> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tokenlab.sh/llms.txt
> Use this file to discover all available pages before exploring further.

# LlamaIndex

> 使用 OpenAI 相容整合將 TokenLab 與 LlamaIndex 進行整合

## 概覽

<Note>
  **類型**: 框架或平台

  **主要路徑**: 透過 OpenAILike 進行 OpenAI 相容整合

  ## **支援信心**: 透過 OpenAILike 支援
</Note>

對於 TokenLab 而言，更穩健的 LlamaIndex 設定方式是使用 **OpenAI 相容整合**，而非內建的 OpenAI 類別。

目前的 LlamaIndex 文件明確建議針對第三方 OpenAI 相容端點使用 `OpenAILike`，因為內建的 OpenAI 類別會從官方模型名稱中推斷元數據 (metadata)。

換句話說：請將 `OpenAILike` 視為此處支援的 TokenLab 路徑，而非內建的 OpenAI 類別。

## 安裝

```bash theme={null}
pip install llama-index-core \
  llama-index-readers-file \
  llama-index-llms-openai-like \
  llama-index-embeddings-openai-like
```

## 基本設定

```python theme={null}
from llama_index.core import Settings
from llama_index.llms.openai_like import OpenAILike
from llama_index.embeddings.openai_like import OpenAILikeEmbedding

llm = OpenAILike(
    model="gpt-5.4",
    api_base="https://api.tokenlab.sh/v1",
    api_key="sk-your-tokenlab-key",
    is_chat_model=True,
)

embed_model = OpenAILikeEmbedding(
    model_name="text-embedding-3-small",
    api_base="https://api.tokenlab.sh/v1",
    api_key="sk-your-tokenlab-key",
)

Settings.llm = llm
Settings.embed_model = embed_model
```

## 基本用法

```python theme={null}
response = llm.complete("Explain TokenLab in one sentence.")
print(response.text)
```

## 最小化 OpenAILike LLM

```python theme={null}
from llama_index.llms.openai_like import OpenAILike

llm = OpenAILike(
    model="claude-sonnet-5",
    api_base="https://api.tokenlab.sh/v1",
    api_key="sk-your-tokenlab-key",
    context_window=200000,
    is_chat_model=True,
    is_function_calling_model=True,
)
```

## 聊天 (Chat)

```python theme={null}
from llama_index.core.llms import ChatMessage

messages = [
    ChatMessage(role="system", content="You are a helpful assistant."),
    ChatMessage(role="user", content="What is the capital of France?")
]

response = llm.chat(messages)
print(response.message.content)
```

## 串流 (Streaming)

```python theme={null}
for chunk in llm.stream_complete("Write a short poem about AI."):
    print(chunk.delta, end="", flush=True)
```

## 嵌入 (Embeddings)

```python theme={null}
vector = embed_model.get_text_embedding("Hello, world!")
print(vector[:5])
```

## 使用文件進行 RAG

```python theme={null}
from llama_index.core import SimpleDirectoryReader, VectorStoreIndex

documents = SimpleDirectoryReader("./data").load_data()
index = VectorStoreIndex.from_documents(documents)

query_engine = index.as_query_engine()
response = query_engine.query("What is in my documents?")
print(response)
```

## 聊天引擎 (Chat Engine)

```python theme={null}
chat_engine = index.as_chat_engine(chat_mode="condense_question")

response = chat_engine.chat("What is TokenLab?")
print(response)

response = chat_engine.chat("How many models does it support?")
print(response)
```

## 非同步用法 (Async Usage)

```python theme={null}
import asyncio

async def main():
    response = await llm.acomplete("Hello!")
    print(response.text)

asyncio.run(main())
```

## 最佳實踐

<AccordionGroup>
  <Accordion title="為 TokenLab 使用 OpenAILike">
    針對 TokenLab 及其他第三方 OpenAI 相容閘道，建議優先使用 `llama_index.llms.openai_like.OpenAILike` 與 `llama_index.embeddings.openai_like.OpenAILikeEmbedding`。
  </Accordion>

  <Accordion title="明確設定 api_base">
    直接在程式碼中傳入 `api_base="https://api.tokenlab.sh/v1"`，而不要依賴舊版的 OpenAI 環境變數名稱。
  </Accordion>

  <Accordion title="區分模型角色">
    使用聊天/推理模型進行合成，並使用 `text-embedding-3-small` 或 `text-embedding-3-large` 進行檢索。
  </Accordion>
</AccordionGroup>