-
-
Notifications
You must be signed in to change notification settings - Fork 684
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
Check writer pipeline #1201
Check writer pipeline #1201
Conversation
…ntire item at the end
…nd deleted failing multitask.py task
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.
👍 Looks good to me! Reviewed everything up to a0b8dc5 in 1 minute and 22 seconds
More details
- Looked at
1766
lines of code in28
files - Skipped
1
files when reviewing. - Skipped posting
2
drafted comments based on config settings.
1. tests/llm/test_writer/test_format_common_models.py:159
- Draft comment:
The Jinja2 template syntax in theprompt
variable is not being processed. Consider using a template engine to render the template before passing it to themessages
parameter. - Reason this comment was not posted:
Confidence changes required:50%
The test filetest_writer/test_format_common_models.py
contains a test functiontest_writer_format_list_of_strings
that uses a Jinja2 template in a string. However, the template syntax is not being processed, which might lead to unexpected behavior or errors during test execution.
2. tests/llm/test_writer/evals/test_classification_enums.py:55
- Draft comment:
Assertions should include error messages for clarity. This applies to other test files as well. - Reason this comment was not posted:
Confidence changes required:80%
The assertion statements in the test files lack error messages. Adding error messages will make it easier to understand the cause of a test failure.
Workflow ID: wflow_PEYsq5d0BKWE8gDc
You can customize Ellipsis with 👍 / 👎 feedback, review rules, user-specific overrides, quiet
mode, and more.
Deploying instructor-py with Cloudflare Pages
|
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 8652b9c in 1 minute and 6 seconds
More details
- Looked at
116
lines of code in4
files - Skipped
0
files when reviewing. - Skipped posting
0
drafted comments based on config settings.
Workflow ID: wflow_6hAJvmbq98hrJ9SA
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.
@@ -0,0 +1,57 @@ | |||
import enum | |||
from itertools import product | |||
|
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.
Missing import for List
and Tuple
. Add from typing import List, Tuple
to avoid NameError.
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.
👍 Looks good to me! Incremental review on c2924c4 in 22 seconds
More details
- Looked at
13
lines of code in1
files - Skipped
0
files when reviewing. - Skipped posting
2
drafted comments based on config settings.
1. tests/llm/test_writer/evals/test_sentiment_analysis.py:39
- Draft comment:
For compatibility with Python versions below 3.9, useList
andTuple
from thetyping
module instead oflist
andtuple
.
model: str, data: List[Tuple[str, Sentiment]], mode: instructor.Mode
- Reason this comment was not posted:
Confidence changes required:80%
The use of list and tuple in type hints is not compatible with Python versions below 3.9. The code should use List and Tuple from the typing module for compatibility.
2. tests/llm/test_writer/evals/test_sentiment_analysis.py:39
- Draft comment:
UseList
andTuple
fromtyping
for consistency with the rest of the codebase.
model: str, data: List[Tuple[str, Sentiment]], mode: instructor.Mode
- Reason this comment was not posted:
Confidence changes required:80%
The type hinting in the test function is inconsistent with the rest of the codebase, which usesList
andTuple
fromtyping
.
Workflow ID: wflow_IpzzC3GeWE5nF4kX
You can customize Ellipsis with 👍 / 👎 feedback, review rules, user-specific overrides, quiet
mode, and more.
Important
Integrate Writer's Palmyra-X-004 model with structured outputs, documentation, and tests, introducing
WRITER_TOOLS
mode.instructor
.from_writer()
function inclient_writer.py
for Writer and AsyncWriter clients.WRITER_TOOLS
mode inmode.py
.writer.md
for integration guide.index.md
to include Writer in supported providers.writer-support.md
announcing the integration.tests/llm/test_writer/
.pyproject.toml
to includewriter-sdk
as a dependency.yanomaly
to.authors.yml
.This description was created by for c2924c4. It will automatically update as commits are pushed.