-
Notifications
You must be signed in to change notification settings - Fork 2.3k
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
feat(openai): Make only AzureOpenAI respect Azure env vars, remove class defaults, update withStructuredOutput defaults #7535
Conversation
The latest updates on your projects. Learn more about Vercel for Git ↗︎
1 Skipped Deployment
|
CC @sinedied |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Can I ask why only moving the env vars and not all azure related properties, since it's a breaking change anyways? (Unless it's that's part of a multi-PR change, then ignore that). Just wondering what the goal is with this change, as it keeps the Azure compatibility with the base OpenAI class when using config property but breaks it when using env vars?
I might be wrong on this one, but should also be lc_secrets()
updated in the Azure implementation since the env vars are moved?
@sarangan12 any thoughts?
Yeah I think this is probably a good idea. CC @efriis |
The minor bump and removal of defaults will also enable #7564 |
Going to try to ship 0.4.0 today - @sinedied any other thoughts here? |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
looks good - some small nits if helpful but you understand better than me here
this.azureOpenAIApiVersion = | ||
fields?.azureOpenAIApiVersion ?? | ||
fields?.openAIApiVersion ?? | ||
getEnvironmentVariable("AZURE_OPENAI_API_VERSION"); |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
this feels funky - should we just update this.openAIApiVersion
?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
WDYM?
this.azureOpenAIApiDeploymentName = | ||
fields?.azureOpenAIApiDeploymentName ?? | ||
fields?.deploymentName ?? | ||
getEnvironmentVariable("AZURE_OPENAI_API_DEPLOYMENT_NAME"); |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
this is not in py but we should add it in py
* Rename auth method in docs * fix(core): Fix trim messages mutation bug (langchain-ai#7547) * release(core): 0.3.31 (langchain-ai#7548) * fix(community): Updated Embeddings URL (langchain-ai#7545) * fix(community): make sure guardrailConfig can be added even with anthropic models (langchain-ai#7542) * docs: Fix PGVectorStore import in install dependencies (TypeScript) example (langchain-ai#7533) * fix(community): Airtable url (langchain-ai#7532) * docs: Fix typo in OpenAIModerationChain example (langchain-ai#7528) * docs: Resolves langchain-ai#7483, resolves langchain-ai#7274 (langchain-ai#7505) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> * docs: Rename auth method in IBM docs (langchain-ai#7524) * docs: correct misspelling (langchain-ai#7522) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> * release(community): 0.3.25 (langchain-ai#7549) * feat(azure-cosmosdb): add session context for a user mongodb (langchain-ai#7436) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> * release(azure-cosmosdb): 0.2.7 (langchain-ai#7550) * fix(ci): Fix build (langchain-ai#7551) * feat(anthropic): Add Anthropic PDF support (document type) in invoke (langchain-ai#7496) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> * release(anthropic): 0.3.12 (langchain-ai#7552) * chore(core,langchain,community): Relax langsmith deps (langchain-ai#7556) * release(community): 0.3.26 (langchain-ai#7557) * release(core): 0.3.32 (langchain-ai#7558) * Release 0.3.12 (langchain-ai#7559) * fix(core): Prevent cache misses from triggering model start callback runs twice (langchain-ai#7565) * fix(core): Ensure that cached flag in run extras is only set for cache hits (langchain-ai#7566) * release(core): 0.3.33 (langchain-ai#7567) * feat(community): Adds graph_document to export list (langchain-ai#7555) Co-authored-by: quantropi-minh <101128605+quantropi-minh@users.noreply.github.com> Co-authored-by: jacoblee93 <jacoblee93@gmail.com> * fix(langchain): Fix ZeroShotAgent createPrompt with correct formatted tool names (langchain-ai#7510) * docs: Add document for AzureCosmosDBMongoChatMessageHistory (langchain-ai#7519) Co-authored-by: root <root@CPC-yangq-FRSGK> * fix(langchain): Allow pulling hub prompts with associated models (langchain-ai#7569) * fix(community,aws): Update handleLLMNewToken to include chunk metadata (langchain-ai#7568) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> * feat(community): Provide fallback relationshipType in case it is not present in graph_transformer (langchain-ai#7521) Co-authored-by: quantropi-minh <101128605+quantropi-minh@users.noreply.github.com> Co-authored-by: jacoblee93 <jacoblee93@gmail.com> * docs: Add redirect (langchain-ai#7570) * fix(langchain,core): Add shim for hub mustache templates with nested input variables (langchain-ai#7581) * fix(chat-models): honor disableStreaming even for `generateUncached` (langchain-ai#7575) * release(core): 0.3.34 (langchain-ai#7584) * feat(langchain): Add hub entrypoint with automatic dynamic entrypoint of models (langchain-ai#7583) * chore(ollama): Export `OllamaEmbeddingsParams` interface (langchain-ai#7574) * docs: Clarify tool creation process in structured outputs documentation (langchain-ai#7578) Co-authored-by: Sahar Shemesh <sahar.shemesh@zoominfo.com> Co-authored-by: jacoblee93 <jacoblee93@gmail.com> * fix(community): Set awaitHandlers to true in upstash ratelimit (langchain-ai#7571) Co-authored-by: Jacob Lee <jacoblee93@gmail.com> * fix(core): Fix trim messages mutation (langchain-ai#7585) * feat(openai): Make only AzureOpenAI respect Azure env vars, remove class defaults, update withStructuredOutput defaults (langchain-ai#7535) * fix(community): Make postgresConnectionOptions optional in PostgresRecordManager (langchain-ai#7580) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> * release(community): 0.3.27 (langchain-ai#7586) * release(ollama): 0.1.5 (langchain-ai#7587) * Release 0.3.13 (langchain-ai#7588) * release(openai): 0.4.0 (langchain-ai#7589) * release(core): 0.3.35 (langchain-ai#7590) * fix(ci): Update lock (langchain-ai#7591) * feat(core): Allow passing returnDirect in tool wrapper params (langchain-ai#7594) * release(core): 0.3.36 (langchain-ai#7595) * fix(openai): Revert Azure default withStructuredOutput changes (langchain-ai#7596) * release(openai): 0.4.1 (langchain-ai#7597) * feat(openai): Refactor to allow easier subclassing (langchain-ai#7598) * release(openai): 0.4.2 (langchain-ai#7599) * feat(deepseek): Adds Deepseek integration (langchain-ai#7604) * release(deepseek): 0.0.1 (langchain-ai#7608) * feat: update Novita AI doc (langchain-ai#7602) * Add deployment chat to chat class * feat(langchain): Add DeepSeek to initChatModel (langchain-ai#7609) * Release 0.3.14 (langchain-ai#7611) * fix: Add test for pdf uploads anthropic (langchain-ai#7613) * feat: Update google genai to support file uploads (langchain-ai#7612) * chore(google-genai): Drop .only in test (langchain-ai#7614) * release(google-genai): 0.1.7 (langchain-ai#7615) * Upadate Watsonx sdk * fix(core): Fix stream events bug when errors are thrown too quickly during iteration (langchain-ai#7617) * release(core): 0.3.37 (langchain-ai#7619) * fix(langchain): Fix Groq import for hub (langchain-ai#7620) * docs: update README/intro * Release 0.3.15 * feat(community): improve support for Tavily search tool args (langchain-ai#7561) * feat(community): Add boolean metadata type support in Supabase structured query translator (langchain-ai#7601) * feat(google-genai): Add support for fileUri in media type in Google GenAI (langchain-ai#7621) Co-authored-by: Jacob Lee <jacoblee93@gmail.com> * release(google-genai): 0.1.8 (langchain-ai#7628) * release(community): 0.3.28 (langchain-ai#7629) * Rework interfaces in llms as well * Bump watsonx-ai sdk version * Remove unused code * Add fake auth * Fix broken changes --------- Co-authored-by: Jacob Lee <jacoblee93@gmail.com> Co-authored-by: Jacky Chen <jackychen4@gmail.com> Co-authored-by: Mohamed Belhadj <medbelh@gmail.com> Co-authored-by: Brian Ploetz <bploetz@gmail.com> Co-authored-by: Eduard-Constantin Ibinceanu <ibinceanu.eduard@yahoo.com> Co-authored-by: Jonathan V <jonathanvelkeneers@hotmail.com> Co-authored-by: ucev <zhangshuaiyf@icloud.com> Co-authored-by: crisjy <cjy1994116@163.com> Co-authored-by: Adham Badr <adhambadr2@gmail.com> Co-authored-by: Minh Ha <hlminh2000@gmail.com> Co-authored-by: quantropi-minh <101128605+quantropi-minh@users.noreply.github.com> Co-authored-by: Chi Thu Le <thu2004@yahoo.se> Co-authored-by: fatmelon <708842811@qq.com> Co-authored-by: root <root@CPC-yangq-FRSGK> Co-authored-by: Mohamad Mohebifar <mohebifar@users.noreply.github.com> Co-authored-by: David Duong <david@duong.cz> Co-authored-by: Brace Sproul <braceasproul@gmail.com> Co-authored-by: Matus Gura <contact@matusgura.com> Co-authored-by: Sahar Shemesh <48128579+saharis9988@users.noreply.github.com> Co-authored-by: Sahar Shemesh <sahar.shemesh@zoominfo.com> Co-authored-by: Cahid Arda Öz <cahidardaooz@hotmail.com> Co-authored-by: Jason <ggbbddjm@gmail.com> Co-authored-by: vbarda <vadym@langchain.dev> Co-authored-by: Vadym Barda <vadim.barda@gmail.com> Co-authored-by: Hugo Borsoni <44852104+hugoleborso@users.noreply.github.com> Co-authored-by: Arman Ghazaryan <arm.ghazaryan01@gmail.com> Co-authored-by: Andy <andy+github@savage.hk>
summary of changes:
withStructuredOutput
method to bejsonSchema
for models that support it