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

# 为 LangChain 的 OCI 生成式 AI 集成

> 使用 LangChain Python 集成 OCI Generative AI 嵌入模型。

本文档将帮助你开始使用 OCI 生成式 AI [嵌入模型](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/embeddings.md)。Oracle Cloud Infrastructure (OCI) 生成式 AI 提供了最先进的文本和图像嵌入模型，支持语义搜索、RAG、聚类和跨模态应用。

有关详细文档，请参阅 [OCI 生成式 AI 文档](https://docs.oracle.com/en-us/iaas/Content/generative-ai/home.htm) 和 [API 参考](https://docs.oracle.com/en-us/iaas/api/#/en/generative-ai/20231130/)。

## 概述

### 集成详情

| 类别 | 包 | 可序列化 | 参数缓存 | 异步 | 下载 | 版本 |
| :- | :- | :-: | :-: | :-: | :-: | :-: |
| [`OCIGenAIEmbeddings`](https://github.com/oracle/langchain-oracle/tree/main/libs/oci) | [`langchain-oci`](https://pypi.org/project/langchain-oci/) | beta | ✅ | ✅ | ![PyPI - 下载](https://img.shields.io/pypi/dm/langchain-oci?style=flat-square\&label=%20) | ![PyPI - 版本](https://img.shields.io/pypi/v/langchain-oci?style=flat-square\&label=%20) |

### 模型特性

| 文本嵌入 | 图像嵌入 | 跨模态 | 批量操作 | 异步 |
| :-: | :-: | :-: | :-: | :-: |
| ✅ | ✅ | ✅ | ✅ | ✅ |

## 设置

```bash pip theme={null}
pip install -qU langchain-oci oci
```

```bash uv theme={null}
uv add langchain-oci oci
```

设置认证：

```bash theme={null}
oci setup config
```

## 实例化

```python theme={null}
from langchain_oci import OCIGenAIEmbeddings

embeddings = OCIGenAIEmbeddings(
    model_id="cohere.embed-english-v3.0",
    service_endpoint="https://inference.generativeai.us-chicago-1.oci.oraclecloud.com",
    compartment_id="ocid1.compartment.oc1..your-compartment-id",
)
```

## 使用

构建技术文档的语义搜索：

```python theme={null}
# Index code documentation
docs = [
    "authenticate() validates JWT tokens and returns user object",
    "authorize() checks user permissions for resource access",
    "audit_log() records user actions for compliance tracking"
]
doc_vectors = embeddings.embed_documents(docs)

# Search with natural language query
query = "How do I verify user identity?"
query_vector = embeddings.embed_query(query)

# Find most relevant documentation
import numpy as np
similarities = [
    np.dot(query_vector, doc_vec) /
    (np.linalg.norm(query_vector) * np.linalg.norm(doc_vec))
    for doc_vec in doc_vectors
]
best_match = docs[np.argmax(similarities)]
# Returns: "authenticate() validates JWT tokens..."
```

**用例：** 代码搜索、文档问答、日志分析、重复检测

## 图像嵌入

使用跨模态嵌入通过文本查询搜索视觉资源：

```python theme={null}
import numpy as np
from langchain_oci import OCIGenAIEmbeddings

embeddings = OCIGenAIEmbeddings(
    model_id="cohere.embed-v4.0",
    service_endpoint="https://inference.generativeai.us-chicago-1.oci.oraclecloud.com",
    compartment_id="ocid1.compartment.oc1..your-compartment-id",
)

# Index architecture diagrams
diagrams = ["microservices.png", "database_schema.png", "network.png"]
image_vectors = embeddings.embed_image_batch(diagrams)

# Search with text query
query_vector = embeddings.embed_query("database relationships")

# Find best match
similarities = [np.dot(query_vector, v) / (np.linalg.norm(query_vector) * np.linalg.norm(v))
                for v in image_vectors]
print(diagrams[np.argmax(similarities)])  # "database_schema.png"
```

**用例：** 技术图表搜索、资产管理、视觉文档检索

## 可用模型

| 模型 | 维度 | 类型 |
| - | - | - |
| `cohere.embed-english-v3.0` | 1024 | 仅文本 |
| `cohere.embed-multilingual-v3.0` | 1024 | 仅文本 |
| `cohere.embed-v4.0` | 256-1536 | 文本 + 图像 |

有关所有模型的详细信息，请参阅 [OCI 模型目录](https://docs.oracle.com/en-us/iaas/Content/generative-ai/pretrained-models.htm)。

## RAG 示例

> [!WARNING]
>
> `langchain-community`包已不再维护。从`langchain_community`导入的示例可能过时或无法使用。请谨慎使用。

```python theme={null}
from langchain_community.vectorstores import FAISS

# Create vector store
vectorstore = FAISS.from_documents(documents, embeddings)

# Search
results = vectorstore.similarity_search("your query", k=3)
```

## 异步

生产环境中的异步操作：

```python theme={null}
query_vector = await embeddings.aembed_query("What is AI?")
doc_vectors = await embeddings.aembed_documents(["Doc 1", "Doc 2"])
```

## API 参考

有关所有 `OCIGenAIEmbeddings` 功能和配置的详细文档，请访问 [API 参考](https://github.com/oracle/langchain-oracle/tree/main/libs/oci)。

## 相关

* [OCI 提供商概述](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/providers/oci.md)
* [`ChatOCIGenAI`](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/chat/oci_generative_ai)
* [嵌入指南](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/embeddings.md)
* [RAG 教程](https://langchain-docs-zh.mintlify.site/langchain/oss/deepagents/rag.md)

***

> 官方原文：[src/oss/python/integrations/embeddings/oci\_generative\_ai.mdx](https://github.com/langchain-ai/docs/blob/main/src/oss/python/integrations/embeddings/oci_generative_ai.mdx) · 非官方翻译，译文由 AI 生成，以英文原文为准。


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.