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。 内容分为两部分：安装与设置，以及对特定 Prediction Guard 封装器的引用。

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描述端点文档导入使用示例
ChatBuild Chat BotsChatfrom langchain_predictionguard import ChatPredictionGuardChatPredictionGuard.ipynb
CompletionsGenerate TextCompletionsfrom langchain_predictionguard import PredictionGuardPredictionGuard.ipynb
Text EmbeddingEmbed String to VectoresEmbeddingsfrom langchain_predictionguard import PredictionGuardEmbeddingsPredictionGuardEmbeddings.ipynb

入门指南​

聊天模型​

Prediction Guard 聊天​

查看一个 使用示例

from langchain_predictionguard import ChatPredictionGuard

使用​

# 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​

Prediction Guard 嵌入​

查看一个 使用示例

from langchain_predictionguard import PredictionGuardEmbeddings

使用​

# 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)

LLMs​

Prediction Guard LLM​

查看一个 使用示例

from langchain_predictionguard import PredictionGuard

使用​

# 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")