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
54 lines
1.7 KiB
Python
54 lines
1.7 KiB
Python
from pathlib import Path
|
|
from typing import Dict, List
|
|
|
|
from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
|
|
|
|
|
|
class PDFKnowledgeSource(BaseFileKnowledgeSource):
|
|
"""A knowledge source that stores and queries PDF file content using embeddings."""
|
|
|
|
def load_content(self) -> Dict[Path, str]:
|
|
"""Load and preprocess PDF file content."""
|
|
pdfplumber = self._import_pdfplumber()
|
|
|
|
content = {}
|
|
|
|
for path in self.safe_file_paths:
|
|
text = ""
|
|
path = self.convert_to_path(path)
|
|
with pdfplumber.open(path) as pdf:
|
|
for page in pdf.pages:
|
|
page_text = page.extract_text()
|
|
if page_text:
|
|
text += page_text + "\n"
|
|
content[path] = text
|
|
return content
|
|
|
|
def _import_pdfplumber(self):
|
|
"""Dynamically import pdfplumber."""
|
|
try:
|
|
import pdfplumber
|
|
|
|
return pdfplumber
|
|
except ImportError:
|
|
raise ImportError(
|
|
"pdfplumber is not installed. Please install it with: pip install pdfplumber"
|
|
)
|
|
|
|
def add(self) -> None:
|
|
"""
|
|
Add PDF file content to the knowledge source, chunk it, compute embeddings,
|
|
and save the embeddings.
|
|
"""
|
|
for _, text in self.content.items():
|
|
new_chunks = self._chunk_text(text)
|
|
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)
|
|
]
|