feat: upgrade fastavro, pyarrow and lancedb

Added explicit tokenizers dependency: Added tokenizers>=0.20.3 to ensure a version compatible with Python 3.13 is used.

.github/workflows/tests.yml

@@ -14,7 +14,7 @@ jobs:
     timeout-minutes: 15
     strategy:
       matrix:
-        python-version: ['3.10', '3.11', '3.12']
+        python-version: ['3.10', '3.11', '3.12', '3.13']
     steps:
       - name: Checkout code
         uses: actions/checkout@v4

docs/installation.mdx

@@ -22,7 +22,7 @@ Watch this video tutorial for a step-by-step demonstration of the installation p
 <Note>
   **Python Version Requirements**
 
-  CrewAI requires `Python >=3.10 and <3.13`. Here's how to check your version:
+  CrewAI requires `Python >=3.10 and <=3.13`. Here's how to check your version:
   ```bash
   python3 --version
   ```

pyproject.toml

@@ -3,7 +3,7 @@ name = "crewai"
 version = "0.121.1"
 description = "Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks."
 readme = "README.md"
-requires-python = ">=3.10,<3.13"
+requires-python = ">=3.10,<3.14"
 authors = [
     { name = "Joao Moura", email = "joao@crewai.com" }
 ]
@@ -22,6 +22,8 @@ dependencies = [
     "opentelemetry-exporter-otlp-proto-http>=1.30.0",
     # Data Handling
     "chromadb>=0.5.23",
+    "tokenizers>=0.20.3",
+    "onnxruntime==1.22.0",
     "openpyxl>=3.1.5",
     "pyvis>=0.3.2",
     # Authentication and Security
@@ -50,7 +52,6 @@ embeddings = [
     "tiktoken~=0.7.0"
 ]
 agentops = ["agentops>=0.3.0"]
-fastembed = ["fastembed>=0.4.1"]
 pdfplumber = [
     "pdfplumber>=0.11.4",
 ]
@@ -100,6 +101,27 @@ exclude = ["cli/templates"]
 [tool.bandit]
 exclude_dirs = ["src/crewai/cli/templates"]
 
+# PyTorch index configuration, since torch 2.5.0 is not compatible with python 3.13
+[[tool.uv.index]]
+name = "pytorch-nightly"
+url = "https://download.pytorch.org/whl/nightly/cpu"
+explicit = true
+
+[[tool.uv.index]]
+name = "pytorch"
+url = "https://download.pytorch.org/whl/cpu"
+explicit = true
+
+[tool.uv.sources]
+torch = [
+  { index = "pytorch-nightly", marker = "python_version >= '3.13'" },
+  { index = "pytorch", marker = "python_version < '3.13'" },
+]
+torchvision = [
+  { index = "pytorch-nightly", marker = "python_version >= '3.13'" },
+  { index = "pytorch", marker = "python_version < '3.13'" },
+]
+
 [build-system]
 requires = ["hatchling"]
 build-backend = "hatchling.build"

src/crewai/knowledge/embedder/fastembed.py

@@ -1,93 +0,0 @@
-from pathlib import Path
-from typing import List, Optional, Union
-
-import numpy as np
-
-from .base_embedder import BaseEmbedder
-
-try:
-    from fastembed_gpu import TextEmbedding  # type: ignore
-
-    FASTEMBED_AVAILABLE = True
-except ImportError:
-    try:
-        from fastembed import TextEmbedding
-
-        FASTEMBED_AVAILABLE = True
-    except ImportError:
-        FASTEMBED_AVAILABLE = False
-
-
-class FastEmbed(BaseEmbedder):
-    """
-    A wrapper class for text embedding models using FastEmbed
-    """
-
-    def __init__(
-        self,
-        model_name: str = "BAAI/bge-small-en-v1.5",
-        cache_dir: Optional[Union[str, Path]] = None,
-    ):
-        """
-        Initialize the embedding model
-
-        Args:
-            model_name: Name of the model to use
-            cache_dir: Directory to cache the model
-            gpu: Whether to use GPU acceleration
-        """
-        if not FASTEMBED_AVAILABLE:
-            raise ImportError(
-                "FastEmbed is not installed. Please install it with: "
-                "uv pip install fastembed or uv pip install fastembed-gpu for GPU support"
-            )
-
-        self.model = TextEmbedding(
-            model_name=model_name,
-            cache_dir=str(cache_dir) if cache_dir else None,
-        )
-
-    def embed_chunks(self, chunks: List[str]) -> List[np.ndarray]:
-        """
-        Generate embeddings for a list of text chunks
-
-        Args:
-            chunks: List of text chunks to embed
-
-        Returns:
-            List of embeddings
-        """
-        embeddings = list(self.model.embed(chunks))
-        return embeddings
-
-    def embed_texts(self, texts: List[str]) -> List[np.ndarray]:
-        """
-        Generate embeddings for a list of texts
-
-        Args:
-            texts: List of texts to embed
-
-        Returns:
-            List of embeddings
-        """
-        embeddings = list(self.model.embed(texts))
-        return embeddings
-
-    def embed_text(self, text: str) -> np.ndarray:
-        """
-        Generate embedding for a single text
-
-        Args:
-            text: Text to embed
-
-        Returns:
-            Embedding array
-        """
-        return self.embed_texts([text])[0]
-
-    @property
-    def dimension(self) -> int:
-        """Get the dimension of the embeddings"""
-        # Generate a test embedding to get dimensions
-        test_embed = self.embed_text("test")
-        return len(test_embed)