本页面介绍如何在 LangChain 中使用 Prediction Guard 生态系统。 它分为两部分：安装和设置，然后是特定 Prediction Guard 包装器的参考。

此集成在以下位置维护 langchain-predictionguard package.

安装和设置

• - 安装 PredictionGuard LangChain 合作伙伴包：

pip install langchain-predictionguard

uv add langchain-predictionguard

• - 获取 Prediction Guard API 密钥（如 Prediction Guard 文档中所述），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| |---|---|---|---------------------------------------------------------|-------------------------------------------------------------------------------| |Chat|构建聊天机器人|Chat| from langchain_predictionguard import ChatPredictionGuard | ChatPredictionGuard.ipynb | |Completions|生成文本|Completions| from langchain_predictionguard import PredictionGuard | PredictionGuard.ipynb | |Text Embedding|将字符串嵌入向量|Embeddings| from langchain_predictionguard import PredictionGuardEmbeddings | PredictionGuardEmbeddings.ipynb |

开始使用

聊天模型

Prediction Guard 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

Prediction Guard 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)

LLMs

Prediction Guard 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")