Skip to main content
Open on GitHub

Prediction Guard

本页面介绍了如何在LangChain中使用Prediction Guard生态系统。 它分为两部分：安装和设置，然后是对特定Prediction Guard包装器的引用。

此集成维护在langchain-predictionguard包中。

安装与设置​

  • 安装PredictionGuard Langchain合作伙伴包：
pip install langchain-predictionguard
  • 获取一个 Prediction Guard API 密钥（如此处所述）并将其设置为环境变量（PREDICTIONGUARD_API_KEY）

Prediction Guard Langchain 集成​

API描述端点文档导入示例用法
聊天构建聊天机器人聊天from langchain_predictionguard import ChatPredictionGuardChatPredictionGuard.ipynb
补全生成文本Completionsfrom langchain_predictionguard import PredictionGuardPredictionGuard.ipynb
文本嵌入将字符串嵌入为向量Embeddingsfrom langchain_predictionguard import PredictionGuardEmbeddingsPredictionGuardEmbeddings.ipynb

入门指南​

聊天模型​

预测保护聊天​

查看使用示例

from langchain_predictionguard import ChatPredictionGuard

用法​

# If predictionguard_api_key is not passed, default behavior is to use the `PREDICTIONGUARD_API_KEY` environment variable.
chat = ChatPredictionGuard(model="Hermes-3-Llama-3.1-8B")

chat.invoke("Tell me a joke")

嵌入模型​

预测保护嵌入​

查看使用示例

from langchain_predictionguard import PredictionGuardEmbeddings

用法​

# If predictionguard_api_key is not passed, default behavior is to use the `PREDICTIONGUARD_API_KEY` environment variable.
embeddings = PredictionGuardEmbeddings(model="bridgetower-large-itm-mlm-itc")

text = "This is an embedding example."
output = embeddings.embed_query(text)

大型语言模型​

预测保护 LLM​

查看使用示例

from langchain_predictionguard import PredictionGuard

用法​

# If predictionguard_api_key is not passed, default behavior is to use the `PREDICTIONGUARD_API_KEY` environment variable.
llm = PredictionGuard(model="Hermes-2-Pro-Llama-3-8B")

llm.invoke("Tell me a joke about bears")

这个页面有帮助吗？