mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-01-08 15:48:29 +00:00
c7c0647dd2
* drop metadata requirement * fix linting * Update docs for new knowledge * more linting * more linting * make save_documents private * update docs to the new way we use knowledge and include clearing memory
41 lines
1.4 KiB
Python
41 lines
1.4 KiB
Python
import csv
|
|
from pathlib import Path
|
|
from typing import Dict, List
|
|
|
|
from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
|
|
|
|
|
|
class CSVKnowledgeSource(BaseFileKnowledgeSource):
|
|
"""A knowledge source that stores and queries CSV file content using embeddings."""
|
|
|
|
def load_content(self) -> Dict[Path, str]:
|
|
"""Load and preprocess CSV file content."""
|
|
content_dict = {}
|
|
for file_path in self.safe_file_paths:
|
|
with open(file_path, "r", encoding="utf-8") as csvfile:
|
|
reader = csv.reader(csvfile)
|
|
content = ""
|
|
for row in reader:
|
|
content += " ".join(row) + "\n"
|
|
content_dict[file_path] = content
|
|
return content_dict
|
|
|
|
def add(self) -> None:
|
|
"""
|
|
Add CSV file content to the knowledge source, chunk it, compute embeddings,
|
|
and save the embeddings.
|
|
"""
|
|
content_str = (
|
|
str(self.content) if isinstance(self.content, dict) else self.content
|
|
)
|
|
new_chunks = self._chunk_text(content_str)
|
|
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)
|
|
]
|