drop metadata requirement

src/crewai/knowledge/knowledge.py

@@ -1,6 +1,6 @@
 import os
+from typing import Any, Dict, List, Optional
 
-from typing import List, Optional, Dict, Any
 from pydantic import BaseModel, ConfigDict, Field
 
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
@@ -46,9 +46,7 @@ class Knowledge(BaseModel):
             source.storage = self.storage
             source.add()
 
-    def query(
-        self, query: List[str], limit: int = 3, preference: Optional[str] = None
-    ) -> List[Dict[str, Any]]:
+    def query(self, query: List[str], limit: int = 3) -> List[Dict[str, Any]]:
         """
         Query across all knowledge sources to find the most relevant information.
         Returns the top_k most relevant chunks.
@@ -57,8 +55,6 @@ class Knowledge(BaseModel):
         results = self.storage.search(
             query,
             limit,
-            filter={"preference": preference} if preference else None,
-            score_threshold=DEFAULT_SCORE_THRESHOLD,
         )
         return results
 

src/crewai/knowledge/source/base_file_knowledge_source.py

@@ -1,13 +1,13 @@
 from abc import ABC, abstractmethod
 from pathlib import Path
-from typing import Union, List, Dict, Any
+from typing import Any, Dict, List, Union
 
 from pydantic import Field
 
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
-from crewai.utilities.logger import Logger
 from crewai.knowledge.storage.knowledge_storage import KnowledgeStorage
 from crewai.utilities.constants import KNOWLEDGE_DIRECTORY
+from crewai.utilities.logger import Logger
 
 
 class BaseFileKnowledgeSource(BaseKnowledgeSource, ABC):
@@ -49,10 +49,9 @@ class BaseFileKnowledgeSource(BaseKnowledgeSource, ABC):
                     color="red",
                 )
 
-    def save_documents(self, metadata: Dict[str, Any]):
+    def save_documents(self):
         """Save the documents to the storage."""
-        chunk_metadatas = [metadata.copy() for _ in self.chunks]
-        self.storage.save(self.chunks, chunk_metadatas)
+        self.storage.save(self.chunks)
 
     def convert_to_path(self, path: Union[Path, str]) -> Path:
         """Convert a path to a Path object."""

src/crewai/knowledge/source/base_knowledge_source.py

@@ -1,5 +1,5 @@
 from abc import ABC, abstractmethod
-from typing import List, Dict, Any, Optional
+from typing import Any, Dict, List, Optional
 
 import numpy as np
 from pydantic import BaseModel, ConfigDict, Field
@@ -17,7 +17,6 @@ class BaseKnowledgeSource(BaseModel, ABC):
 
     model_config = ConfigDict(arbitrary_types_allowed=True)
     storage: KnowledgeStorage = Field(default_factory=KnowledgeStorage)
-    metadata: Dict[str, Any] = Field(default_factory=dict)
     collection_name: Optional[str] = Field(default=None)
 
     @abstractmethod
@@ -41,9 +40,9 @@ class BaseKnowledgeSource(BaseModel, ABC):
             for i in range(0, len(text), self.chunk_size - self.chunk_overlap)
         ]
 
-    def save_documents(self, metadata: Dict[str, Any]):
+    def save_documents(self):
         """
         Save the documents to the storage.
         This method should be called after the chunks and embeddings are generated.
         """
-        self.storage.save(self.chunks, metadata)
+        self.storage.save(self.chunks)

src/crewai/knowledge/source/csv_knowledge_source.py

@@ -1,6 +1,6 @@
 import csv
-from typing import Dict, List
 from pathlib import Path
+from typing import Dict, List
 
 from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
 
@@ -30,7 +30,7 @@ class CSVKnowledgeSource(BaseFileKnowledgeSource):
         )
         new_chunks = self._chunk_text(content_str)
         self.chunks.extend(new_chunks)
-        self.save_documents(metadata=self.metadata)
+        self.save_documents()
 
     def _chunk_text(self, text: str) -> List[str]:
         """Utility method to split text into chunks."""

src/crewai/knowledge/source/excel_knowledge_source.py

@@ -1,5 +1,6 @@
-from typing import Dict, List
 from pathlib import Path
+from typing import Dict, List
+
 from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
 
 
@@ -44,7 +45,7 @@ class ExcelKnowledgeSource(BaseFileKnowledgeSource):
 
         new_chunks = self._chunk_text(content_str)
         self.chunks.extend(new_chunks)
-        self.save_documents(metadata=self.metadata)
+        self.save_documents()
 
     def _chunk_text(self, text: str) -> List[str]:
         """Utility method to split text into chunks."""

src/crewai/knowledge/source/json_knowledge_source.py

@@ -1,6 +1,6 @@
 import json
-from typing import Any, Dict, List
 from pathlib import Path
+from typing import Any, Dict, List
 
 from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
 
@@ -42,7 +42,7 @@ class JSONKnowledgeSource(BaseFileKnowledgeSource):
         )
         new_chunks = self._chunk_text(content_str)
         self.chunks.extend(new_chunks)
-        self.save_documents(metadata=self.metadata)
+        self.save_documents()
 
     def _chunk_text(self, text: str) -> List[str]:
         """Utility method to split text into chunks."""

src/crewai/knowledge/source/pdf_knowledge_source.py

@@ -1,5 +1,5 @@
-from typing import List, Dict
 from pathlib import Path
+from typing import Dict, List
 
 from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
 
@@ -43,7 +43,7 @@ class PDFKnowledgeSource(BaseFileKnowledgeSource):
         for _, text in self.content.items():
             new_chunks = self._chunk_text(text)
             self.chunks.extend(new_chunks)
-        self.save_documents(metadata=self.metadata)
+        self.save_documents()
 
     def _chunk_text(self, text: str) -> List[str]:
         """Utility method to split text into chunks."""

src/crewai/knowledge/source/string_knowledge_source.py

@@ -24,7 +24,7 @@ class StringKnowledgeSource(BaseKnowledgeSource):
         """Add string content to the knowledge source, chunk it, compute embeddings, and save them."""
         new_chunks = self._chunk_text(self.content)
         self.chunks.extend(new_chunks)
-        self.save_documents(metadata=self.metadata)
+        self.save_documents()
 
     def _chunk_text(self, text: str) -> List[str]:
         """Utility method to split text into chunks."""

src/crewai/knowledge/source/text_file_knowledge_source.py

@@ -1,5 +1,5 @@
-from typing import Dict, List
 from pathlib import Path
+from typing import Dict, List
 
 from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
 
@@ -24,7 +24,7 @@ class TextFileKnowledgeSource(BaseFileKnowledgeSource):
         for _, text in self.content.items():
             new_chunks = self._chunk_text(text)
             self.chunks.extend(new_chunks)
-        self.save_documents(metadata=self.metadata)
+        self.save_documents()
 
     def _chunk_text(self, text: str) -> List[str]:
         """Utility method to split text into chunks."""

src/crewai/knowledge/storage/knowledge_storage.py

@@ -1,18 +1,20 @@
 import contextlib
+import hashlib
 import io
 import logging
-import chromadb
 import os
+from typing import Any, Dict, List, Optional, Union, cast
 
+import chromadb
 import chromadb.errors
-from crewai.utilities.paths import db_storage_path
-from typing import Optional, List, Dict, Any, Union
-from crewai.utilities import EmbeddingConfigurator
-from crewai.knowledge.storage.base_knowledge_storage import BaseKnowledgeStorage
-import hashlib
-from chromadb.config import Settings
 from chromadb.api import ClientAPI
+from chromadb.api.types import OneOrMany
+from chromadb.config import Settings
+
+from crewai.knowledge.storage.base_knowledge_storage import BaseKnowledgeStorage
+from crewai.utilities import EmbeddingConfigurator
 from crewai.utilities.logger import Logger
+from crewai.utilities.paths import db_storage_path
 
 
 @contextlib.contextmanager
@@ -116,11 +118,16 @@ class KnowledgeStorage(BaseKnowledgeStorage):
     def save(
         self,
         documents: List[str],
-        metadata: Union[Dict[str, Any], List[Dict[str, Any]]],
+        metadata: Optional[Union[Dict[str, Any], List[Dict[str, Any]]]] = None,
     ):
         if self.collection:
             try:
-                metadatas = [metadata] if isinstance(metadata, dict) else metadata
+                if metadata is None:
+                    metadatas: Optional[OneOrMany[chromadb.Metadata]] = None
+                elif isinstance(metadata, list):
+                    metadatas = [cast(chromadb.Metadata, m) for m in metadata]
+                else:
+                    metadatas = cast(chromadb.Metadata, metadata)
 
                 ids = [
                     hashlib.sha256(doc.encode("utf-8")).hexdigest() for doc in documents