错误描述

我之前使用LlamaIndex内置的向量索引实现了一个VectorIndexRetriever,没有使用任何向量数据库，并启用了MMR模式和mmr_threshold。它运行正常。
然后我添加了ChromaDB,发现只要不包含mmr_threshold,MMR模式就可以正常工作。如果你在vector_store_kwargs参数中设置了mmr_threshold,就会报错。

版本

llama-index-0.10.1

重现步骤

这是我代码中的相关部分。如果我注解掉"# ERROR"这一行，那么代码就可以正常工作。

from llama_index.core.indices.vector_store.base import VectorStoreIndex
from llama_index.core.storage import StorageContext
from llama_index.core.indices.vector_store.retrievers.retriever import (
    VectorIndexRetriever,
)
from llama_index.core.query_engine.retriever_query_engine import (
    RetrieverQueryEngine
)
from llama_index.core import Settings
from llama_index.vector_stores.chroma.base import ChromaVectorStore
import chromadb

def run_query(
    question: str,
    vectorstore: str,
    top_k: int,
    mmr_threshold: float,
) -> RetrieverQueryEngine | None:
    '''
    Return an LLM response to an input query after doing a vector search.

    Args:
        question (str): The query to the LLM.
        vectorstore (str): Folder name of vector database.
        top_k (int): Number of retrievals or citations to retrieve via
            vector search.
        mmr_threshold (float): A float between 0 and 1, for MMR search mode.
            Closer to 0 gives you more diversity in the retrievals.
            Closer to 1 gives you more relevance in the retrievals.

    Returns:
        RetrieverQueryEngine | None: If vectorstore location exists, return a
            Response object from RetrieverQueryEngine, else return nothing.
    '''

    if not os.path.exists(vectorstore):
        print('Error: Vectorstore', vectorstore, 'not found!')
        return
    else:
        # Instantiate a Chroma client, setting storage folder location:
        client = chromadb.PersistentClient(path=vectorstore)

        # Instantiate a Chroma collection based on the client:
        chroma_collection = client.get_or_create_collection(vectorstore)

        # Instantiate a ChromaVectorStore based on the Chroma collection:
        vector_store = ChromaVectorStore(chroma_collection=chroma_collection)

        # Instantiate a storage context based on the ChromaVectorStore:
        storage_context = StorageContext.from_defaults(
            vector_store=vector_store
        )

        # Instantiate LLM and embedding model:
        llm, embedding = create_azure_models()

        # Add these 2 models to the LlamaIndex Settings:
        Settings.llm = llm
        Settings.embed_model = embedding

        index = VectorStoreIndex.from_vector_store(
            vector_store,
            storage_context=storage_context
        )

        # Instantiate and configure a VectorIndexRetriever:
        # Note about parameters:
        # similarity_top_k sets the number of retrievals (citations).
        # mmr_threshold is a value between 0 and 1.
        # Closer to 0 gives you more diversity.
        # Closer to 1 gives you more relevance.
        # If the data contains duplicated entries, set it lower (e.g. 0.2)
        # so that the retriever will skip over search results that are
        # identical or very similar and go for greater diversity.
        retriever = VectorIndexRetriever(
            index=index,
            similarity_top_k=top_k,
            vector_store_query_mode='mmr',
            vector_store_kwargs={'mmr_threshold': mmr_threshold}  # ERROR
        )

        # Instantiate RetrieverQueryEngine and pass in the VectorIndexRetriever:
        query_engine = RetrieverQueryEngine(
            retriever=retriever
        )

        # Query the index:
        response = query_engine.query(question)

        return response

相关日志/回溯

File ".../text_data_helpers.py", line 142, in run_query
    response = query_engine.query(question)
  File ".../lib/python3.10/site-packages/llama_index/core/base/base_query_engine.py", line 40, in query
    return self._query(str_or_query_bundle)
  File ".../lib/python3.10/site-packages/llama_index/core/query_engine/retriever_query_engine.py", line 186, in _query
    nodes = self.retrieve(query_bundle)
  File ".../lib/python3.10/site-packages/llama_index/core/query_engine/retriever_query_engine.py", line 142, in retrieve
    nodes = self._retriever.retrieve(query_bundle)
  File ".../lib/python3.10/site-packages/llama_index/core/base/base_retriever.py", line 229, in retrieve
    nodes = self._retrieve(query_bundle)
  File ".../lib/python3.10/site-packages/llama_index/core/indices/vector_store/retrievers/retriever.py", line 94, in _retrieve
    return self._get_nodes_with_embeddings(query_bundle)
  File ".../lib/python3.10/site-packages/llama_index/core/indices/vector_store/retrievers/retriever.py", line 170, in _get_nodes_with_embeddings
    query_result = self._vector_store.query(query, **self._kwargs)
  File ".../lib/python3.10/site-packages/llama_index/vector_stores/chroma/base.py", line 292, in query
    results = self._collection.query(
TypeError: Collection.query() got an unexpected keyword argument 'mmr_threshold'