-
Notifications
You must be signed in to change notification settings - Fork 905
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.
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
fix: Split payload content by smaller batches for embedding #653
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
❌ Changes requested. Reviewed everything up to 54bb2e8 in 33 seconds
More details
- Looked at
70
lines of code in1
files - Skipped
0
files when reviewing. - Skipped posting
0
drafted comments based on config settings.
Workflow ID: wflow_FIAa0RNmiZNq7CCF
Want Ellipsis to fix these issues? Tag @ellipsis-dev
in a comment. You can customize Ellipsis with 👍 / 👎 feedback, review rules, user-specific overrides, quiet
mode, and more.
54bb2e8
to
ec62ad4
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
❌ Changes requested. Incremental review on ec62ad4 in 21 seconds
More details
- Looked at
116
lines of code in2
files - Skipped
0
files when reviewing. - Skipped posting
0
drafted comments based on config settings.
Workflow ID: wflow_I3kx3ykCwpJQk4Y6
Want Ellipsis to fix these issues? Tag @ellipsis-dev
in a comment. You can customize Ellipsis with 👍 / 👎 feedback, review rules, user-specific overrides, quiet
mode, and more.
86cf911
to
7505347
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
❌ Changes requested. Incremental review on 7505347 in 24 seconds
More details
- Looked at
116
lines of code in2
files - Skipped
0
files when reviewing. - Skipped posting
0
drafted comments based on config settings.
Workflow ID: wflow_UqXhNfmt1sPs48pp
Want Ellipsis to fix these issues? Tag @ellipsis-dev
in a comment. You can customize Ellipsis with 👍 / 👎 feedback, review rules, user-specific overrides, quiet
mode, and more.
bc46948
to
0476f38
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
❌ Changes requested. Incremental review on 0476f38 in 25 seconds
More details
- Looked at
77
lines of code in1
files - Skipped
0
files when reviewing. - Skipped posting
0
drafted comments based on config settings.
Workflow ID: wflow_WbBquX6idAR3tRpX
Want Ellipsis to fix these issues? Tag @ellipsis-dev
in a comment. You can customize Ellipsis with 👍 / 👎 feedback, review rules, user-specific overrides, quiet
mode, and more.
0476f38
to
cb9eb91
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
❌ Changes requested. Incremental review on cb9eb91 in 45 seconds
More details
- Looked at
60
lines of code in1
files - Skipped
0
files when reviewing. - Skipped posting
2
drafted comments based on config settings.
1. agents-api/agents_api/activities/embed_docs.py:19
- Draft comment:
Theindices
variable is created but not used inembed_snippets_query
. Ensure that this is intentional and that indices are not needed. - Reason this comment was not posted:
Comment did not seem useful.
2. agents-api/agents_api/activities/embed_docs.py:49
- Draft comment:
Themax_batch_size
parameter inmock_embed_docs
is unused and can be removed for clarity. - Reason this comment was not posted:
Confidence changes required:50%
Themock_embed_docs
function has amax_batch_size
parameter that is not used. This is unnecessary and should be removed for clarity.
Workflow ID: wflow_qzPp0Wty8HHM5R3Q
Want Ellipsis to fix these issues? Tag @ellipsis-dev
in a comment. You can customize Ellipsis with 👍 / 👎 feedback, review rules, user-specific overrides, quiet
mode, and more.
cb9eb91
to
30b26be
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
❌ Changes requested. Incremental review on 30b26be in 24 seconds
More details
- Looked at
60
lines of code in1
files - Skipped
0
files when reviewing. - Skipped posting
0
drafted comments based on config settings.
Workflow ID: wflow_j5MnZy7166y1WaFm
Want Ellipsis to fix these issues? Tag @ellipsis-dev
in a comment. You can customize Ellipsis with 👍 / 👎 feedback, review rules, user-specific overrides, quiet
mode, and more.
lgtm. just double check the tests and typechecks (maybe add a mock embedding test with 1000 entries or something) |
Important
embed_docs
inembed_docs.py
now processes payloads in smaller batches asynchronously usingbatched
andasyncio
, with a new test case added.embed_docs
inembed_docs.py
now processes payload content in smaller batches usingbatched
fromitertools
.max_batch_size
parameter to control batch size, defaulting to 100.asyncio.wait
for asynchronous embedding of batches.embed_batch
inner function to process each batch of indices and snippets.embed_docs
to useembed_batch
for batch processing.asyncio
andbatched
imports to support new batching logic.test_activities.py
to verifyembed_docs
with batching logic usingunittest.mock.patch
.This description was created by for 30b26be. It will automatically update as commits are pushed.