dosubot[bot]
commented
1 year ago 🤖
Hello,
From your code, it seems you're using TypeScript. However, the LangChain framework is written in Python, and the solutions provided in the context are also in Python.
In Python, to include a system message in the chain, you would typically use the SystemMessagePromptTemplate.from_template() method. This method is used to create a system message from a string template. Here's an example of how it's used:
# Create a system message template
system_message_template = SystemMessagePromptTemplate.from_template("This is a system message")
# Now you can use this template to format a system message
formatted_message = system_message_template.format()However, since you're using TypeScript, the equivalent functionality might not be directly available. The LangChain framework doesn't currently have a TypeScript version, and I couldn't find a TypeScript equivalent of the SystemMessagePromptTemplate.from_template() method in the LangChain repository.
You might need to implement a similar functionality in TypeScript yourself. You could create a function that takes a string template as an argument and returns a formatted system message. Here's a rough example of how you could do this:
function formatSystemMessage(template: string): string {
// Format the template into a system message
let formattedMessage = template;
// Add any additional formatting logic here
return formattedMessage;
}
// Use the function to format a system message
let systemMessage = formatSystemMessage("This is a system message");Please note that this is a very basic example and you might need to add additional logic to handle more complex templates.
I hope this helps! If you have any other questions, feel free to ask.
Sources
- Question: System messages with AgentExecutors
- Issue: Is it possible to add system message with the prompt?
- Question: How can I include SystemMessage with RetrievalQA
- libs/langchain/langchain/prompts/chat.py
This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.
Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.
If you want to continue the conversation, start your reply with @dosu-bot.
Issue you'd like to raise.
Hi ,
I'm trying to see how I can put a system message for my chain to tell him that for example "Your name is XX".
I've tried a lot of things and saw a lot of issues resolved and documentations but they never worked... Any help will be appreciated. here is the code of my chain.ts: ` import {OpenAI} from "langchain/llms/openai"; import {pinecone} from "@/utils/pinecone-client"; import {PineconeStore} from "langchain/vectorstores/pinecone"; import {OpenAIEmbeddings} from "langchain/embeddings/openai"; import {ConversationalRetrievalQAChain} from "langchain/chains"; import { PromptTemplate } from "langchain/prompts"; import { ChatOpenAI } from "langchain/chat_models/openai";
async function initChain() { const model = new ChatOpenAI({ modelName: "gpt-3.5-turbo", temperature: 0, });
const pineconeIndex = pinecone.Index('canada'); const vectorStore = await PineconeStore.fromExistingIndex( new OpenAIEmbeddings({}), { pineconeIndex: pineconeIndex, textKey: 'text', }, ); return ConversationalRetrievalQAChain.fromLLM( model, vectorStore.asRetriever(), {returnSourceDocuments: true} ); return ConversationalRetrievalQAChain.fromLLM( model, vectorStore.asRetriever(), {returnSourceDocuments: true}, ); }
export const chain = await initChain()`
Suggestion:
No response