Skip to content

examples: simplify the paper_metadata example: inline embedding call #714

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
merged 1 commit into from
Jul 8, 2025
Merged

examples: simplify the paper_metadata example: inline embedding call #714

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
27 changes: 10 additions & 17 deletions examples/paper_metadata/main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,21 +70,6 @@ def pdf_to_markdown(content: bytes) -> str:
return text


@cocoindex.transform_flow()
def text_to_embedding(
text: cocoindex.DataSlice[str],
) -> cocoindex.DataSlice[list[float]]:
"""
Embed the text using a SentenceTransformer model.
This is a shared logic between indexing and querying, so extract it as a function.
"""
return text.transform(
cocoindex.functions.SentenceTransformerEmbed(
model="sentence-transformers/all-MiniLM-L6-v2"
)
)


@cocoindex.flow_def(name="PaperMetadata")
def paper_metadata_flow(
flow_builder: cocoindex.FlowBuilder, data_scope: cocoindex.DataScope
Expand Down Expand Up @@ -115,7 +100,11 @@ def paper_metadata_flow(
instruction="Please extract the metadata from the first page of the paper.",
)
)
doc["title_embedding"] = text_to_embedding(doc["metadata"]["title"])
doc["title_embedding"] = doc["metadata"]["title"].transform(
cocoindex.functions.SentenceTransformerEmbed(
model="sentence-transformers/all-MiniLM-L6-v2"
)
)
doc["abstract_chunks"] = doc["metadata"]["abstract"].transform(
cocoindex.functions.SplitRecursively(
custom_languages=[
Expand Down Expand Up @@ -152,7 +141,11 @@ def paper_metadata_flow(
)

with doc["abstract_chunks"].row() as chunk:
chunk["embedding"] = text_to_embedding(chunk["text"])
chunk["embedding"] = chunk["text"].transform(
cocoindex.functions.SentenceTransformerEmbed(
model="sentence-transformers/all-MiniLM-L6-v2"
)
)
metadata_embeddings.collect(
id=cocoindex.GeneratedField.UUID,
filename=doc["filename"],
Expand Down