Skip to content

Generate answer parallel #480

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

Closed
wants to merge 16 commits into from
Closed

Conversation

VinciGit00
Copy link
Collaborator

No description provided.

VinciGit00 and others added 11 commits June 29, 2024 20:26
## [1.10.0](v1.9.2...v1.10.0) (2024-07-20)

### Features

* add gpt4o omni ([431edb7](431edb7))
* add searchngx integration ([5c92186](5c92186))
* refactoring_to_md function ([602dd00](602dd00))

### Bug Fixes

* add gpt o mini for azure ([77777c8](77777c8))
* parse_node ([07f1e23](07f1e23))
* search link node ([cf3ab55](cf3ab55))

### chore

* correct search engine name ([7ba2f6a](7ba2f6a))
* remove unused import ([fd1b7cb](fd1b7cb))
* **ci:** upgrade lockfiles ([c7b05a4](c7b05a4))
* upgrade tiktoken ([7314bc3](7314bc3))

### Docs

* **gpt-4o-mini:** added new gpt, fixed chromium lazy loading, ([99dc849](99dc849))

### CI

* **release:** 1.10.0-beta.1 [skip ci] ([8f619de](8f619de))
* **release:** 1.10.0-beta.2 [skip ci] ([aa7d4f0](aa7d4f0))
* **release:** 1.10.0-beta.3 [skip ci] ([bf0a2f3](bf0a2f3))
* **release:** 1.10.0-beta.4 [skip ci] ([a91807a](a91807a))
* **release:** 1.10.0-beta.5 [skip ci] ([0d5f925](0d5f925))
* **release:** 1.9.0-beta.3 [skip ci] ([d3e63d9](d3e63d9))
* **release:** 1.9.0-beta.4 [skip ci] ([2fa04b5](2fa04b5))
* **release:** 1.9.0-beta.5 [skip ci] ([bb62439](bb62439))
* **release:** 1.9.0-beta.6 [skip ci] ([54a69de](54a69de))
## [1.10.1](v1.10.0...v1.10.1) (2024-07-21)

### Bug Fixes

* abstract_graph moel token bug ([ce6be37](ce6be37))
## [1.10.2](v1.10.1...v1.10.2) (2024-07-21)

### Bug Fixes

* telemetry version ([b0418b6](b0418b6))

# Use tqdm to add progress bar
for i, chunk in enumerate(tqdm(doc, desc="Processing chunks", disable=not self.verbose)):
if len(doc) == 1:
# No batching needed for single chunk
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

why checking the document length inside the for-loop and not outside of it?

rather, the for-loop should be in place only if the document has multiple chunks

@VinciGit00 VinciGit00 closed this Jul 22, 2024
@VinciGit00 VinciGit00 deleted the generate_answer_parallel branch July 22, 2024 14:17
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants