-
Notifications
You must be signed in to change notification settings - Fork 198
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
Properly handle multi-query retrieval #1067
Draft
arn-tru
wants to merge
567
commits into
main
Choose a base branch
from
arn/1327-properly-handle-multiquery-retrieval
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Draft
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
Contributor
arn-tru
commented
Apr 10, 2024
- Added missing import in one of the notebooks
* Update 2_honest_rag.ipynb * Update 3_harmless_eval.ipynb * Update 4_harmless_rag.ipynb * Update 5_helpful_eval.ipynb * Update 2_honest_rag.ipynb
* basic langchain provider implementation * langchain provider, minor refactor * update docstring --------- Co-authored-by: Josh Reini <[email protected]>
* change relative links to hardcoded links in docs * hardlink contributions guide * update readmes, contributing
* first pass at migrating to pydantic v2, not ready * more fixes * disable protected namespace warning * cleanup setup * revert Any types * fixing schema and serial types * fixing more v1 -> v2 pydantic changes * working trubot * patching serialization and loading issues * remove unneeded * remove uneeded * format * pydantic update in reqs file * test fixes * revert explain changes * remove unneeded * fixing unit tests --------- Co-authored-by: Josh Reini <[email protected]>
* adding migration from prior versions and a dump of current version database * few fixes * more fixes * moar * add pip list to pipeline * activate * fix pipeline again * dont use class info unless needed * deserialize * fix type annotation of ground_truth * update SimpleWebPageReader import * notes * missed some import changes * more fixes * type annot * more fixes * more fixes * add Feedback info instead of FeedbackDefinition info
* update nb tagged versions * bump py script quickstarts
* update nb tagged versions * bump py script quickstarts * remove cohere provider, fix typo in hf api docs * more cohere removes
Co-authored-by: joshreini1 <[email protected]> Co-authored-by: Josh Reini <[email protected]>
Co-authored-by: joshreini1 <[email protected]>
* better messages * better dummy * remove unused streamlit_javascript requirement
#690) * extra query_str from query bundle as main input * add test to dev_notebook * notes for dev notebook
* add langchain rag instrumentation * remove unneeded
* bump versions in quickstarts * bump version * remove openai references in function definitions page
Co-authored-by: joshreini1 <[email protected]>
* bump versions in quickstarts * bump version * remove openai references in function definitions page * gemini example * headers * second example: semantic evals * updates, add rag triad * update top header
…#696) * add aliases for selectors for main method args and main method return * break down * refine --------- Co-authored-by: Josh Reini <[email protected]>
* exposed AzureOpenAI provider * added docs * Update CONTRIBUTING.md * typo in mkdocs.yml --------- Co-authored-by: Josh Reini <[email protected]>
* first * typos * typehint
* import llama only if needed * use optional imports instead --------- Co-authored-by: Piotr Mardziel <[email protected]>
* fix * typo * don't print external if internal is available
Co-authored-by: Piotr Mardziel <[email protected]>
* adjust docstring for select_context * langchain select_context, update quickstarts * undo app name change * remove dev cell * generalized langchain select_context (#711) * generalized langchain select_context * typo * typo in string * update langchain example to pass app in select_context --------- Co-authored-by: Josh Reini <[email protected]> * comments, clarity updates to quickstarts * add lib-independent select_context * update lc li quickstarts --------- Co-authored-by: Piotr Mardziel <[email protected]>
* add optional * bug class_info fix
* update configs * bugfix * dont add class info to dicts
* Fix correctness prompt Fixes #718 * Update base.py
…7-properly-handle-multiquery-retrieval
* add maintainers and releases files * add maintainers and releases to docs * add more maintainers and github names * more maintainers * add release process info * releases text
* fix expositional example colab links * fix notebook description of test cases
* first * delete instructions * static delete singleton instructions
Co-authored-by: Aaron <[email protected]>
* remove legacy db * change message for when legacy db is detected * nit * nits * remove unneeded * circular import avoid revert * nits * remove legacy db example * remove 2 more outdated databases * clean up removed db version references * remove one more old ref * remove last legacy db --------- Co-authored-by: Aaron <[email protected]>
* shuffling * update standard.md to mention python versions tested * de-circularizing * finishing up decircularization * fix imports in tests * more import fixes * more import fixes * updating docs and docstrings with new locations * add temp to bedrock and ignored warning * trying to remove circular import * more debugging * more fixes * more of the same * last few * missed on * nits * typo * fix feedbackmode imports * 2 more fixes
* Fixes to package build. * bump version
…las notebook update (#1097) * fix dividing by zero error * update notebook for webinar
* pin openai version for hackathon * runnable e2e * add migration guide
* oss models in app * import change * fix dims issue, pass embeddings manually * keep some output * remove settings print * link model list for cost tracking
… functions exist (#1108) --------- Co-authored-by: Josh Reini <[email protected]>
removed this so it's less confusing for newcomers
Co-authored-by: joshreini1 <[email protected]>
* azureopenai docstring * azureopenai.md * remove extra references to supported feedbacks * Update azureopenai.md
Co-authored-by: Josh Reini <[email protected]>
* fix link on langchain instrumentation docs * fix llama-index quickstart link * fix langchain instrumentation docs, add missing imports * add missing imports to nemo instrumentation docs
* fix rag triad and awaitable calls * remove locals printout in awaitables message
* fix rag triad and awaitable calls * remove locals printout in awaitables message * update __getattr__ in select_context (#1119) --------- Co-authored-by: Piotr Mardziel <[email protected]>
Co-authored-by: Josh Reini <[email protected]>
* Update feedback.py * use name
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.