Knowledge (#1567)

* initial knowledge

* WIP

* Adding core knowledge sources

* Improve types and better support for file paths

* added additional sources

* fix linting

* update yaml to include optional deps

* adding in lorenze feedback

* ensure embeddings are persisted

* improvements all around Knowledge class

* return this

* properly reset memory

* properly reset memory+knowledge

* consolodation and improvements

* linted

* cleanup rm unused embedder

* fix test

* fix duplicate

* generating cassettes for knowledge test

* updated default embedder

* None embedder to use default on pipeline cloning

* improvements

* fixed text_file_knowledge

* mypysrc fixes

* type check fixes

* added extra cassette

* just mocks

* linted

* mock knowledge query to not spin up db

* linted

* verbose run

* put a flag

* fix

* adding docs

* better docs

* improvements from review

* more docs

* linted

* rm print

* more fixes

* clearer docs

* added docstrings and type hints for cli

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
Co-authored-by: Lorenze Jay <lorenzejaytech@gmail.com>

src/crewai/knowledge/source/base_knowledge_source.py

@@ -0,0 +1,48 @@
+from abc import ABC, abstractmethod
+from typing import List, Dict, Any
+
+import numpy as np
+from pydantic import BaseModel, ConfigDict, Field
+
+from crewai.knowledge.storage.knowledge_storage import KnowledgeStorage
+
+
+class BaseKnowledgeSource(BaseModel, ABC):
+    """Abstract base class for knowledge sources."""
+
+    chunk_size: int = 4000
+    chunk_overlap: int = 200
+    chunks: List[str] = Field(default_factory=list)
+    chunk_embeddings: List[np.ndarray] = Field(default_factory=list)
+
+    model_config = ConfigDict(arbitrary_types_allowed=True)
+    storage: KnowledgeStorage = Field(default_factory=KnowledgeStorage)
+    metadata: Dict[str, Any] = Field(default_factory=dict)
+
+    @abstractmethod
+    def load_content(self) -> Dict[Any, str]:
+        """Load and preprocess content from the source."""
+        pass
+
+    @abstractmethod
+    def add(self) -> None:
+        """Process content, chunk it, compute embeddings, and save them."""
+        pass
+
+    def get_embeddings(self) -> List[np.ndarray]:
+        """Return the list of embeddings for the chunks."""
+        return self.chunk_embeddings
+
+    def _chunk_text(self, text: str) -> List[str]:
+        """Utility method to split text into chunks."""
+        return [
+            text[i : i + self.chunk_size]
+            for i in range(0, len(text), self.chunk_size - self.chunk_overlap)
+        ]
+
+    def save_documents(self, metadata: Dict[str, Any]):
+        """
+        Save the documents to the storage.
+        This method should be called after the chunks and embeddings are generated.
+        """
+        self.storage.save(self.chunks, metadata)