[Bug] [storage] wrong config in VectorStoreConnector

[FOkvj]

Search before asking

• I had searched in the issues and found no similar issues.

Operating system information

Linux

Python version information

3.10

DB-GPT version

latest release

Related scenes

• Chat Data
• Chat Excel
• Chat DB
• Chat Knowledge
• Model Management
• Dashboard
• Plugins

Installation Information

• Installation From Source

• Docker Installation

• Docker Compose Installation

• Cluster Installation

• AutoDL Image

• Other

Device information

Device:CPU

Models information

no

What happened

connector = VectorStoreConnector.from_default(
        "Chroma",
        vector_store_config=ElasticsearchVectorConfig(index_name="test" ),
        embedding_fn=DefaultEmbeddingFactory(
            default_model_name=os.path.join(MODEL_PATH, "text2vec-large-chinese"),
        ).create(),
    )

1. when you create a specific VectorStoreConnector, likes ElasticsearchVectorConfig.
2. the param index_name would not be set in the connector correctly.

What you expected to happen

The code in the second picture is wrong and unnecessary. The Variable config would miss some fields in vector_store_config, like index_name in ElasticsearchVectorConfig.

How to reproduce

connector = VectorStoreConnector.from_default(
        "Chroma",
        vector_store_config=ElasticsearchVectorConfig(index_name="test" ),
        embedding_fn=DefaultEmbeddingFactory(
            default_model_name=os.path.join(MODEL_PATH, "text2vec-large-chinese"),
        ).create(),
    )

2. debug at dbgpt/storage/vector_store/elastic_store.py, line 128
3. you will find out the value of index_name is not "test" but the default value "index_name_test"

Additional context

the vector_store_config of "KnowledgeGraph" should be BuiltinKnowledgeGraphConfig but not VectorStoreConfig

Are you willing to submit PR?

• Yes I am willing to submit a PR!