Skip to content

support openai embedding for topic clustering #2729

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
CodingWithTim merged 4 commits into from
Jan 20, 2024
Merged

support openai embedding for topic clustering #2729

Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
12d32a2
support openai embedding for topic clustering
CodingWithTim Nov 24, 2023
7afdac2
combine the 2 embedding functions
CodingWithTim Nov 24, 2023
a07060f
fix load text
CodingWithTim Jan 19, 2024
4c66f70
finalize
CodingWithTim Jan 20, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
finalize
  • Loading branch information
@CodingWithTim
CodingWithTim committed Jan 20, 2024
commit 4c66f701f1fb8acb8b47f8d8e67f375441ac6c1c
7 changes: 4 additions & 3 deletions fastchat/serve/monitor/topic_clustering.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -244,15 +244,16 @@ def get_cluster_info(texts, labels, topk_indices):
texts = read_texts(
args.input_file, args.min_length, args.max_length, args.english_only
)
print(f"#text: {len(texts)}")

if args.embeddings_file is None:
print(f"#text: {len(texts)}")
embeddings = get_embeddings(texts, args.model, args.batch_size)
print(f"embeddings shape: {embeddings.shape}")
if args.save_embeddings:
# allow saving embedding to save time
# allow saving embedding to save time and money
torch.save(embeddings, "embeddings.pt")
else:
embeddings = torch.load(args.embeddings_file)
print(f"embeddings shape: {embeddings.shape}")

if args.cluster_alg == "kmeans":
centers, labels = run_k_means(embeddings, num_clusters)
Expand Down