ChatGPT Assistant
Integrating ChatGPT for AI-powered automation.
Create Assistant
Create Assistant - an action type node required to create a GPT Chatbot assistant.
Node Configuration
To configure the Create Assistant node, you must fill in the required and optional fields.
Required* fields include:
- API Key;
- Model ID.
API Key
The field required for entering the API key (see more details here).
Model ID
Drop-down list to select the desired version of the GPT Chatbot model (see more details here). By default, the field is filled with the value gpt-3.5-turbo.
File IDs list
A field for entering file IDs that the assistant can use, for example, to write code, if these features are enabled.
The following format for entering file IDs is used:["file-abc123","file-abc456"].
Metadata
The field required to enter additional information about the assistant in the key-value format. The key can contain 64 characters, and the value can contain 512 characters.
Assistant name
A field for entering the name of the assistant. The name can contain up to 256 characters.
Description
A field for entering a description of the assistant. The description can contain up to 512 characters.
System instructions
A field for entering instructions for the assistant.
Tools
Fields for configuring the assistant with the option to select true/false:
- Code interpreter(Tools) - The setting allows the assistant to write and run Python code in an isolated runtime environment. This tool can process files with a variety of data and formatting, as well as create files with data and graph images. The code Interpreter allows your Assistant to iteratively run code to solve complex code and mathematical problems. For more information, see here.
- Retrieval(Tools) - Extraction complements the assistant with knowledge beyond its model, such as private product information or documents provided by your users. After the file is uploaded and transferred to the assistant, the documents are automatically divided into parts, indexed and attachments are saved. For more information, see here.
Function(Tools)
A field for entering a function that the assistant can use. Assistants API supports function calling. Function calling allows you to describe functions to the Assistants and have it intelligently return the functions that need to be called along with their arguments. The Assistants API will pause execution during a Run when it invokes functions, and you can supply the results of the function call back to continue the Run execution.
For more information, see here.
The following function input format is used:
[{"type": "function", "function": {"name": "function_name","parameters": {},"description": "function_description"}]
Example of launching a node
It is necessary to run the Create Assistant node once with the parameters:
- API Key - Your API key;
- Model ID - gpt-3.5-turbo;
- Assistant name - Latenode platform assistant;
- Description - An assistant answering questions about the user's work on the Latenode platform, for example, about creating scenarios, nodes, routes.
The result of the node execution is the creation of an assistant named assistant Latenode platform assistant. The output data of the node Create Assistant are the parameters of the assistant:
Create Run
Create Run an action type node required to create a run for which the assistant will start processing messages.
Node Configuration
To configure the Create Run node, you must fill in the required and optional fields.
The required* fields include:
- API Key;
- Thread ID;
- Assistant ID.
API Key
The field required for entering the API key (see more details here).
Thread ID
The field required to specify the ID of the thread in which the message processing should be started.
Assistant ID
The field required to specify the ID of the assistant that will process the thread messages after run.
Metadata
The field required to enter additional information about the assistant in the key-value format. The key can contain 64 characters, and the value can contain 512 characters.
System instructions
A field for entering instructions for run.
Model ID
Drop-down list to select the desired version of the GPT Chatbot model (see more details here). By default, the field is filled with the gpt-4 value.
Tools
Fields for configuring the assistant with the option to select true/false:
- Code interpreter(Tools) - The setting allows the assistant to write and run Python code in an isolated runtime environment. This tool can process files with a variety of data and formatting, as well as create files with data and graph images. The code Interpreter allows your Assistant to iteratively run code to solve complex code and mathematical problems. For more information, see here.
- Retrieval(Tools) - Extraction complements the assistant with knowledge beyond its model, such as private product information or documents provided by your users. After the file is uploaded and transferred to the assistant, the documents are automatically divided into parts, indexed and attachments are saved. For more information, see here.
Function(Tools)
A field for entering a function that the assistant can use. Assistants API supports function calling. Function calling allows you to describe functions to the Assistants and have it intelligently return the functions that need to be called along with their arguments. The Assistants API will pause execution during a Run when it invokes functions, and you can supply the results of the function call back to continue the Run execution.
For more information, see here.
The following function input format is used:
[{"type": "function", "function": {"name": "function_name","parameters": {},"description": "function_description"}]
Example of launching a node
It is necessary to run the node Create Run once with the parameters:
- API Key - Your API key;
- Thread ID - ID of an existing platform thread;
- Assistant ID - ID of an existing platform assistant.
The result of node execution is the creation of a run for processing and receiving a response to a message from a specified thread by a specified assistant:
Delete Thread
Delete Thread an action type node required to delete a previously created thread.
Node Configuration
To configure the Delete Thread node, you must fill in the required fields.
The required* fields include:
- API Key;
- Thread ID.
API Key
The field required for entering the API key (see more details here).
Thread ID
The field required to specify the ID of the thread to be deleted.
Example of launching a node
It is necessary to run the Delete Thread node once with the parameters:
- API Key - Your API key;
- Thread ID - ID of the previously created thread.
The result of node execution is the deletion of a previously created thread. The output data of the Delete Thread node is the deletion status and the thread ID:
Send Message
Send Message - an action type node required to send a GPT Chatbot message and receive a response, regardless of assistants, threads, and runs. When sending a message, you can select the GPT Chatbot version.
Node Configuration
To configure the Send Message node, you must fill in the required and optional fields.
Required* fields include:
- Message;
- API Key.
Message
The field required for entering the text of the message to the GPT chatbot.
API Key
The field required for entering the API key (see more details here).
GPT Version
A field for selecting the desired version of the GPT chatbot model (see more details here). By default, the field is filled with the value gpt-3.5-turbo.
Example of Node Usage
To receive a response from the GPT chatbot, you need to create a scenario with nodes:
1. Trigger on Webhook node is used to trigger the scenario and pass a text question, for example, What is the most popular programming language?;
2. Send Message node is used to send the question to the GPT chatbot;
3. Webhook response for receiving a response to a message.
The result of executing this scenario is the response from the GPT chatbot, for example:
As of 2021, the most popular programming language is JavaScript. It is widely used for web development and is supported by all major web browsers. Other popular programming languages include Python, Java, C++, and C#. The popularity of programming languages can vary depending on the specific domain or industry.
Create Message
Create Message - an action type node required to send a GPT chatbot message using a given thread.
Node Configuration
To configure the Create Message node, you must fill in the required and optional fields.
Required* fields include:
- Message content;
- API Key;
- Thread ID.
API Key
The field required for entering the API key (see more details here).
Thread ID
The field required to specify the ID of the thread to which the message should be sent.
Message content
The text field required to enter the message.
File IDs list
A list of File IDs that the message should use. There can be a maximum of 10 files attached to a message.
Metadata
The field required to enter additional information about the assistant in the key-value format. The key can contain 64 characters, and the value can contain 512 characters.
Entity role
The role of the entity that is creating the message. Currently only user is supported.
Example of launching a node
It is necessary to run the Create Message node once with the parameters:
- API Key - Your API key;
- Thread ID - id of the previously created thread;
- Message content - How do I add a node to the scenario?;
- Entity role - User.
The result of the node execution is the creation of a message with the specified text. The output of the Create Message node is the message parameters.
Create Thread
Create Thread - an action type node required to create a thread.
Node Configuration
To configure the Create Thread node, you must fill in the required and optional fields.
Required* fields include:
- API Key.
API Key
The field required for entering the API key (see more details here).
New message
A field with the option to select true/false. If true is checked, a message will be sent in the Message content field when creating a thread. If false is checked, the thread will be created empty.
Message content
The text field required to enter the message.
File IDs list
A list of File IDs that the message should use. There can be a maximum of 10 files attached to a message.
Metadata
The field required to enter additional information about the assistant in the key-value format. The key can contain 64 characters, and the value can contain 512 characters.
Entity role
The role of the entity that is creating the message. Currently only user is supported.
Example of launching a node
It is necessary to run the Create Thread node once with the parameters:
- API Key - Your API key;
- New message - true;
- Message content - Welcome to the Latenode platform! I am waiting for your questions;
- Entity role - User.
The result of node execution is the creation of a thread with the specified message (if such a setting has been made). The output data of the Create Thread node are the parameters of the thread.
GPT 3.5 turbo instruct
GPT 3.5 turbo instruct - an action type node required to send a GPT Chatbot message of the gpt-3.5-turbo-instruct version and receive a response regardless of assistants, threads and runs. When sending a message, the choice of the GPT Chatbot version is NOT available.
Node Configuration
To configure the GPT 3.5 turbo instruct node, you must fill in the required and optional fields.
Required* fields include:
- Message;
- API Key.
Message
The field required for entering the text of the message to the GPT Chatbot.
API Key
The field required for entering the API key (see more details here).
Example of launching a node
It is necessary to run the GPT 3.5 turbo instruct node once with the parameters:
- API Key - Your API key;
- Message - What is the most popular programming language?.
The result of node execution is the formation of a response to a given message. The output data of the GPT 3.5 turbo instruct node are message parameters, including text.
Delete Assistant
Delete Assistant an action type node required to delete a previously created assistant.
Node Configuration
To configure the Delete Assistant node, you must fill in the required fields.
The required* fields include:
- API Key;
- Assistant ID.
API Key
The field required for entering the API key (see more details here).
Assistant ID
The field required to specify the ID of the assistant to be deleted.
Example of launching a node
It is necessary to launch the Delete Assistant node once with the parameters:
- API Key - Your API key;
- Assistant ID - the ID of the previously created assistant.
The result of the node execution is the deletion of the previously created assistant. The output data of the Delete Assistant node is the delete status and the assistant ID.
Download File
Download File - an action type node required for downloading chatbot files uploaded to GPT.
Node Configuration
To set up the Download File node, you must fill in the required fields.
Required* fields include:
- API Key;
- File ID.
API Key
The field required for entering the API key (see more details here).
File ID
ID of the previously uploaded file that needs to be downloaded.
Example of launching a node
It is necessary to launch the Download File node once with the parameters:
- API Key - Your API key;
- File ID - ID of the previously uploaded file.
The result of node execution is file download. The output data of the Download File node is the file parameters, including the content.
Modify Assistant
Modify Assistant - an action type node required to modify an already created GPT Chatbot assistant.
Node Configuration
To configure the Modify Assistant node, you must fill in the required and optional fields.
Required* fields include:
- API Key;
- Assistant ID.
API Key
The field required for entering the API key (see more details here).
Assistant ID
A field for entering the ID of the assistant whose parameters need to be replaced.
Model ID
Drop-down list to select the desired version of the GPT Chatbot model (see more details here). By default, the field is filled with the value gpt-3.5-turbo.
File IDs list
A field for entering file IDs that the assistant can use, for example, to write code, if these features are enabled.
The following format for entering file IDs is used:
["file-abc123","file-abc456"].
Metadata
The field required to enter additional information about the assistant in the key-value format. The key can contain 64 characters, and the value can contain 512 characters.
Assistant name
A field for entering the name of the assistant. The name can contain up to 256 characters.
Description
A field for entering a description of the assistant. The description can contain up to 512 characters.
System instructions
A field for entering instructions for the assistant.
Tools
Fields for configuring the assistant with the option to select true/false:
- Code interpreter(Tools) - The setting allows the assistant to write and run Python code in an isolated runtime environment. This tool can process files with a variety of data and formatting, as well as create files with data and graph images. The code Interpreter allows your Assistant to iteratively run code to solve complex code and mathematical problems. For more information, see here.
- Retrieval(Tools) - Extraction complements the assistant with knowledge beyond its model, such as private product information or documents provided by your users. After the file is uploaded and transferred to the assistant, the documents are automatically divided into parts, indexed and attachments are saved. For more information, see here.
Function(Tools)
A field for entering a function that the assistant can use. Assistants API supports function calling. Function calling allows you to describe functions to the Assistants and have it intelligently return the functions that need to be called along with their arguments. The Assistants API will pause execution during a Run when it invokes functions, and you can supply the results of the function call back to continue the Run execution.
For more information, see here.
The following function input format is used:
[{"type": "function", "function": {"name": "function_name","parameters": {},"description": "function_description"}]
Example of launching a node
It is necessary to run the Modify Assistant node once with the parameters:
- API Key - Your API key;
- Assistant ID - ID of the previously created assistant;
- Model ID - gpt-3.5-turbo;
- Assistant name - Latenode platform assistant version 2.
The result of the node execution is the change of the previously created assistant, including its name to Latenode platform assistant version 2. The output data of the Modify Assistant node are the assistant parameters:
Modify Run
Modify Run is an action type node required to change the run metadata in the selected GPT chatbot thread.
Node Configuration
To configure the Modify Run node, you must fill in the required and optional fields.
The required* fields include:
- Run ID;
- API Key;
- Thread ID.
API Key
The field required for entering the API key (see more details here).
Thread ID
The field required to specify the ID of the thread in which the run needs to be changed.
Run ID
ID of the run whose metadata needs to be changed.
Metadata
The field required to enter additional information about the assistant in the key-value format. The key can contain 64 characters, and the value can contain 512 characters.