常见问题解答 (FAQ)

在本节中，我们从您为入门示例编写的代码开始，向您展示为满足您的使用场景可能需要定制的最常见方式：

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader

documents = SimpleDirectoryReader("data").load_data()
index = VectorStoreIndex.from_documents(documents)
query_engine = index.as_query_engine()
response = query_engine.query("What did the author do growing up?")
print(response)

“我想将我的文档解析成更小的片段”

# Global settings
from llama_index.core import Settings

Settings.chunk_size = 512

# Local settings
from llama_index.core.node_parser import SentenceSplitter

index = VectorStoreIndex.from_documents(
    documents, transformations=[SentenceSplitter(chunk_size=512)]
)

“我想使用不同的向量存储”

首先，您可以安装想要使用的向量存储。例如，要使用 Chroma 作为向量存储，您可以通过 pip 安装：

pip install llama-index-vector-stores-chroma

要了解更多可用的集成，请查看 LlamaHub。

然后，你可以在代码中使用它：

import chromadb
from llama_index.vector_stores.chroma import ChromaVectorStore
from llama_index.core import StorageContext

chroma_client = chromadb.PersistentClient()
chroma_collection = chroma_client.create_collection("quickstart")
vector_store = ChromaVectorStore(chroma_collection=chroma_collection)
storage_context = StorageContext.from_defaults(vector_store=vector_store)

StorageContext 定义了存储后端，用于存储文档、嵌入向量和索引。您可以了解更多关于存储和如何自定义它的信息。

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader

documents = SimpleDirectoryReader("data").load_data()
index = VectorStoreIndex.from_documents(
    documents, storage_context=storage_context
)
query_engine = index.as_query_engine()
response = query_engine.query("What did the author do growing up?")
print(response)

“我希望在查询时能获取更多上下文信息”

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader

documents = SimpleDirectoryReader("data").load_data()
index = VectorStoreIndex.from_documents(documents)
query_engine = index.as_query_engine(similarity_top_k=5)
response = query_engine.query("What did the author do growing up?")
print(response)

as_query_engine 在索引基础上构建默认的 retriever 和 query engine。您可以通过传入关键字参数来配置检索器和查询引擎。这里，我们将检索器配置为返回前5个最相似的文档（而非默认的2个）。您可以了解更多关于检索器和查询引擎的信息。

“我想使用不同的LLM”

# Global settings
from llama_index.core import Settings
from llama_index.llms.ollama import Ollama

Settings.llm = Ollama(
    model="mistral",
    request_timeout=60.0,
    # Manually set the context window to limit memory usage
    context_window=8000,
)

# Local settings
index.as_query_engine(
    llm=Ollama(
        model="mistral",
        request_timeout=60.0,
        # Manually set the context window to limit memory usage
        context_window=8000,
    )
)

您可以了解更多关于定制大型语言模型的信息。

“我想使用不同的响应模式”

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader

documents = SimpleDirectoryReader("data").load_data()
index = VectorStoreIndex.from_documents(documents)
query_engine = index.as_query_engine(response_mode="tree_summarize")
response = query_engine.query("What did the author do growing up?")
print(response)

您可以了解更多关于查询引擎和响应模式的信息。

“我希望流式返回响应”

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader

documents = SimpleDirectoryReader("data").load_data()
index = VectorStoreIndex.from_documents(documents)
query_engine = index.as_query_engine(streaming=True)
response = query_engine.query("What did the author do growing up?")
response.print_response_stream()

您可以了解更多关于流式响应的信息。

“我想要一个聊天机器人而不是问答系统”

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader

documents = SimpleDirectoryReader("data").load_data()
index = VectorStoreIndex.from_documents(documents)
query_engine = index.as_chat_engine()
response = query_engine.chat("What did the author do growing up?")
print(response)

response = query_engine.chat("Oh interesting, tell me more.")
print(response)

了解更多关于聊天引擎的信息。

后续步骤

想要详细了解（几乎）所有可配置项？请从理解LlamaIndex开始。
想要更深入地了解特定模块？请查阅组件指南。