remove milvus from RAG

metagpt/rag/factories/index.py

@@ -8,7 +8,6 @@ from llama_index.core.vector_stores.types import BasePydanticVectorStore
 from llama_index.vector_stores.chroma import ChromaVectorStore
 from llama_index.vector_stores.elasticsearch import ElasticsearchStore
 from llama_index.vector_stores.faiss import FaissVectorStore
-from llama_index.vector_stores.milvus import MilvusVectorStore
 
 from metagpt.rag.factories.base import ConfigBasedFactory
 from metagpt.rag.schema import (
@@ -18,7 +17,6 @@ from metagpt.rag.schema import (
     ElasticsearchIndexConfig,
     ElasticsearchKeywordIndexConfig,
     FAISSIndexConfig,
-    MilvusIndexConfig,
 )
 
 
@@ -30,7 +28,6 @@ class RAGIndexFactory(ConfigBasedFactory):
             BM25IndexConfig: self._create_bm25,
             ElasticsearchIndexConfig: self._create_es,
             ElasticsearchKeywordIndexConfig: self._create_es,
-            MilvusIndexConfig: self._create_milvus,
         }
         super().__init__(creators)
 
@@ -49,11 +46,6 @@ class RAGIndexFactory(ConfigBasedFactory):
 
         return self._index_from_storage(storage_context=storage_context, config=config, **kwargs)
 
-    def _create_milvus(self, config: MilvusIndexConfig, **kwargs) -> VectorStoreIndex:
-        vector_store = MilvusVectorStore(collection_name=config.collection_name, uri=config.uri, token=config.token)
-
-        return self._index_from_vector_store(vector_store=vector_store, config=config, **kwargs)
-
     def _create_chroma(self, config: ChromaIndexConfig, **kwargs) -> VectorStoreIndex:
         db = chromadb.PersistentClient(str(config.persist_path))
         chroma_collection = db.get_or_create_collection(config.collection_name, metadata=config.metadata)

metagpt/rag/factories/retriever.py

@@ -13,7 +13,6 @@ from llama_index.core.vector_stores.types import BasePydanticVectorStore
 from llama_index.vector_stores.chroma import ChromaVectorStore
 from llama_index.vector_stores.elasticsearch import ElasticsearchStore
 from llama_index.vector_stores.faiss import FaissVectorStore
-from llama_index.vector_stores.milvus import MilvusVectorStore
 
 from metagpt.rag.factories.base import ConfigBasedFactory
 from metagpt.rag.retrievers.base import RAGRetriever
@@ -22,7 +21,6 @@ from metagpt.rag.retrievers.chroma_retriever import ChromaRetriever
 from metagpt.rag.retrievers.es_retriever import ElasticsearchRetriever
 from metagpt.rag.retrievers.faiss_retriever import FAISSRetriever
 from metagpt.rag.retrievers.hybrid_retriever import SimpleHybridRetriever
-from metagpt.rag.retrievers.milvus_retriever import MilvusRetriever
 from metagpt.rag.schema import (
     BaseRetrieverConfig,
     BM25RetrieverConfig,
@@ -30,7 +28,6 @@ from metagpt.rag.schema import (
     ElasticsearchKeywordRetrieverConfig,
     ElasticsearchRetrieverConfig,
     FAISSRetrieverConfig,
-    MilvusRetrieverConfig,
 )
 
 
@@ -60,7 +57,6 @@ class RetrieverFactory(ConfigBasedFactory):
             ChromaRetrieverConfig: self._create_chroma_retriever,
             ElasticsearchRetrieverConfig: self._create_es_retriever,
             ElasticsearchKeywordRetrieverConfig: self._create_es_retriever,
-            MilvusRetrieverConfig: self._create_milvus_retriever,
         }
         super().__init__(creators)
 
@@ -81,11 +77,6 @@ class RetrieverFactory(ConfigBasedFactory):
 
         return index.as_retriever()
 
-    def _create_milvus_retriever(self, config: MilvusRetrieverConfig, **kwargs) -> MilvusRetriever:
-        config.index = self._build_milvus_index(config, **kwargs)
-
-        return MilvusRetriever(**config.model_dump())
-
     def _create_faiss_retriever(self, config: FAISSRetrieverConfig, **kwargs) -> FAISSRetriever:
         config.index = self._build_faiss_index(config, **kwargs)
 
@@ -144,14 +135,6 @@ class RetrieverFactory(ConfigBasedFactory):
 
         return self._build_index_from_vector_store(config, vector_store, **kwargs)
 
-    @get_or_build_index
-    def _build_milvus_index(self, config: MilvusRetrieverConfig, **kwargs) -> VectorStoreIndex:
-        vector_store = MilvusVectorStore(
-            uri=config.uri, collection_name=config.collection_name, token=config.token, dim=config.dimensions
-        )
-
-        return self._build_index_from_vector_store(config, vector_store, **kwargs)
-
     @get_or_build_index
     def _build_es_index(self, config: ElasticsearchRetrieverConfig, **kwargs) -> VectorStoreIndex:
         vector_store = ElasticsearchStore(**config.store_config.model_dump())

metagpt/rag/retrievers/milvus_retriever.py

@@ -1,17 +0,0 @@
-"""Milvus retriever."""
-
-from llama_index.core.retrievers import VectorIndexRetriever
-from llama_index.core.schema import BaseNode
-
-
-class MilvusRetriever(VectorIndexRetriever):
-    """Milvus retriever."""
-
-    def add_nodes(self, nodes: list[BaseNode], **kwargs) -> None:
-        """Support add nodes."""
-        self._index.insert_nodes(nodes, **kwargs)
-
-    def persist(self, persist_dir: str, **kwargs) -> None:
-        """Support persist.
-
-        Milvus automatically saves, so there is no need to implement."""

metagpt/rag/schema.py

@@ -69,36 +69,6 @@ class BM25RetrieverConfig(IndexRetrieverConfig):
     _no_embedding: bool = PrivateAttr(default=True)
 
 
-class MilvusRetrieverConfig(IndexRetrieverConfig):
-    """Config for Milvus-based retrievers."""
-
-    uri: str = Field(default="./milvus_local.db", description="The directory to save data.")
-    collection_name: str = Field(default="metagpt", description="The name of the collection.")
-    token: str = Field(default=None, description="The token for Milvus")
-    metadata: Optional[CollectionMetadata] = Field(
-        default=None, description="Optional metadata to associate with the collection"
-    )
-    dimensions: int = Field(default=0, description="Dimensionality of the vectors for Milvus index construction.")
-
-    _embedding_type_to_dimensions: ClassVar[dict[EmbeddingType, int]] = {
-        EmbeddingType.GEMINI: 768,
-        EmbeddingType.OLLAMA: 4096,
-    }
-
-    @model_validator(mode="after")
-    def check_dimensions(self):
-        if self.dimensions == 0:
-            self.dimensions = config.embedding.dimensions or self._embedding_type_to_dimensions.get(
-                config.embedding.api_type, 1536
-            )
-            if not config.embedding.dimensions and config.embedding.api_type not in self._embedding_type_to_dimensions:
-                logger.warning(
-                    f"You didn't set dimensions in config when using {config.embedding.api_type}, default to 1536"
-                )
-
-        return self
-
-
 class ChromaRetrieverConfig(IndexRetrieverConfig):
     """Config for Chroma-based retrievers."""
 
@@ -210,17 +180,6 @@ class ChromaIndexConfig(VectorIndexConfig):
     )
 
 
-class MilvusIndexConfig(VectorIndexConfig):
-    """Config for milvus-based index."""
-
-    collection_name: str = Field(default="metagpt", description="The name of the collection.")
-    uri: str = Field(default="./milvus_local.db", description="The uri of the index.")
-    token: Optional[str] = Field(default=None, description="The token of the index.")
-    metadata: Optional[CollectionMetadata] = Field(
-        default=None, description="Optional metadata to associate with the collection"
-    )
-
-
 class BM25IndexConfig(BaseIndexConfig):
     """Config for bm25-based index."""