refactor: RAG Refactor (#985)

Co-authored-by: Aralhi <xiaoping0501@gmail.com>
Co-authored-by: csunny <cfqsunny@163.com>

examples/rag/embedding_rag_example.py

@@ -0,0 +1,53 @@
+import asyncio
+
+from dbgpt.rag.chunk_manager import ChunkParameters
+from dbgpt.rag.embedding.embedding_factory import DefaultEmbeddingFactory
+from dbgpt.rag.knowledge.factory import KnowledgeFactory
+from dbgpt.serve.rag.assembler.embedding import EmbeddingAssembler
+from dbgpt.storage.vector_store.chroma_store import ChromaVectorConfig
+from dbgpt.storage.vector_store.connector import VectorStoreConnector
+
+"""Embedding rag example.
+    pre-requirements:
+    set your embedding model path in your example code.
+    ```
+    embedding_model_path = "{your_embedding_model_path}"
+    ```
+
+    Examples:
+        ..code-block:: shell
+            python examples/rag/embedding_rag_example.py
+"""
+
+
+async def main():
+    file_path = "./docs/docs/awel.md"
+    vector_persist_path = "{your_persist_path}"
+    embedding_model_path = "{your_embedding_model_path}"
+    knowledge = KnowledgeFactory.from_file_path(file_path)
+    vector_connector = VectorStoreConnector.from_default(
+        "Chroma",
+        vector_store_config=ChromaVectorConfig(
+            name="vector_name",
+            persist_path=vector_persist_path,
+        ),
+        embedding_fn=DefaultEmbeddingFactory(
+            default_model_name=embedding_model_path
+        ).create(),
+    )
+    chunk_parameters = ChunkParameters(chunk_strategy="CHUNK_BY_SIZE")
+    # get embedding assembler
+    assembler = EmbeddingAssembler.load_from_knowledge(
+        knowledge=knowledge,
+        chunk_parameters=chunk_parameters,
+        vector_store_connector=vector_connector,
+    )
+    assembler.persist()
+    # get embeddings retriever
+    retriever = assembler.as_retriever(3)
+    chunks = await retriever.aretrieve_with_scores("RAG", 0.3)
+    print(f"embedding rag example results:{chunks}")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())