Created
September 3, 2023 16:01
-
-
Save CurtisAccelerate/b240a0088b1baeb588dd7056791b0eb9 to your computer and use it in GitHub Desktop.
Search Helper for GPT-4 Advanced Data Analysis
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from difflib import SequenceMatcher | |
# Text-based Case-Insensitive Search Function with Snippet Extraction | |
def text_search_focused(query, text, snippet_size=1000, max_results=20): | |
results = [] | |
start_idx = 0 | |
query = query.lower() # Convert query to lowercase for case-insensitive search | |
text = text.lower() # Convert text to lowercase for case-insensitive search | |
while len(results) < max_results: | |
start_idx = text.find(query, start_idx) | |
if start_idx == -1: | |
break | |
# Extract snippet around found text | |
snippet_start_idx = max(0, start_idx - snippet_size // 2) | |
snippet_end_idx = min(start_idx + snippet_size // 2, len(text)) | |
snippet = text[snippet_start_idx:snippet_end_idx] | |
# Add result to list | |
results.append({ | |
'snippet': snippet, | |
'start_idx': snippet_start_idx, | |
'end_idx': snippet_end_idx | |
}) | |
# Move index forward for next search | |
start_idx += len(query) | |
return results |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment