Improve documentation of using LLMs #1636
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
jieguangzhou
changed the title
Codecov ReportAll modified and coverable lines are covered by tests ✅
Additional details and impacted files@@ Coverage Diff @@
## main #1636 +/- ##
==========================================
+ Coverage 80.33% 80.35% +0.01%
==========================================
Files 95 116 +21
Lines 6602 8194 +1592
==========================================
+ Hits 5304 6584 +1280
- Misses 1298 1610 +312 ☔ View full report in Codecov by Sentry. |
jieguangzhou
changed the title
jieguangzhou
force-pushed
the
doc/llm
branch
2 times, most recently
from
90fd25b
to
117ab10
Compare
jieguangzhou
force-pushed
the
doc/llm
branch
2 times, most recently
from
db20a8e
to
6db444d
Compare
jieguangzhou
commented
Jan 3, 2024
Comment on lines
+156
to
+180
| def _generate_wrapper(self, prompt: str, **kwargs: Any) -> str: | ||
| """ | ||
| Wrapper for the _generate method to handle exceptions. | ||
| """ | ||
| try: | ||
| return self._generate(prompt, **kwargs) | ||
| except Exception as e: | ||
| logging.error(f"Error generating response for prompt '{prompt}': {e}") | ||
| return "" | ||
|
|
||
| def _batch_generate(self, prompts: List[str], **kwargs: Any) -> List[str]: | ||
| """ | ||
| Base method to batch generate text from a list of prompts using multi-threading. | ||
| Handles exceptions in _generate method. | ||
| """ | ||
| with concurrent.futures.ThreadPoolExecutor( | ||
| max_workers=self.max_batch_size | ||
| ) as executor: | ||
| results = list( | ||
| executor.map( | ||
| lambda prompt: self._generate_wrapper(prompt, **kwargs), prompts | ||
| ) | ||
| ) | ||
|
|
||
| return results |
There was a problem hiding this comment.
Use multi-threading instead of async function for concurrent API requests. Because some versions of Jupyter do not directly support asynchronous requests, and this is easier to maintain and understand.
This was
linked to
issues
Jan 3, 2024
- Support dialog format messages - Delete the model class in vllm openai format - Use multi-threading instead of async function for concurrent API requests
blythed
reviewed
Jan 5, 2024
|
|
||
|
|
||
|
|
||
| ## Support Framework/API |
blythed
approved these changes
Jan 5, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
Related Issues
Checklist
make unit-testingandmake integration-testingsuccessfully?Additional Notes or Comments