pass through openai model params #864
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
request by pinecone devrel for hackathon
* Add files via upload * colab link
* adding more instruments to llama_index agents * added memory to llama index instrumentation, documenting todo for how to keep track on dynamically created instances * adjustments to calls layout * remove debug stuff from llama agents example * update the correct notebook * remove old * final fixes * change default key set method * update langchain and remove old unusued class to instrument --------- Co-authored-by: rshih32 <[email protected]> Co-authored-by: Josh Reini <[email protected]>
* starting example notebook * example and bugfix to queue full * minor * typo * working on jupyter app runner * prototype app ui * prototyping app ui * working on async in app ui * add appui example notebook * rest of jsonpath parsing * remove uneeded * add dev note * update notebooks * moved notebooks * remove old notebook * format * mismerges * add warning * bugfix and more selectors for appui example * remove uneeded * more unneeded * nit * add stdpipes widgets to ui * minor changes
* update version * fix import warning * fix logger dep warning * update link
* hotfix confusing prompt * version upgrade * fix combine script and generate files * fix colabs --------- Co-authored-by: rick <[email protected]>
Co-authored-by: rshih32 <[email protected]>
* pin python to 3.11 since currently not working on 3.12 * conda version
* initial commit * optional sklearn * add import logic * do not use default coloring for distance metrics * fix format
* add sql params * add comment
Co-authored-by: Josh Reini <[email protected]>
* litellm import inside class, not requirement * drop import from endpoint
* starting example notebook * example and bugfix to queue full * minor * typo * working on jupyter app runner * prototype app ui * prototyping app ui * working on async in app ui * add appui example notebook * rest of jsonpath parsing * remove uneeded * starting work * work * work * add dev note * update notebooks * moved notebooks * remove old notebook * format * mismerges * add warning * streamlit ui work * bugfixing TP, split later into another PR * added selectors to ui * multiple apps bug * nit * more comments * jsonify for ui in apps * added llama_index to streamlit app running * added llama_index to jupyer appui example * removing unrelated for another PR * remove the rest of unrelated * put back accidental deletions --------- Co-authored-by: rshih32 <[email protected]>
* organizaing existing feedback functions under each provider type * misc * work * work * moving feedback reorg into feedback/v2 * readme * updating pointers to v2 * static help function * the rest of openai moderation * moved more prompts * small fixes * update litellm version
* Fix output errors for windows * Update text.py --------- Co-authored-by: Shayak Sen <[email protected]> Co-authored-by: rshih32 <[email protected]>
* starting example notebook * example and bugfix to queue full * minor * typo * working on jupyter app runner * prototype app ui * prototyping app ui * working on async in app ui * add appui example notebook * rest of jsonpath parsing * remove uneeded * starting work * work * work * add dev note * update notebooks * moved notebooks * remove old notebook * format * mismerges * add warning * streamlit ui work * bugfixing TP, split later into another PR * added selectors to ui * multiple apps bug * nit * more comments * jsonify for ui in apps * added llama_index to streamlit app running * added llama_index to jupyer appui example * remove things for another pr * remove unrelated * remove old * jsonify adjustments for appuis * remove unneeded * more docs in streamlit app ui notebook * added example selectors for llama index appui * remove TODO printouts and up the serialization size limit for loaders * add humanize to requirement --------- Co-authored-by: rshih32 <[email protected]>
* use cases guide structure * update guide structure * spacing * nits * azure and bedrock links * model comparison * moderation * moderation update * update imports * langmatch * any use case * update llama quickstart * rag use cases * production use cases * md update * title update azure
* bedrock as model * bedrock provider * move bedrock notebook * update for bedrock ga * bedrock as a provider * move boto3 import to inside class * update rest of feedbacks * bedrock provider to docks * remove dup code * add overrides to requirements * remove dup code * remove dupe code * usage examples in docstrings * import fixes * add base provider to docs * remove override * split up feedbacks and providers in docs * provider api in docs
Co-authored-by: joshreini1 <[email protected]> Co-authored-by: rshih32 <[email protected]>
* starting example notebook * example and bugfix to queue full * minor * typo * working on jupyter app runner * prototype app ui * prototyping app ui * working on async in app ui * add appui example notebook * rest of jsonpath parsing * remove uneeded * starting work * work * work * add dev note * update notebooks * moved notebooks * remove old notebook * format * mismerges * add warning * streamlit ui work * bugfixing TP, split later into another PR * added selectors to ui * multiple apps bug * nit * more comments * jsonify for ui in apps * added llama_index to streamlit app running * added llama_index to jupyer appui example * remove things for another pr * remove unrelated * remove old * jsonify adjustments for appuis * first * basic and custom appui and double records bugfix * remove notebook outputs --------- Co-authored-by: rshih32 <[email protected]>
* pii detection feedback * update * 1- score * docstrings * move pii detection to exp * pii detection in user guides
* bump version * fix depending on hugs return
* version bump combine nb to docs * hotfix
* first try * starting feedback imp tests * working on feedback tests * nits * more tests * more adjustments * disable unit tests for now * added in-domain tests variants to run for now
* bump versions * combine_docs * truvirtual api ref * fix docstring formatting tru_virtual
Co-authored-by: joshreini1 <[email protected]>
* copy from another slower PR * add req
Co-authored-by: Josh Reini <[email protected]>
* copy updates * nav changes, replace welcome with home * merge conflict fix * remove welcome.md * nav updates * fix linking * remove nav sections and tabs * shift emojis to higher level
Co-authored-by: joshreini1 <[email protected]>
* update azure example, also show provider extension * update trulens version * remove force dashboard * add score-only example * custom feedback docs * refactor for user-facing generate_score and generate_score_and_reasons methods * update azure example with more user-friendly methods * update bedrock with more user-friendly methods * user friendly methods for provider extension * types in docstring
* first * CI update * global import static test * disable py312 test * add nltk optional fix * remove unrelated * add format and python bound * nit * adjust matrix cell name for ordering * spec * disable tests when optional package not installed * adjust ci script * syntax issues * typo * test * remove more * newline * name first * comment * nit * matrix no sequences * remove duplicate matrix cell * displayname again * unexpected symbol * hmm * fix test import * optional tests marking * imports tests * few more ellipses * remove non-existant import * expected error * fixing optionals * message on subtest * add subtests requirement * fix discovered import bugs * more fixes * adjust ipython requirement * downgrade bound even more for python 3.9 * more fixes * ipython fix * remove ipykernel installation in unit tests * change pr job name * name * more informative tests name * rename optional var and renable format condition * cond try fix * nit * again --------- Co-authored-by: Josh Reini <[email protected]>
#839) Bumps [vite](https://github.com/vitejs/vite/tree/HEAD/packages/vite) from 4.4.2 to 4.5.2. - [Release notes](https://github.com/vitejs/vite/releases) - [Changelog](https://github.com/vitejs/vite/blob/v4.5.2/packages/vite/CHANGELOG.md) - [Commits](https://github.com/vitejs/vite/commits/v4.5.2/packages/vite) --- updated-dependencies: - dependency-name: vite dependency-type: direct:development ... Signed-off-by: dependabot[bot] <[email protected]> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Josh Reini <[email protected]>
* make more tests pass * small changes * more tests working * skip moderation * test for multiple models * more passing * unused e removed * fix typing issues * more cot tests * incorrect prompt * more cot reasons tests * stereotypes more extreme * improve stereotyping prompt * typo * unittest only gpt-3.5-turbo * add missing import * mark calibration as optional test * fix typo * move oai import to top[] * oai imports for all testss
* bump * bump
Co-authored-by: joshreini1 <[email protected]>
* debug why static tests did not fail * check more base modules * update module hierarchy doc and delete another deprecated module * trubot is optional * don't try to run a script in static tests * Don't try to import migrations env * typo * nit * cleanup and assertion failure messages * pinecone optional message * update pinecone usage * note
* prototype * update md * fix run_feedback * update * update * update
* replaced threaded pacer * remove unused method * dep note * revert nonneeded * typo * typo * args/kwargs debugging * add api env to pipeline definition for when running optional tests * typos * typo
* added more fake behaviour to dummy app and dummy endpoint * dummy testing * typo * update feedback_result usage in notebooks * clean up imports * revert unneeded * make format * nits to dummy example testing * format * nits to satisfy pydantic * adding a wait for pending feedback for entire app * renamed * bugfix race * reenable tests that were async and never awaited * remove dotdotdot for python 3.9 * more dotdotdots * adding nest_asyncio to reqs and trying to use fewer desync calls * adding unit tests * cleanup * forgot typevar * add fake parameterizable Queue type * more unit tests * more Tru class testing * fix bad merge * nits * change llama test example * nits and move chain tests to optional requirements * nits * update langchain usage * several more outdated uses * update optional requirements * organize imports * remove old * cleanup requirements files * fix ipywidgets import test * add note * typo again ... * another deprecating call * fighting the import organizer * make pending feedback manager non-parent-blocking * remove thread * remove another non-needed * revert accidental delete --------- Co-authored-by: Josh Reini <[email protected]>
Co-authored-by: piotrm0 <[email protected]>
streamlit deprecating in april, producing ugly warning now
* first * fix pinecone package name * adjust progress and add dummy provider delay option --------- Co-authored-by: Josh Reini <[email protected]>
* input/output schema depend on model provider within bedrock * fix ai21, change meta to not implemented due to inability to complete task * remove unneeded * change meta not implemented to else condition * more helpful error message
* fix st.query_params * bump streamlit version
* version bump * misssed version bump * bump py_script quickstarts * typo --------- Co-authored-by: Piotr Mardziel <[email protected]>
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.
No description provided.