Null filepath and URL in Azure OpenAI Response using chatCompletions

[hind214875]

Null filepath and URL in Azure OpenAI Response using chatCompletions

[joshfree]

Thanks for sharing this beta feedback @hind214875 -- @mssfang can you please follow up?

[mssfang]

Thank you for reporting this issue. @hind214875
Can you try update pom dependency as below?

<dependencies>
   <dependency>
     <groupId>com.azure</groupId>
     <artifactId>azure-ai-openai</artifactId>
     <version>1.0.0-beta.6</version>
   </dependency>

   <dependency>
     <groupId>com.azure</groupId>
     <artifactId>azure-search-documents</artifactId>
     <version>11.6.0-beta.7</version>
     <exclusions>
         <exclusion>
             <groupId>com.azure</groupId>
             <artifactId>azure-core-serializer-json-jackson</artifactId>
         </exclusion>
     </exclusions>
   </dependency>
 </dependencies>

[github-actions]

Hi @hind214875. Thank you for opening this issue and giving us the opportunity to assist. To help our team better understand your issue and the details of your scenario please provide a response to the question asked above or the information requested above. This will help us more accurately address your issue.

[hind214875]

Hi mssfang!
Thank you for your reply, but unfortunately it is still not working.

[mssfang]

Hi mssfang! Thank you for your reply, but unfortunately it is still not working.

Thanks for the try out. Is possible we can have a sample code that can reproduce this issue?

[mssfang]

Is possible we can have a sample code from your side that can use to reproduce the issue?

I have tried to use following codesnippet to reproduce the issue but find there is able to get the URL and filePath.

String azureSearchIndexName = "openai-test-index-carbon-wiki"; // "hotels-vector-sample-index"

        AzureCognitiveSearchChatExtensionConfiguration searchConfiguration =
                new AzureCognitiveSearchChatExtensionConfiguration(
                        new AzureCognitiveSearchChatExtensionParameters(azureSearchEndpoint, azureSearchIndexName)
                                .setAuthentication(new OnYourDataApiKeyAuthenticationOptions(azureSearchAdminKey))
                                .setQueryType(AzureCognitiveSearchQueryType.SIMPLE) // SIMPLE, VECTOR, or Hybrid
                                .setInScope(true)
                                .setTopNDocuments(2)
                                // the deployment name of the embedding model when you are using a vector or hybrid query type
                                .setEmbeddingDependency(new OnYourDataDeploymentNameVectorizationSource("text-embedding-ada-002"))
                                .setFieldsMapping(
                                        new AzureCognitiveSearchIndexFieldMappingOptions()
                                                .setFilepathField("setupwinenv.md")
                                )
                );

        String question = "How to build carbon on Windows";
        List<ChatRequestMessage> chatMessages = new ArrayList<>();
        chatMessages.add(new ChatRequestUserMessage(question));
        ChatCompletionsOptions chatCompletionsOptions = new ChatCompletionsOptions(chatMessages)
                .setDataSources(Arrays.asList(searchConfiguration));

        ChatCompletions chatCompletions = client.getChatCompletions(deploymentOrModelId, chatCompletionsOptions);

        System.out.println("Question: " + question);
        for (ChatChoice choice : chatCompletions.getChoices()) {
            ChatResponseMessage message = choice.getMessage();
            System.out.printf("Answer: %s%n%n", message.getContent());
            // If Azure OpenAI chat extensions are configured, this array represents the incremental steps performed
            // by those extensions while processing the chat completions request.
            List<ChatResponseMessage> contextMessages = message.getContext().getMessages();
            for (ChatResponseMessage contextMessage : contextMessages) {
                System.out.println("Context Message: ");
                System.out.println("   - " + contextMessage.getContent());
            }
        }

Hi mssfang! Thank you for your reply, but unfortunately it is still not working.

[github-actions]

Hi @hind214875. Thank you for opening this issue and giving us the opportunity to assist. To help our team better understand your issue and the details of your scenario please provide a response to the question asked above or the information requested above. This will help us more accurately address your issue.

[github-actions]

Hi @hind214875, we're sending this friendly reminder because we haven't heard back from you in 7 days. We need more information about this issue to help address it. Please be sure to give us your input. If we don't hear back from you within 14 days of this comment the issue will be automatically closed. Thank you!

[hind214875]

Hi mssfang!

Sorry for the late replay, I actually tested yesterday again and this time it works i didn't change anything so i don't really know why it works now. Thank you for your help :)

[mssfang]

@hind214875 Glad to see that works. BTW, we have a new beta, beta.7 released that includes some breaking change and new features Text-to-Speech.

[github-actions]

Hi @hind214875. Thank you for opening this issue and giving us the opportunity to assist. We believe that this has been addressed. If you feel that further discussion is needed, please add a comment with the text "/unresolve" to remove the "issue-addressed" label and continue the conversation.