提示

如果你还没有做过，请先安装 LlamaIndex，并完成起步教程。如果碰到不认识的名词，可以查看高层概念。

在这一节里，我们从你在起步示例中写下的代码出发，演示为你自己的场景做定制时最常用的几种方式：

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)

---

“我想把文档切分成更小的块”

# 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)]
)

---

"我想换一个向量库”

首先，安装你想用的向量库。例如，要把 Chroma 作为向量库，可以用 pip 安装：

终端窗口

pip install llama-index-vector-stores-chroma

想了解全部可用集成，请看集成页面。

然后，就可以在代码里使用它：

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 定义了文档、嵌入和索引存放在哪个存储后端。你可以进一步了解存储以及如何定制它。

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)

---

”我想在查询时检索更多上下文”

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 会在索引之上构建默认的 retriever 和 query engine。你可以通过关键字参数来配置检索器和查询引擎。这里我们把检索器配置为返回最相似的前 5 个文档（默认是 2 个）。你可以进一步了解检索器和查询引擎。

---

”我想换一个 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,
    )
)

你可以进一步了解如何定制 LLM。

---

”我想换一种响应模式”

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)

你可以进一步了解查询引擎和响应模式。

---

”我想让回答流式返回”

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()

你可以进一步了解流式响应。

---

”我想要聊天机器人，而不是 Q&A”

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)

进一步了解对话引擎。

---

下一步

• 想系统地了解（几乎）所有可配置项？从理解 LlamaIndex 开始。
• 想更深入地理解某个具体模块？请看组件指南。