Skip to content
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

Cognitive search vector #6

Merged
merged 125 commits into from
Sep 25, 2023
Merged

Cognitive search vector #6

merged 125 commits into from
Sep 25, 2023

Conversation

dantelmomsft
Copy link
Collaborator

Purpose

  • ...

Does this introduce a breaking change?

[ ] Yes
[ ] No

Pull Request Type

What kind of change does this Pull Request introduce?

[ ] Bugfix
[ ] Feature
[ ] Code style update (formatting, local variables)
[ ] Refactoring (no functional changes, no api changes)
[ ] Documentation content changes
[ ] Other... Please describe:

How to Test

  • Get the code
git clone [repo-address]
cd [repo-name]
git checkout [branch-name]
npm install
  • Test the code

What to Check

Verify that the following are valid

  • ...

Other Information

pamelafox and others added 30 commits June 23, 2023 21:00
Bumps [pypdf](https://github.com/py-pdf/pypdf) from 3.5.0 to 3.9.0.
- [Release notes](https://github.com/py-pdf/pypdf/releases)
- [Changelog](https://github.com/py-pdf/pypdf/blob/main/CHANGELOG.md)
- [Commits](py-pdf/pypdf@3.5.0...3.9.0)

---
updated-dependencies:
- dependency-name: pypdf
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
…df-3.9.0

Bump pypdf from 3.5.0 to 3.9.0 in /scripts
Co-authored-by: Pamela Fox <pamela.fox@gmail.com>
Co-authored-by: Pamela Fox <pamela.fox@gmail.com>
Co-authored-by: Pamela Fox <pamela.fox@gmail.com>
Co-authored-by: Pamela Fox <pamela.fox@gmail.com>
Update README.md with a more direct link to models availability docs.
Co-authored-by: Pamela Fox <pamela.fox@gmail.com>
Co-authored-by: Pamela Fox <pamela.fox@gmail.com>
Co-authored-by: Pamela Fox <pamela.fox@gmail.com>
Co-authored-by: Pamela Fox <pamela.fox@gmail.com>
pamelafox and others added 26 commits September 7, 2023 15:12
* Remove defaults for getenv

* Remove print

* missing output

* Add tests and fix prepdocs issue

* rm uneeded print
* Update README.md with logging info

* Build logging in with env var
* Remove defaults for getenv

* Remove print

* missing output

* Add tests and fix prepdocs issue

* Fix prompt issue, add tests

* Fix prompt issue, add tests

* Delete unneeded print
* Run black on all files

* Fix acreate
* Adding openai non-azure endpoint support

* Editing infra files

* Adding missing args for the prepdocs script

* Rolling back indentation changes

* rolling back indentiation edits

* removing unnecessary parenthesis

* Adding OPENAI_EMB_MODEL parameter to bicep config

* Adding conditional args to reduce if statements

* Rm notebooks again

* OpenAI api type

* Tests pass

* Fix bicep issue

* Prepdocs fix

* Add main.bicep changes

* Add main.bicep changes

* Add missing api_type

* Parameterize tests

* Rm comma

* Making chatGptModelName param conditional

* Conditional system identity

* Make Azure_openai_service conditional

* fix inconsistencies across emb model param naming

* Fix formatting after merge from main

* Script fix

---------

Co-authored-by: Pamela Fox <pamela.fox@gmail.com>
Co-authored-by: Pamela Fox <pamelafox@microsoft.com>
* Adding anchors

* Feature comparison table

* Update table to rm unneeded row

* remove en-us in links
* Adding anchors

* Free wont work
This smooths out the rate streamed content is presented to the user.
It enables a more complex backend to provide intial results quickly
and then use the fact the user will be reading those results to make
affordable (from a UX performance point of view) more complex
chains or processes for subset of the results that occur later in the
overall answer.

Prevent partial citation text

Citations are provided as text within square brackets.
Printing these before the citation is closed causes flashing during the
streaming.

This update checks if the text ends on something looks like a citation
in progress and does not print that text until the citation is closed.

When streaming is done we display with the non-streaming ui. This
means the risk of accidentally omitting text due to an unexpected
use of mismatched brackets by the llm will merely delay rather than
omit text. (Note .. any unexpected uses of brackets probably interacts
poorly with the citations, but I have not dug further on that.)
* Use function call to stabilize search query

* minor changes

* sort imports

* fix ruff

* s

* Update app/backend/approaches/chatreadretrieveread.py

Co-authored-by: Pamela Fox <pamelafox@microsoft.com>

* s

* blacj format

* add test

* save

---------

Co-authored-by: Pamela Fox <pamelafox@microsoft.com>
* Adding anchors

* Rm fund notice

* Account for bug

* rm unrelated change
added support for cognitive search vector database. App insights monitoring added as well. README updated
@dantelmomsft dantelmomsft temporarily deployed to Development September 25, 2023 17:15 — with GitHub Actions Inactive
@dantelmomsft dantelmomsft merged commit 5e661f4 into main Sep 25, 2023
@dantelmomsft dantelmomsft temporarily deployed to Development September 25, 2023 17:19 — with GitHub Actions Inactive
@dantelmomsft dantelmomsft deleted the cognitive-search-vector branch October 12, 2023 09:09
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.