mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-01-04 13:48:31 +00:00
b3185ad90c
* added tool for docling support * docling support installation * use file_paths instead of file_path * fix import * organized imports * run_type docs * needs to be list * fixed logic * logged but file_path is backwards compatible * use file_paths instead of file_path 2 * added test for multiple sources for file_paths * fix run-types * enabling local files to work and type cleanup * linted * fix test and types * fixed run types * fix types * renamed to CrewDoclingSource * linted * added docs * resolve conflicts --------- Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com> Co-authored-by: Brandon Hancock <brandon@brandonhancock.io>
35 lines
1.2 KiB
Python
35 lines
1.2 KiB
Python
from typing import List, Optional
|
|
|
|
from pydantic import Field
|
|
|
|
from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
|
|
|
|
|
|
class StringKnowledgeSource(BaseKnowledgeSource):
|
|
"""A knowledge source that stores and queries plain text content using embeddings."""
|
|
|
|
content: str = Field(...)
|
|
collection_name: Optional[str] = Field(default=None)
|
|
|
|
def model_post_init(self, _):
|
|
"""Post-initialization method to validate content."""
|
|
self.validate_content()
|
|
|
|
def validate_content(self):
|
|
"""Validate string content."""
|
|
if not isinstance(self.content, str):
|
|
raise ValueError("StringKnowledgeSource only accepts string content")
|
|
|
|
def add(self) -> None:
|
|
"""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()
|
|
|
|
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)
|
|
]
|