嵌入模型

Ollama 支持嵌入模型，使构建检索增强生成 (RAG) 应用程序成为可能，这些应用程序将文本提示与现有文档或其他数据相结合。

什么是嵌入模型？

嵌入模型是专门训练用于生成向量嵌入的模型：代表给定文本序列的语义含义的长的数字数组。

生成的向量嵌入数组随后可以存储在数据库中，数据库将比较它们作为一种搜索语义相似的數據的方法。

嵌入模型示例

使用

要生成向量嵌入，首先拉取模型

ollama pull mxbai-embed-large

接下来，使用REST API、Python 或 JavaScript 库从模型生成向量嵌入

_{REST API}

curl https://127.0.0.1:11434/api/embeddings -d '{
  "model": "mxbai-embed-large",
  "prompt": "Llamas are members of the camelid family"
}'

_{Python 库}

ollama.embeddings(
  model='mxbai-embed-large',
  prompt='Llamas are members of the camelid family',
)

_{Javascript 库}

ollama.embeddings({
    model: 'mxbai-embed-large',
    prompt: 'Llamas are members of the camelid family',
})

Ollama 还与流行的工具集成，以支持嵌入工作流，例如 LangChain 和 LlamaIndex。

示例

此示例逐步介绍如何使用 Ollama 和嵌入模型构建检索增强生成 (RAG) 应用程序。

步骤 1：生成嵌入

pip install ollama chromadb

创建一个名为example.py 的文件，其内容为

import ollama
import chromadb

documents = [
  "Llamas are members of the camelid family meaning they're pretty closely related to vicuñas and camels",
  "Llamas were first domesticated and used as pack animals 4,000 to 5,000 years ago in the Peruvian highlands",
  "Llamas can grow as much as 6 feet tall though the average llama between 5 feet 6 inches and 5 feet 9 inches tall",
  "Llamas weigh between 280 and 450 pounds and can carry 25 to 30 percent of their body weight",
  "Llamas are vegetarians and have very efficient digestive systems",
  "Llamas live to be about 20 years old, though some only live for 15 years and others live to be 30 years old",
]

client = chromadb.Client()
collection = client.create_collection(name="docs")

# store each document in a vector embedding database
for i, d in enumerate(documents):
  response = ollama.embeddings(model="mxbai-embed-large", prompt=d)
  embedding = response["embedding"]
  collection.add(
    ids=[str(i)],
    embeddings=[embedding],
    documents=[d]
  )

步骤 2：检索

接下来，添加代码以根据示例提示检索最相关的文档

# an example prompt
prompt = "What animals are llamas related to?"

# generate an embedding for the prompt and retrieve the most relevant doc
response = ollama.embeddings(
  prompt=prompt,
  model="mxbai-embed-large"
)
results = collection.query(
  query_embeddings=[response["embedding"]],
  n_results=1
)
data = results['documents'][0][0]

步骤 3：生成

最后，使用提示和在上一步中检索到的文档来生成答案！

# generate a response combining the prompt and data we retrieved in step 2
output = ollama.generate(
  model="llama2",
  prompt=f"Using this data: {data}. Respond to this prompt: {prompt}"
)

print(output['response'])

然后，运行代码

python example.py

Llama 2 将使用数据回答提示哪些动物与羊驼有关？

Llamas are members of the camelid family, which means they are closely related to two other animals: vicuñas and camels. All three species belong to the same evolutionary lineage and share many similarities in terms of their physical characteristics, behavior, and genetic makeup. Specifically, llamas are most closely related to vicuñas, with which they share a common ancestor that lived around 20-30 million years ago. Both llamas and vicuñas are members of the family Camelidae, while camels belong to a different family (Dromedary).

即将推出

更多功能即将推出，以支持涉及嵌入的工作流

• 批量嵌入：同时处理多个输入数据提示
• OpenAI API 兼容性：支持/v1/embeddings OpenAI 兼容端点
• 更多嵌入模型架构：支持 ColBERT、RoBERTa 和其他嵌入模型架构