langflow/docs/docs/starter-projects/memory-chatbot.mdx
2024-06-24 04:37:06 -07:00

81 lines
3.8 KiB
Text

import ThemedImage from "@theme/ThemedImage";
import useBaseUrl from "@docusaurus/useBaseUrl";
import ZoomableImage from "/src/theme/ZoomableImage.js";
import ReactPlayer from "react-player";
import Admonition from "@theme/Admonition";
# Memory Chatbot
<Admonition type="warning" title="warning">
This page may contain outdated information. It will be updated as soon as possible.
</Admonition>
This flow extends the [basic prompting flow](./basic-prompting) to include chat memory for unique SessionIDs.
## Prerequisites
- [Langflow installed and running](../getting-started/install-langflow)
- [OpenAI API key created](https://platform.openai.com)
## Create the memory chatbot project
1. From the Langflow dashboard, click **New Project**.
2. Select **Memory Chatbot**.
3. The **Memory Chatbot** flow is created.
<ZoomableImage
alt="Docusaurus themed image"
sources={{
light: "img/memory-chatbot.png",
dark: "img/memory-chatbot.png",
}}
style={{
width: "80%",
margin: "20px auto",
display: "flex",
justifyContent: "center",
}}
/>
This flow creates a basic chatbot with the **Chat Input**, **Prompt**, and **OpenAI** components.
This chatbot is augmented with the **Chat Memory** component, which stores messages submitted via **Chat Input** and prepends them to subsequent prompts to OpenAI via `{context}`.
The **Chat History** component gives the **OpenAI** component a memory of previous questions.
4. To create an environment variable for the **OpenAI** component, in the **OpenAI API Key** field, click the **Globe** button, and then click **Add New Variable**.
1. In the **Variable Name** field, enter `openai_api_key`.
2. In the **Value** field, paste your OpenAI API Key (`sk-...`).
3. Click **Save Variable**.
## Run the memory chatbot flow
1. Click the **Run** button.
The **Interaction Panel** opens, where you can converse with your bot.
2. Type a message and press Enter.
The bot will respond according to the template in the **Prompt** component.
3. Type more questions. In the **Outputs** log, your queries are logged in order. Up to 5 queries are stored by default. Try asking `What is the first subject I asked you about?` to see where the LLM's memory disappears.
## Modify the Session ID field to have multiple conversations
`SessionID` is a unique identifier in Langchain for a conversation session between a chatbot and a client.
A `SessionID` is created when a conversation is initiated, and then associated with all subsequent messages during that session.
In the **Memory Chatbot** flow you created, the **Chat Memory** component references past interactions with **Chat Input** by **Session ID**.
You can demonstrate this by modifying the **Session ID** value to switch between conversation histories.
1. In the **Session ID** field of the **Chat Memory** and **Chat Input** components, change the **Session ID** value from `MySessionID` to `AnotherSessionID`.
2. Click the **Run** button to run your flow.
In the **Interaction Panel**, you will have a new conversation. (You may need to clear the cache with the **Eraser** button).
3. Type a few questions to your bot.
4. In the **Session ID** field of the **Chat Memory** and **Chat Input** components, change the **Session ID** value back to `MySessionID`.
5. Run your flow.
The **Outputs** log of the **Interaction Panel** displays the history from your initial chat with `MySessionID`.
## Store Session ID as a Langflow variable
To store **Session ID** as a Langflow variable, in the **Session ID** field, click the **Globe** button, and then click **Add New Variable**.
1. In the **Variable Name** field, enter a name like `customer_chat_emea`.
2. In the **Value** field, enter a value like `1B5EBD79-6E9C-4533-B2C8-7E4FF29E983B`.
3. Click **Save Variable**.
4. Apply this variable to **Chat Input**.