feat(models)!: openAI 1.0 #1716
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
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
Co-authored-by: Xander Song <axiomofjoy@gmail.com>
Co-authored-by: Xander Song <axiomofjoy@gmail.com>
Co-authored-by: Xander Song <axiomofjoy@gmail.com>
Co-authored-by: Xander Song <axiomofjoy@gmail.com>
Co-authored-by: Xander Song <axiomofjoy@gmail.com>
Co-authored-by: Xander Song <axiomofjoy@gmail.com>
Co-authored-by: Xander Song <axiomofjoy@gmail.com>
Co-authored-by: Xander Song <axiomofjoy@gmail.com>
Co-authored-by: Xander Song <axiomofjoy@gmail.com>
Co-authored-by: Xander Song <axiomofjoy@gmail.com>
Co-authored-by: Xander Song <axiomofjoy@gmail.com>
axiomofjoy
reviewed
Nov 10, 2023
Comment on lines
+102
to
+103
| with patch.object(OpenAIModel, "_init_tiktoken", return_value=None): | ||
| model = OpenAIModel(max_retries=0) |
There was a problem hiding this comment.
Curious why need to patch this method here but not elsewhere?
There was a problem hiding this comment.
I'm not sure I know the other places you are referring to but the unfortunate side-effect is that tiktoken makes network calls so it fails in an isolated CI env. Yet another reason we probably shouldn't have this initialization as part of the construction process, let alone maybe be a part of the model.
anticorrelator
requested changes
Nov 10, 2023
anticorrelator
approved these changes
Nov 10, 2023
mikeldking
added a commit
that referenced
this pull request
Nov 13, 2023
* git output via openai migrate * WIP * git output via openai migrate WIP * get pytests running * get pytests running * completions changes * fix llm_classify tests * fix llm generate tests * minimal test for openai * fix llama_index tests * add back model * fix openai * fix openai tests * Add explanations section for relevance * run GPT4-Turbo * update notebooks * migrate find clusters notebook * update more notebooks * fix relevance * fix tutorials/llm_generative_gpt_4.ipynb * add more tutorials * Start refactoring httpx tests to be order-agnostic * Finish refactoring classification tests * Refactor `generate` tests to be order-agnostic * Migrate to respx for langchain tracer tests * Update openai tracing tests to use respx * feat(evals): azure openai support * address pr comments * return early for azure * fix tiktoken failures * remove model name aliasing * make gpt-4 point to latest * ruff format * docs: update documentation * feat: update OpenAIInstrumentor to support openai>=1.0.0 and deprecate support for openai<1.0.0 (#1723) * correct unit test to mock completions endpoint (#1730) * Update langchain_pinecone_search_and_retrieval_tutorial.ipynb Co-authored-by: Xander Song <axiomofjoy@gmail.com> * Update llama_index_search_and_retrieval_tutorial.ipynb Co-authored-by: Xander Song <axiomofjoy@gmail.com> * Update llm_generative_gpt_4.ipynb Co-authored-by: Xander Song <axiomofjoy@gmail.com> * Update milvus_llamaindex_search_and_retrieval_tutorial.ipynb Co-authored-by: Xander Song <axiomofjoy@gmail.com> * Update ragas_retrieval_evals_tutorial.ipynb Co-authored-by: Xander Song <axiomofjoy@gmail.com> * Update langchain_agent_tracing_tutorial.ipynb Co-authored-by: Xander Song <axiomofjoy@gmail.com> * Update langchain_tracing_tutorial.ipynb Co-authored-by: Xander Song <axiomofjoy@gmail.com> * Update llama_index_openai_agent_tracing_tutorial.ipynb Co-authored-by: Xander Song <axiomofjoy@gmail.com> * Update llama_index_tracing_tutorial.ipynb Co-authored-by: Xander Song <axiomofjoy@gmail.com> * Update langchain_retrieval_qa_with_sources_chain_tracing_tutorial.ipynb Co-authored-by: Xander Song <axiomofjoy@gmail.com> * Update find_cluster_export_and_explore_with_gpt.ipynb Co-authored-by: Xander Song <axiomofjoy@gmail.com> * Update evaluate_toxicity_classifications.ipynb Co-authored-by: Xander Song <axiomofjoy@gmail.com> * Update evaluate_summarization_classifications.ipynb Co-authored-by: Xander Song <axiomofjoy@gmail.com> * Update evaluate_QA_classifications.ipynb Co-authored-by: Xander Song <axiomofjoy@gmail.com> * Update evaluate_hallucination_classifications.ipynb Co-authored-by: Xander Song <axiomofjoy@gmail.com> * Update evaluate_code_readability_classifications.ipynb Co-authored-by: Xander Song <axiomofjoy@gmail.com> * document breaking changes, bump langchain * add more details to the breaking changes * langchain bump * fix qa evals notebook * fix style * update major version * remove logging token count warnings --------- Co-authored-by: Dustin Ngo <dustin@arize.com> Co-authored-by: Xander Song <axiomofjoy@gmail.com>
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.
resolves #1715
Updates everything to OpenAI 1.0
requestsandresponses@anticorrelatorDocumentation
request_timeoutparameterManual tests
Regression Testing