Semantic configuration is not created for Azure AI Search index using Langchain community.

Checked other resources

[X] I added a very descriptive title to this issue.
[X] I searched the LangChain documentation with the integrated search.
[X] I used the GitHub search to find a similar question and didn't find it.
[X] I am sure that this is a bug in LangChain rather than my code.
[X] The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).

Example Code

from langchain.vectorstores.azuresearch import AzureSearch
from azure.search.documents.indexes.models import (
    FreshnessScoringFunction,
    FreshnessScoringParameters,
    ScoringProfile,
    SearchableField,
    SearchField,
    SearchFieldDataType,
    SimpleField,
    TextWeights,
    SemanticConfiguration,
    SemanticPrioritizedFields,
    SemanticField
)

 fields = [
                SimpleField(
                    name="id",
                    type=SearchFieldDataType.String,
                    key=True,
                    filterable=True,
                ),
                SearchableField(
                    name="header1",
                    type=SearchFieldDataType.String,
                    searchable=True,
                ),
                 SearchableField(
                    name="header2",
                    type=SearchFieldDataType.String,
                    searchable=True,
                ), SearchableField(
                    name="header3",
                    type=SearchFieldDataType.String,
                    searchable=True,
                ),
                SearchableField(
                    name="content",
                    type=SearchFieldDataType.String,
                    searchable=True,
                ),
                SearchField(
                    name="content_vector",
                    type=SearchFieldDataType.Collection(SearchFieldDataType.Single),
                    searchable=True,
                    vector_search_dimensions=len(aoai_embeddings.embed_query("Text")),
                    vector_search_profile_name="myExhaustiveKnnProfile",
                ),
                SearchableField(
                    name="metadata",
                    type=SearchFieldDataType.String,
                    searchable=True,
                ),
            ]

 index_name: str = vector_store_index
    # Adding a custom scoring profile with a freshness function
    sc_name = "csrd_scoring_profile"
    sc = ScoringProfile(
        name=sc_name,
        text_weights=TextWeights(weights={
            "header1": 10,
            "header2": 9,
            "content": 8,
            "content_vector": 8
            }),
        function_aggregation="sum"
    )

 semantic_configuration_name = 'my_semantic_configuration'
    semantic_config = SemanticConfiguration(
        name=semantic_configuration_name,
        prioritized_fields=SemanticPrioritizedFields(
            title_field=SemanticField(field_name='header2'),
            content_fields=[SemanticField(field_name='content')],
            keywords_fields=None,
        )
    )

    vector_store: AzureSearch = AzureSearch(
        search_type='semantic_hybrid',
        scoring_profiles=[sc],
        default_scoring_profile=sc_name,
        semantic_configurations=[semantic_config],
        semantic_configuration_name=semantic_configuration_name,
        azure_search_endpoint=vector_store_address,
        azure_search_key=vector_store_password,
        index_name=index_name,
        embedding_function=aoai_embeddings.embed_query,
        fields=fields,
    )

Error Message and Stack Trace (if applicable)

There is no error but semantic configuration is not created for index.

Description

Semantic configuration is not created for Azure AI Search index using Langchain community if both semantic config name and semantic configuration is provided.

When I checked in AzureSearch.py, I found below snippet which creates the semantic configuration.

# Create the semantic settings with the configuration
        semantic_search = None
        if semantic_configurations is None and semantic_configuration_name is not None:
            semantic_configuration = SemanticConfiguration(
                name=semantic_configuration_name,
                prioritized_fields=SemanticPrioritizedFields(
                    content_fields=[SemanticField(field_name=FIELDS_CONTENT)],
                ),
            )
            semantic_search = SemanticSearch(configurations=[semantic_configuration])

         # Create the search index with the semantic settings and vector search
        index = SearchIndex(
            name=index_name,
            fields=fields,
            vector_search=vector_search,
            semantic_search=semantic_search,
            scoring_profiles=scoring_profiles,
            default_scoring_profile=default_scoring_profile,
            cors_options=cors_options,
        )
        index_client.create_index(index)

if you observe, it create semantic config if semantic configuration is None and semantic configuration is not None only. else condition is not specified if both configuration and configuration name is present.

System Info

System Information

OS: Windows OS Version: 10.0.20348 Python Version: 3.11.6 (tags/v3.11.6:8b6ee5b, Oct 2 2023, 14:57:12) [MSC v.1935 64 bit (AMD64)]

Package Information

langchain_core: 0.1.27 langchain: 0.1.8 langchain_community: 0.0.24 langsmith: 0.1.10 langchain_openai: 0.0.8 langchainhub: 0.1.14

Packages not installed (Not Necessarily a Problem)

The following packages were not found:

langgraph langserve

langchain-ai / langchain