Applying Conversation History

To pass this lesson, use the getHistory() and saveHistory() methods to save and retrieve the conversation history from the database.

  1. Add a config object to the chain.invoke() call, passing { configurable: { sessionId } }

  2. Within RunnablePassthrough.assign(), use the sessionId from config.configurable? to retrieve the message history via the getHistory() function. Assign this to the history key

  3. Add a MessagesPlaceholder for history to the ChatMessagePromptTemplate

  4. Save the input and response to the database using the saveHistory() function

Solution
typescript
import {
  ChatPromptTemplate,
  SystemMessagePromptTemplate,
  HumanMessagePromptTemplate,
  MessagesPlaceholder
 } from "@langchain/core/prompts";
import { ChatOpenAI, OpenAIEmbeddings } from "@langchain/openai";
import { StringOutputParser } from "@langchain/core/output_parsers";
import { RunnableSequence, RunnablePassthrough, RunnablePick } from "@langchain/core/runnables";
import { Neo4jVectorStore } from "@langchain/community/vectorstores/neo4j_vector";
import { getHistory, saveHistory } from "./history";

export async function call(
  message: string,
  sessionId: string
): Promise<string> {
  const embeddings = new OpenAIEmbeddings({
    openAIApiKey: process.env.OPEN_AI_API_KEY,
  });
  const store = await Neo4jVectorStore.fromExistingGraph(embeddings, {
    url: process.env.NEO4J_URI,
    username: process.env.NEO4J_USERNAME,
    password: process.env.NEO4J_PASSWORD,
    nodeLabel: "Talk",
    textNodeProperties: ["title", "description"],
    indexName: "talk_embeddings_openai",
    embeddingNodeProperty: "embedding",
    retrievalQuery: `
    RETURN node.description AS text, score,
    node {
      .time, .title,
      url: 'https://athens.cityjsconf.org/'+ node.url,
      speaker: [
        (node)-[:GIVEN_BY]->(s) |
        s { .name, .company, .x_handle, .bio }
      ][0],
      room: [ (node)-[:IN_ROOM]->(r) | r.name ][0],
      tags: [ (node)-[:HAS_TAG]->(t) | t.name ]

    } AS metadata
  `,
  });
  const retriever = store.asRetriever();

  // 1. create a prompt template
  const prompt = ChatPromptTemplate.fromMessages([
    SystemMessagePromptTemplate.fromTemplate(
      `You are a helpful assistant helping users with queries
      about the CityJS Athens conference.
      Answer the user's question to the best of your ability.
      If you do not know the answer, just say you don't know.
      `
    ),
    SystemMessagePromptTemplate.fromTemplate(
      `
        Here are some talks to help you answer the question.
        Don't use your pre-trained knowledge to answer the question.
        Always include a full link to the meetup.
        If the answer isn't included in the documents, say you don't know.

        Documents:
        {documents}
      `
    ),
    new MessagesPlaceholder("history"),
    HumanMessagePromptTemplate.fromTemplate(`Question: {message}`),
  ]);

  // 2. choose an LLM
  const llm = new ChatOpenAI({
    openAIApiKey: process.env.OPENAI_API_KEY,
    temperature: 0.9,
  });

  // 3. parse the response
  const parser = new StringOutputParser();

  // 4. runnable sequence (LCEL)
  const chain = RunnableSequence.from<RunInput, string>([
    RunnablePassthrough.assign({
      history: (input, config) => getHistory(config?.configurable.sessionId, 3),
      documents: new RunnablePick("input").pipe(
        retriever.pipe((docs) => JSON.stringify(docs))
      ),
    }),
    prompt,
    llm,
    new StringOutputParser(),
  ]);

  // 5. invoke the chain
  const output = await chain.invoke(
    { message },
    {
      configurable: {
        sessionId,
      },
    }
  );

  // 6. Save history
  await saveHistory(sessionId, message, output);

  return output;
}

Summary

Loving your work!

Chatbot

Hi, I am an Educational Learning Assistant for Intelligent Network Exploration. You can call me E.L.A.I.N.E.

How can I help you today?