chore: update create chroma store param (#2798)

docs/docs/agents/modules/memory/hybrid_memory.md

@@ -57,12 +57,10 @@ from dbgpt_ext.storage.vector_store.chroma_store import ChromaVectorConfig, Chro
 shutil.rmtree("/tmp/tmp_ltm_vector_store", ignore_errors=True)
 vector_store = ChromaStore(
     ChromaVectorConfig(
-        embedding_fn=embeddings,
-        vector_store_config=ChromaVectorConfig(
-            name="ltm_vector_store",
         persist_path="/tmp/tmp_ltm_vector_store",
     ),
-    )
+    name="ltm_vector_store",
+    embedding_fn=embeddings
 )
 ```
 

docs/docs/agents/modules/memory/long_term_memory.md

@@ -47,13 +47,11 @@ from dbgpt_ext.storage.vector_store.chroma_store import ChromaVectorConfig, Chro
 # Delete old vector store directory(/tmp/tmp_ltm_vector_stor)
 shutil.rmtree("/tmp/tmp_ltm_vector_store", ignore_errors=True)
 vector_store = ChromaStore(
-    ChromaVectorConfig(
-        embedding_fn=embeddings,
     vector_store_config=ChromaVectorConfig(
-            name="ltm_vector_store",
         persist_path="/tmp/tmp_ltm_vector_store",
     ),
-    )
+    name="ltm_vector_store",
+    embedding_fn=embeddings,
 )
 ```
 

docs/docs/awel/cookbook/first_rag_with_awel.md

@@ -11,7 +11,7 @@ In this example, we will load your knowledge from a URL and store it in a vector
 First, you need to install the `dbgpt` library.
 
 ```bash
-pip install "dbgpt[rag]>=0.5.2"
+pip install "dbgpt[agent,simple_framework, client]>=0.7.1" "dbgpt_ext>=0.7.1" -U
 ````
 
 ### Prepare Embedding Model
@@ -84,11 +84,11 @@ shutil.rmtree("/tmp/awel_rag_test_vector_store", ignore_errors=True)
 
 vector_store = ChromaStore(
     vector_store_config=ChromaVectorConfig(
+        persist_path="/tmp/awel_rag_test_vector_store"
+    ),
     name="test_vstore",
-        persist_path="/tmp/awel_rag_test_vector_store",
     embedding_fn=embeddings
 )
-)
 
 with DAG("load_knowledge_dag") as knowledge_dag:
     # Load knowledge from URL
@@ -274,10 +274,10 @@ shutil.rmtree("/tmp/awel_rag_test_vector_store", ignore_errors=True)
 
 vector_store = ChromaStore(
     vector_store_config=ChromaVectorConfig(
-        name="test_vstore",
         persist_path="/tmp/awel_rag_test_vector_store",
-        embedding_fn=embeddings
     ),
+    name="test_vstore",
+    embedding_fn=embeddings
 )
 
 with DAG("load_knowledge_dag") as knowledge_dag:

docs/docs/awel/cookbook/write_your_chat_database.md

@@ -29,7 +29,8 @@ In this guide, we mainly focus on step 1, 2, and 3.
 First, you need to install the `dbgpt` library.
 
 ```bash
-pip install "dbgpt[rag]>=0.7.0" -U
+pip install "dbgpt[rag, agent, client, simple_framework]>=0.7.0" "dbgpt_ext>=0.7.0" -U
+pip install openai
 ````
 
 ## Build Knowledge Base
@@ -92,17 +93,17 @@ shutil.rmtree("/tmp/awel_with_data_vector_store", ignore_errors=True)
 vector_store = ChromaStore(
     ChromaVectorConfig(
         persist_path="/tmp/tmp_ltm_vector_store",
+    ),
     name="ltm_vector_store",
     embedding_fn=embeddings,
 )
-)
 
 with DAG("load_schema_dag") as load_schema_dag:
     input_task = InputOperator.dummy_input()
     # Load database schema to vector store
     assembler_task = DBSchemaAssemblerOperator(
         connector=db_conn,
-        index_store=vector_store,
+        table_vector_store_connector=vector_store,
         chunk_parameters=ChunkParameters(chunk_strategy="CHUNK_BY_SIZE")
     )
     input_task >> assembler_task
@@ -122,7 +123,8 @@ with DAG("retrieve_schema_dag") as retrieve_schema_dag:
     # Retrieve database schema from vector store
     retriever_task = DBSchemaRetrieverOperator(
         top_k=1,
-        index_store=vector_store,
+        table_vector_store_connector=vector_store,
+        field_vector_store_connector=vector_store
     )
     input_task >> retriever_task
 
@@ -487,10 +489,10 @@ db_conn.create_temp_tables(
 
 vector_store = ChromaStore(
     ChromaVectorConfig(
+        persist_path="/tmp/awel_with_data_vector_store",
+    ),
     embedding_fn=embeddings,
     name="db_schema_vector_store",
-        persist_path="/tmp/awel_with_data_vector_store",
-    )
 )
 
 antv_charts = [
@@ -623,7 +625,7 @@ with DAG("load_schema_dag") as load_schema_dag:
     # Load database schema to vector store
     assembler_task = DBSchemaAssemblerOperator(
         connector=db_conn,
-        index_store=vector_store,
+        table_vector_store_connector=vector_store,
         chunk_parameters=ChunkParameters(chunk_strategy="CHUNK_BY_SIZE"),
     )
     input_task >> assembler_task

examples/awel/simple_nl_schema_sql_chart_example.py

@@ -51,16 +51,16 @@ INPUT_PROMPT = "\n###Input:\n{}\n###Response:"
 
 def _create_vector_connector():
     """Create vector connector."""
-    config = ChromaVectorConfig(
+    config = ChromaVectorConfig(persist_path=PILOT_PATH)
-        persist_path=PILOT_PATH,
+
+    return ChromaStore(
+        config,
         name="embedding_rag_test",
         embedding_fn=DefaultEmbeddingFactory(
             default_model_name=os.path.join(MODEL_PATH, "text2vec-large-chinese"),
         ).create(),
     )
 
-    return ChromaStore(config)
-
 
 def _create_temporary_connection():
     """Create a temporary database connection for testing."""

examples/sdk/chat_data_with_awel.py

@@ -60,12 +60,12 @@ db_conn.create_temp_tables(
     }
 )
 
-config = ChromaVectorConfig(
+config = ChromaVectorConfig(persist_path=PILOT_PATH)
-    persist_path=PILOT_PATH,
+vector_store = ChromaStore(
+    config,
     name="db_schema_vector_store",
     embedding_fn=embeddings,
 )
-vector_store = ChromaStore(config)
 
 antv_charts = [
     {"response_line_chart": "used to display comparative trend analysis data"},

packages/dbgpt-core/src/dbgpt/agent/core/memory/hybrid.py

@@ -94,12 +94,10 @@ class HybridMemory(Memory, Generic[T]):
         vstore_path = vstore_path or os.path.join(DATA_DIR, "agent_memory")
 
         vector_store = ChromaStore(
-            ChromaVectorConfig(
+            ChromaVectorConfig(persist_path=vstore_path),
             name=vstore_name,
-                persist_path=vstore_path,
             embedding_fn=embeddings,
         )
-        )
         return cls.from_vstore(
             vector_store=vector_store,
             embeddings=embeddings,