Mercurial > repos > bgruening > chatgpt_openai_api

comparison README.md @ 3:7770a4bd42e2 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/chatgpt commit c21d9a2cb410ee30dc47f4a13247862481816266
author bgruening
date Wed, 11 Sep 2024 16:36:21 +0000
parents f256dc85e1a0
children
comparison
equal deleted inserted replaced
2:dab494dce303 3:7770a4bd42e2
1 # ChatGPT Galaxy tool 1 # ChatGPT Galaxy tool
2 2
3 ## What it does 3 ## What it does
4 4
5 This tool leverages OpenAI's ChatGPT API to generate responses based on user-provided context and questions. 5 This tool leverages OpenAI's ChatGPT API to generate responses based on user-provided context and prompt.
6 Users can upload context data in various formats and ask questions related to that data. 6 Users can upload context data in various formats and ask questions or execute prompts related to that data.
7 The tool then uploads the data to a OpenAI server and processes them using the selected ChatGPT model, returning an AI-generated response tailored to the context provided. 7 The tool then uploads the data to a OpenAI server and processes them using the selected ChatGPT model, returning an AI-generated response tailored to the context provided.
8 8
9 To utilize this tool, users need to input their OpenAI API key in the user preferences. To obtain an API key, visit https://platform.openai.com/account/api-keys. 9 To utilize this tool, users need to input their OpenAI API key in the user preferences. To obtain an API key, visit https://platform.openai.com/account/api-keys.
10 10
11 Make sure to setup the payment method in your OpenAI account to use the API key in here: https://platform.openai.com/settings/organization/billing/
12
11 When you run this tool, your input data is sent to OpenAI's servers using your API-key. 13 When you run this tool, your input data is sent to OpenAI's servers using your API-key.
12 OpenAI's models process the data and generate a response based on the context and question provided. 14 OpenAI's models process the data and generate a response based on the context and prompt provided.
13 After receiving the response from the OpenAI server, the tool returns it to Galaxy and puts it in your history. 15 After receiving the response from the OpenAI server, the tool returns it to Galaxy and puts it in your history.
14 The files that have been uploaded are then deleted from the OpenAI's server, so they are not stored beyond their necessary use. 16 The files that have been uploaded are then deleted from the OpenAI's server, so they are not stored beyond their necessary use.
15 If the tool fails to delete your uploaded files automatically, you can manually delete them by visiting https://platform.openai.com/storage/. You might want to check your OpenAI storage from time to time as they also have a quota. 17 If the tool fails to delete your uploaded files automatically, you can manually delete them by visiting https://platform.openai.com/storage/. You might want to check your OpenAI storage from time to time as they also have a quota.
16 18
17 ## Usage 19 ## Usage
18 20
19 **Input** 21 **Input**
20 22
21 1. **Upload Context Data**: Users can upload up to 500 files in formats such as DOC, DOCX, HTML, JSON, PDF, TXT, JPG, JPEG, PNG, WEBP, or GIF. 23 1. **Upload Context Data**: Users can upload up to 500 files in formats such as DOC, DOCX, HTML, JSON, PDF, TXT, JPG, JPEG, PNG, WEBP, or GIF.
22 This context data serves as the background information for the question you wish to ask. 24 This context data serves as the input for the prompt you wish to execute.
23 25
24 2. **Ask a Question**: Once the context data is added, users can pose a question related to the content. 26 2. **Provide a Prompt**: Once the context data is added, users can provide a prompt for a task ChatGPT should execute.
25 The more specific the question, the more tailored the response will be. 27 The more specific the prompt, the more tailored the response will be.
28
29 [General thoughts on prompting with GPT-4](https://help.openai.com/en/articles/4936848-how-do-i-create-a-good-prompt-for-an-ai-model-like-gpt-4)
30
31 [Open Ai's prompt example page for more information](https://platform.openai.com/docs/examples)
26 32
27 3. **Select a Model**: Choose the ChatGPT model that best fits your needs. 33 3. **Select a Model**: Choose the ChatGPT model that best fits your needs.
28 Information about different models and their pricing can be found at https://platform.openai.com/docs/models and https://openai.com/api/pricing. 34 Information about different models and their pricing can be found at https://platform.openai.com/docs/models and https://openai.com/api/pricing.
29 35
30 36
31 **Output** 37 **Output**
32 38
33 The output is a response generated by ChatGPT, crafted based on the provided context data and the question posed. 39 The output is a response generated by ChatGPT, crafted based on the provided context data and the prompt posed.
34 This response is saved in the `output.txt` file. 40 This response is saved in the `output.txt` file.
35 41