythonhosted.org/packages/e2/be/94267dc6ee64f0f8ba2b2ae7c7a2df934a816baaa7291db9e1aa77394c3c/zstandard-0.25.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:72d35d7aa0bba323965da807a462b0966c91608ef3a48ba761678cb20ce5d8b7", size = 5366047, upload-time = "2025-09-14T22:16:51.328Z" },
+    { url = "https://files.pythonhosted.org/packages/7b/a3/732893eab0a3a7aecff8b99052fecf9f605cf0fb5fb6d0290e36beee47a4/zstandard-0.25.0-cp311-cp311-win32.whl", hash = "sha256:f5aeea11ded7320a84dcdd62a3d95b5186834224a9e55b92ccae35d21a8b63d4", size = 436484, upload-time = "2025-09-14T22:16:55.005Z" },
+    { url = "https://files.pythonhosted.org/packages/43/a3/c6155f5c1cce691cb80dfd38627046e50af3ee9ddc5d0b45b9b063bfb8c9/zstandard-0.25.0-cp311-cp311-win_amd64.whl", hash = "sha256:daab68faadb847063d0c56f361a289c4f268706b598afbf9ad113cbe5c38b6b2", size = 506183, upload-time = "2025-09-14T22:16:52.753Z" },
+    { url = "https://files.pythonhosted.org/packages/8c/3e/8945ab86a0820cc0e0cdbf38086a92868a9172020fdab8a03ac19662b0e5/zstandard-0.25.0-cp311-cp311-win_arm64.whl", hash = "sha256:22a06c5df3751bb7dc67406f5374734ccee8ed37fc5981bf1ad7041831fa1137", size = 462533, upload-time = "2025-09-14T22:16:53.878Z" },
+    { url = "https://files.pythonhosted.org/packages/82/fc/f26eb6ef91ae723a03e16eddb198abcfce2bc5a42e224d44cc8b6765e57e/zstandard-0.25.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:7b3c3a3ab9daa3eed242d6ecceead93aebbb8f5f84318d82cee643e019c4b73b", size = 795738, upload-time = "2025-09-14T22:16:56.237Z" },
+    { url = "https://files.pythonhosted.org/packages/aa/1c/d920d64b22f8dd028a8b90e2d756e431a5d86194caa78e3819c7bf53b4b3/zstandard-0.25.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:913cbd31a400febff93b564a23e17c3ed2d56c064006f54efec210d586171c00", size = 640436, upload-time = "2025-09-14T22:16:57.774Z" },
+    { url = "https://files.pythonhosted.org/packages/53/6c/288c3f0bd9fcfe9ca41e2c2fbfd17b2097f6af57b62a81161941f09afa76/zstandard-0.25.0-cp312-cp312-manylinux2010_i686.manylinux2014_i686.manylinux_2_12_i686.manylinux_2_17_i686.whl", hash = "sha256:011d388c76b11a0c165374ce660ce2c8efa8e5d87f34996aa80f9c0816698b64", size = 5343019, upload-time = "2025-09-14T22:16:59.302Z" },
+    { url = "https://files.pythonhosted.org/packages/1e/15/efef5a2f204a64bdb5571e6161d49f7ef0fffdbca953a615efbec045f60f/zstandard-0.25.0-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:6dffecc361d079bb48d7caef5d673c88c8988d3d33fb74ab95b7ee6da42652ea", size = 5063012, upload-time = "2025-09-14T22:17:01.156Z" },
+    { url = "https://files.pythonhosted.org/packages/b7/37/a6ce629ffdb43959e92e87ebdaeebb5ac81c944b6a75c9c47e300f85abdf/zstandard-0.25.0-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:7149623bba7fdf7e7f24312953bcf73cae103db8cae49f8154dd1eadc8a29ecb", size = 5394148, upload-time = "2025-09-14T22:17:03.091Z" },
+    { url = "https://files.pythonhosted.org/packages/e3/79/2bf870b3abeb5c070fe2d670a5a8d1057a8270f125ef7676d29ea900f496/zstandard-0.25.0-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:6a573a35693e03cf1d67799fd01b50ff578515a8aeadd4595d2a7fa9f3ec002a", size = 5451652, upload-time = "2025-09-14T22:17:04.979Z" },
+    { url = "https://files.pythonhosted.org/packages/53/60/7be26e610767316c028a2cbedb9a3beabdbe33e2182c373f71a1c0b88f36/zstandard-0.25.0-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:5a56ba0db2d244117ed744dfa8f6f5b366e14148e00de44723413b2f3938a902", size = 5546993, upload-time = "2025-09-14T22:17:06.781Z" },
+    { url = "https://files.pythonhosted.org/packages/85/c7/3483ad9ff0662623f3648479b0380d2de5510abf00990468c286c6b04017/zstandard-0.25.0-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:10ef2a79ab8e2974e2075fb984e5b9806c64134810fac21576f0668e7ea19f8f", size = 5046806, upload-time = "2025-09-14T22:17:08.415Z" },
+    { url = "https://files.pythonhosted.org/packages/08/b3/206883dd25b8d1591a1caa44b54c2aad84badccf2f1de9e2d60a446f9a25/zstandard-0.25.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:aaf21ba8fb76d102b696781bddaa0954b782536446083ae3fdaa6f16b25a1c4b", size = 5576659, upload-time = "2025-09-14T22:17:10.164Z" },
+    { url = "https://files.pythonhosted.org/packages/9d/31/76c0779101453e6c117b0ff22565865c54f48f8bd807df2b00c2c404b8e0/zstandard-0.25.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:1869da9571d5e94a85a5e8d57e4e8807b175c9e4a6294e3b66fa4efb074d90f6", size = 4953933, upload-time = "2025-09-14T22:17:11.857Z" },
+    { url = "https://files.pythonhosted.org/packages/18/e1/97680c664a1bf9a247a280a053d98e251424af51f1b196c6d52f117c9720/zstandard-0.25.0-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:809c5bcb2c67cd0ed81e9229d227d4ca28f82d0f778fc5fea624a9def3963f91", size = 5268008, upload-time = "2025-09-14T22:17:13.627Z" },
+    { url = "https://files.pythonhosted.org/packages/1e/73/316e4010de585ac798e154e88fd81bb16afc5c5cb1a72eeb16dd37e8024a/zstandard-0.25.0-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:f27662e4f7dbf9f9c12391cb37b4c4c3cb90ffbd3b1fb9284dadbbb8935fa708", size = 5433517, upload-time = "2025-09-14T22:17:16.103Z" },
+    { url = "https://files.pythonhosted.org/packages/5b/60/dd0f8cfa8129c5a0ce3ea6b7f70be5b33d2618013a161e1ff26c2b39787c/zstandard-0.25.0-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:99c0c846e6e61718715a3c9437ccc625de26593fea60189567f0118dc9db7512", size = 5814292, upload-time = "2025-09-14T22:17:17.827Z" },
+    { url = "https://files.pythonhosted.org/packages/fc/5f/75aafd4b9d11b5407b641b8e41a57864097663699f23e9ad4dbb91dc6bfe/zstandard-0.25.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:474d2596a2dbc241a556e965fb76002c1ce655445e4e3bf38e5477d413165ffa", size = 5360237, upload-time = "2025-09-14T22:17:19.954Z" },
+    { url = "https://files.pythonhosted.org/packages/ff/8d/0309daffea4fcac7981021dbf21cdb2e3427a9e76bafbcdbdf5392ff99a4/zstandard-0.25.0-cp312-cp312-win32.whl", hash = "sha256:23ebc8f17a03133b4426bcc04aabd68f8236eb78c3760f12783385171b0fd8bd", size = 436922, upload-time = "2025-09-14T22:17:24.398Z" },
+    { url = "https://files.pythonhosted.org/packages/79/3b/fa54d9015f945330510cb5d0b0501e8253c127cca7ebe8ba46a965df18c5/zstandard-0.25.0-cp312-cp312-win_amd64.whl", hash = "sha256:ffef5a74088f1e09947aecf91011136665152e0b4b359c42be3373897fb39b01", size = 506276, upload-time = "2025-09-14T22:17:21.429Z" },
+    { url = "https://files.pythonhosted.org/packages/ea/6b/8b51697e5319b1f9ac71087b0af9a40d8a6288ff8025c36486e0c12abcc4/zstandard-0.25.0-cp312-cp312-win_arm64.whl", hash = "sha256:181eb40e0b6a29b3cd2849f825e0fa34397f649170673d385f3598ae17cca2e9", size = 462679, upload-time = "2025-09-14T22:17:23.147Z" },
+    { url = "https://files.pythonhosted.org/packages/35/0b/8df9c4ad06af91d39e94fa96cc010a24ac4ef1378d3efab9223cc8593d40/zstandard-0.25.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:ec996f12524f88e151c339688c3897194821d7f03081ab35d31d1e12ec975e94", size = 795735, upload-time = "2025-09-14T22:17:26.042Z" },
+    { url = "https://files.pythonhosted.org/packages/3f/06/9ae96a3e5dcfd119377ba33d4c42a7d89da1efabd5cb3e366b156c45ff4d/zstandard-0.25.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:a1a4ae2dec3993a32247995bdfe367fc3266da832d82f8438c8570f989753de1", size = 640440, upload-time = "2025-09-14T22:17:27.366Z" },
+    { url = "https://files.pythonhosted.org/packages/d9/14/933d27204c2bd404229c69f445862454dcc101cd69ef8c6068f15aaec12c/zstandard-0.25.0-cp313-cp313-manylinux2010_i686.manylinux2014_i686.manylinux_2_12_i686.manylinux_2_17_i686.whl", hash = "sha256:e96594a5537722fdfb79951672a2a63aec5ebfb823e7560586f7484819f2a08f", size = 5343070, upload-time = "2025-09-14T22:17:28.896Z" },
+    { url = "https://files.pythonhosted.org/packages/6d/db/ddb11011826ed7db9d0e485d13df79b58586bfdec56e5c84a928a9a78c1c/zstandard-0.25.0-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:bfc4e20784722098822e3eee42b8e576b379ed72cca4a7cb856ae733e62192ea", size = 5063001, upload-time = "2025-09-14T22:17:31.044Z" },
+    { url = "https://files.pythonhosted.org/packages/db/00/87466ea3f99599d02a5238498b87bf84a6348290c19571051839ca943777/zstandard-0.25.0-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:457ed498fc58cdc12fc48f7950e02740d4f7ae9493dd4ab2168a47c93c31298e", size = 5394120, upload-time = "2025-09-14T22:17:32.711Z" },
+    { url = "https://files.pythonhosted.org/packages/2b/95/fc5531d9c618a679a20ff6c29e2b3ef1d1f4ad66c5e161ae6ff847d102a9/zstandard-0.25.0-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:fd7a5004eb1980d3cefe26b2685bcb0b17989901a70a1040d1ac86f1d898c551", size = 5451230, upload-time = "2025-09-14T22:17:34.41Z" },
+    { url = "https://files.pythonhosted.org/packages/63/4b/e3678b4e776db00f9f7b2fe58e547e8928ef32727d7a1ff01dea010f3f13/zstandard-0.25.0-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:8e735494da3db08694d26480f1493ad2cf86e99bdd53e8e9771b2752a5c0246a", size = 5547173, upload-time = "2025-09-14T22:17:36.084Z" },
+    { url = "https://files.pythonhosted.org/packages/4e/d5/ba05ed95c6b8ec30bd468dfeab20589f2cf709b5c940483e31d991f2ca58/zstandard-0.25.0-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:3a39c94ad7866160a4a46d772e43311a743c316942037671beb264e395bdd611", size = 5046736, upload-time = "2025-09-14T22:17:37.891Z" },
+    { url = "https://files.pythonhosted.org/packages/50/d5/870aa06b3a76c73eced65c044b92286a3c4e00554005ff51962deef28e28/zstandard-0.25.0-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:172de1f06947577d3a3005416977cce6168f2261284c02080e7ad0185faeced3", size = 5576368, upload-time = "2025-09-14T22:17:40.206Z" },
+    { url = "https://files.pythonhosted.org/packages/5d/35/398dc2ffc89d304d59bc12f0fdd931b4ce455bddf7038a0a67733a25f550/zstandard-0.25.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:3c83b0188c852a47cd13ef3bf9209fb0a77fa5374958b8c53aaa699398c6bd7b", size = 4954022, upload-time = "2025-09-14T22:17:41.879Z" },
+    { url = "https://files.pythonhosted.org/packages/9a/5c/36ba1e5507d56d2213202ec2b05e8541734af5f2ce378c5d1ceaf4d88dc4/zstandard-0.25.0-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:1673b7199bbe763365b81a4f3252b8e80f44c9e323fc42940dc8843bfeaf9851", size = 5267889, upload-time = "2025-09-14T22:17:43.577Z" },
+    { url = "https://files.pythonhosted.org/packages/70/e8/2ec6b6fb7358b2ec0113ae202647ca7c0e9d15b61c005ae5225ad0995df5/zstandard-0.25.0-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:0be7622c37c183406f3dbf0cba104118eb16a4ea7359eeb5752f0794882fc250", size = 5433952, upload-time = "2025-09-14T22:17:45.271Z" },
+    { url = "https://files.pythonhosted.org/packages/7b/01/b5f4d4dbc59ef193e870495c6f1275f5b2928e01ff5a81fecb22a06e22fb/zstandard-0.25.0-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:5f5e4c2a23ca271c218ac025bd7d635597048b366d6f31f420aaeb715239fc98", size = 5814054, upload-time = "2025-09-14T22:17:47.08Z" },
+    { url = "https://files.pythonhosted.org/packages/b2/e5/fbd822d5c6f427cf158316d012c5a12f233473c2f9c5fe5ab1ae5d21f3d8/zstandard-0.25.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:4f187a0bb61b35119d1926aee039524d1f93aaf38a9916b8c4b78ac8514a0aaf", size = 5360113, upload-time = "2025-09-14T22:17:48.893Z" },
+    { url = "https://files.pythonhosted.org/packages/8e/e0/69a553d2047f9a2c7347caa225bb3a63b6d7704ad74610cb7823baa08ed7/zstandard-0.25.0-cp313-cp313-win32.whl", hash = "sha256:7030defa83eef3e51ff26f0b7bfb229f0204b66fe18e04359ce3474ac33cbc09", size = 436936, upload-time = "2025-09-14T22:17:52.658Z" },
+    { url = "https://files.pythonhosted.org/packages/d9/82/b9c06c870f3bd8767c201f1edbdf9e8dc34be5b0fbc5682c4f80fe948475/zstandard-0.25.0-cp313-cp313-win_amd64.whl", hash = "sha256:1f830a0dac88719af0ae43b8b2d6aef487d437036468ef3c2ea59c51f9d55fd5", size = 506232, upload-time = "2025-09-14T22:17:50.402Z" },
+    { url = "https://files.pythonhosted.org/packages/d4/57/60c3c01243bb81d381c9916e2a6d9e149ab8627c0c7d7abb2d73384b3c0c/zstandard-0.25.0-cp313-cp313-win_arm64.whl", hash = "sha256:85304a43f4d513f5464ceb938aa02c1e78c2943b29f44a750b48b25ac999a049", size = 462671, upload-time = "2025-09-14T22:17:51.533Z" },
+]