fix ruff errors and formatting
This commit is contained in:
@@ -1,5 +1,5 @@
|
||||
The Project Gutenberg eBook of Pride and Prejudice
|
||||
|
||||
|
||||
This ebook is for the use of anyone anywhere in the United States and
|
||||
most other parts of the world at no cost and with almost no restrictions
|
||||
whatsoever. You may copy it, give it away or re-use it under the terms
|
||||
@@ -14557,7 +14557,7 @@ her into Derbyshire, had been the means of uniting them.
|
||||
*** END OF THE PROJECT GUTENBERG EBOOK PRIDE AND PREJUDICE ***
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
Updated editions will replace the previous one—the old editions will
|
||||
be renamed.
|
||||
@@ -14662,7 +14662,7 @@ performed, viewed, copied or distributed:
|
||||
at www.gutenberg.org. If you
|
||||
are not located in the United States, you will have to check the laws
|
||||
of the country where you are located before using this eBook.
|
||||
|
||||
|
||||
1.E.2. If an individual Project Gutenberg™ electronic work is
|
||||
derived from texts not protected by U.S. copyright law (does not
|
||||
contain a notice indicating that it is posted with permission of the
|
||||
@@ -14724,7 +14724,7 @@ provided that:
|
||||
Gutenberg Literary Archive Foundation at the address specified in
|
||||
Section 4, “Information about donations to the Project Gutenberg
|
||||
Literary Archive Foundation.”
|
||||
|
||||
|
||||
• You provide a full refund of any money paid by a user who notifies
|
||||
you in writing (or by e-mail) within 30 days of receipt that s/he
|
||||
does not agree to the terms of the full Project Gutenberg™
|
||||
@@ -14732,15 +14732,15 @@ provided that:
|
||||
copies of the works possessed in a physical medium and discontinue
|
||||
all use of and all access to other copies of Project Gutenberg™
|
||||
works.
|
||||
|
||||
|
||||
• You provide, in accordance with paragraph 1.F.3, a full refund of
|
||||
any money paid for a work or a replacement copy, if a defect in the
|
||||
electronic work is discovered and reported to you within 90 days of
|
||||
receipt of the work.
|
||||
|
||||
|
||||
• You comply with all other terms of this agreement for free
|
||||
distribution of Project Gutenberg™ works.
|
||||
|
||||
|
||||
|
||||
1.E.9. If you wish to charge a fee or distribute a Project
|
||||
Gutenberg™ electronic work or group of works on different terms than
|
||||
@@ -14903,5 +14903,3 @@ This website includes information about Project Gutenberg™,
|
||||
including how to make donations to the Project Gutenberg Literary
|
||||
Archive Foundation, how to help produce our new eBooks, and how to
|
||||
subscribe to our email newsletter to hear about new eBooks.
|
||||
|
||||
|
||||
|
||||
@@ -27,7 +27,10 @@ def load_sample_documents():
|
||||
"title": "Intro to Python",
|
||||
"content": "Python is a high-level, interpreted language known for simplicity.",
|
||||
},
|
||||
{"title": "ML Basics", "content": "Machine learning builds systems that learn from data."},
|
||||
{
|
||||
"title": "ML Basics",
|
||||
"content": "Machine learning builds systems that learn from data.",
|
||||
},
|
||||
{
|
||||
"title": "Data Structures",
|
||||
"content": "Data structures like arrays, lists, and graphs organize data.",
|
||||
|
||||
@@ -21,7 +21,9 @@ DEFAULT_CHROME_PROFILE = os.path.expanduser("~/Library/Application Support/Googl
|
||||
|
||||
|
||||
def create_leann_index_from_multiple_chrome_profiles(
|
||||
profile_dirs: list[Path], index_path: str = "chrome_history_index.leann", max_count: int = -1
|
||||
profile_dirs: list[Path],
|
||||
index_path: str = "chrome_history_index.leann",
|
||||
max_count: int = -1,
|
||||
):
|
||||
"""
|
||||
Create LEANN index from multiple Chrome profile data sources.
|
||||
|
||||
@@ -474,7 +474,8 @@ Messages ({len(messages)} messages, {message_group["total_length"]} chars):
|
||||
message_group, contact_name
|
||||
)
|
||||
doc = Document(
|
||||
text=doc_content, metadata={"contact_name": contact_name}
|
||||
text=doc_content,
|
||||
metadata={"contact_name": contact_name},
|
||||
)
|
||||
docs.append(doc)
|
||||
count += 1
|
||||
|
||||
@@ -315,7 +315,11 @@ async def main():
|
||||
|
||||
# Create or load the LEANN index from all sources
|
||||
index_path = create_leann_index_from_multiple_sources(
|
||||
messages_dirs, INDEX_PATH, args.max_emails, args.include_html, args.embedding_model
|
||||
messages_dirs,
|
||||
INDEX_PATH,
|
||||
args.max_emails,
|
||||
args.include_html,
|
||||
args.embedding_model,
|
||||
)
|
||||
|
||||
if index_path:
|
||||
|
||||
@@ -92,7 +92,10 @@ def main():
|
||||
help="Directory to store the index (default: mail_index_embedded)",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--max-emails", type=int, default=10000, help="Maximum number of emails to process"
|
||||
"--max-emails",
|
||||
type=int,
|
||||
default=10000,
|
||||
help="Maximum number of emails to process",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--include-html",
|
||||
@@ -112,7 +115,10 @@ def main():
|
||||
else:
|
||||
print("Creating new index...")
|
||||
index = create_and_save_index(
|
||||
mail_path, save_dir, max_count=args.max_emails, include_html=args.include_html
|
||||
mail_path,
|
||||
save_dir,
|
||||
max_count=args.max_emails,
|
||||
include_html=args.include_html,
|
||||
)
|
||||
if index:
|
||||
queries = [
|
||||
|
||||
@@ -347,7 +347,9 @@ def demo_aggregation():
|
||||
print(f"\n{'=' * 20} {method.upper()} AGGREGATION {'=' * 20}")
|
||||
|
||||
aggregator = MultiVectorAggregator(
|
||||
aggregation_method=method, spatial_clustering=True, cluster_distance_threshold=100.0
|
||||
aggregation_method=method,
|
||||
spatial_clustering=True,
|
||||
cluster_distance_threshold=100.0,
|
||||
)
|
||||
|
||||
aggregated = aggregator.aggregate_results(mock_results, top_k=5)
|
||||
|
||||
Reference in New Issue
Block a user