⚠️ This is an experimental version. ⚠️

Product Manager

Developer

DevOps

Tell your AI team what microservice you want to build, and they will do it for you. Your imagination is the limit!

Welcome to Dev GPT, where we bring your ideas to life with the power of advanced artificial intelligence! Our automated development team is designed to create microservices tailored to your specific needs, making your software development process seamless and efficient. Comprised of a virtual Product Manager, Developer, and DevOps, our AI team ensures that every aspect of your project is covered, from concept to deployment.

pip install dev-gpt
dev-gpt generate

• OpenAI key with access to gpt-3.5-turbo or gpt-4

dev-gpt configure --key <your openai api key>

If you set the environment variable OPENAI_API_KEY, the configuration step can be skipped. Your api key must have access to gpt-4 to use this tool. We are working on a way to use gpt-3.5-turbo as well.

dev-gpt generate \
--description "<description of the microservice>" \
--model <gpt-3.5-turbo or gpt-4> \
--path </path/to/local/folder>

To generate your personal microservice two things are required:

• A description of the task you want to accomplish. (optional)
• The model you want to use - either gpt-3.5-turbo or gpt-4. gpt-3.5-turbo is ~10x cheaper, but will not be able to generate as complex microservices. (default: largest you have access to)
• A path on the local drive where the microservice will be generated. (default: ./microservice)

The creation process should take between 5 and 15 minutes. During this time, GPT iteratively builds your microservice until it finds a strategy that make your test scenario pass.

Be aware that the costs you have to pay for openai vary between $0.50 and $3.00 per microservice using GPT-4 or $0.05 to $0.30 for GPT-3.5-Trubo.

Run the microservice locally in docker. In case docker is not running on your machine, it will try to run it without docker. With this command a playground opens in your browser where you can test the microservice.

dev-gpt run --path <path to microservice>

If you want to deploy your microservice to the cloud a Jina account is required. When creating a Jina account, you get some free credits, which you can use to deploy your microservice ($0.025/hour). If you run out of credits, you can purchase more.

dev-gpt deploy --microservice_path <path to microservice>

To save credits you can delete your microservice via the following commands:

jc list # get the microservice id
jc delete <microservice id>

In this section you can get a feeling for the kind of microservices that can be generated with Dev-GPT.

dev-gpt generate \
--description "The user writes something and gets a related deep compliment." \
--model gpt-4

dev-gpt generate \
--description "Extract text from a news article URL using Newspaper3k library and generate a summary using gpt. Example input: http://fox13now.com/2013/12/30/new-year-new-laws-obamacare-pot-guns-and-drones/" \
--model gpt-4

dev-gpt generate \
--description "Convert a chemical formula into a 2D chemical structure diagram. Example inputs: C=C, CN=C=O, CCC(=O)O" \
--model gpt-4

dev-gpt generate \
--description "create a 2d rendering of a whole 3d object and x,y,z object rotation using trimesh and pyrender.OffscreenRenderer with os.environ['PYOPENGL_PLATFORM'] = 'egl' and freeglut3-dev library - example input: https://graphics.stanford.edu/courses/cs148-10-summer/as3/code/as3/teapot.obj" \
--model gpt-4

dev-gpt generate \
--description "Generate personalized product recommendations based on user product browsing history and the product categories fashion, electronics and sport. Example: Input: browsing history: prod1(electronics),prod2(fashion),prod3(fashion), output: p4(fashion)" \
--model gpt-4

dev-gpt generate \
--description "Given a search query, find articles on hacker news using the hacker news api and return a list of (title, author, website_link, first_image_on_the_website)" \
--model gpt-4

dev-gpt generate \
--description "Given an image, return the image with bounding boxes of all animals (https://pjreddie.com/media/files/yolov3.weights, https://raw.githubusercontent.com/pjreddie/darknet/master/cfg/yolov3.cfg), Example input: https://images.unsplash.com/photo-1444212477490-ca407925329e" \
--model gpt-4

dev-gpt generate \
--description "Generate a meme from an image and a caption. Example input: https://media.wired.com/photos/5f87340d114b38fa1f8339f9/master/w_1600,c_limit/Ideas_Surprised_Pikachu_HD.jpg, TOP:When you discovered GPT Dev" \
--model gpt-4

dev-gpt generate \
--description "Given a word, return a list of rhyming words using the datamuse api" \
--model gpt-4

dev-gpt generate \
--description "Generate a word cloud from a given text" \
--model gpt-4

dev-gpt generate \
--description "Given a 3d object, return vertex count and face count. Example: https://raw.githubusercontent.com/polygonjs/polygonjs-assets/master/models/wolf.obj" \
--model gpt-4

dev-gpt generate \
--description "Given a URL, extract all tables as csv. Example: http://www.ins.tn/statistiques/90" \
--model gpt-4

dev-gpt generate \
--description "Create mel spectrogram from audio file. Example: https://cdn.pixabay.com/download/audio/2023/02/28/audio_550d815fa5.mp3" \
--model gpt-4

dev-gpt generate \
--description "Convert text to speech" \
--model gpt-4

dev-gpt generate \
--description "Create a heatmap from an image and a list of relative coordinates. Example input: https://images.unsplash.com/photo-1574786198875-49f5d09fe2d2, [[0.1, 0.2], [0.3, 0.4], [0.5, 0.6], [0.2, 0.1], [0.7, 0.2], [0.4, 0.2]]" \
--model gpt-4

dev-gpt generate \
--description "Generate QR code from URL. Example input: https://www.example.com" \
--model gpt-4 

dev-gpt generate \
--description "Visualize the Mandelbrot set with custom parameters. Example input: center=-0 1i, zoom=1.0, size=800x800, iterations=1000" \
--model gpt-4

dev-gpt generate --description "Convert markdown to HTML"

The graphic below illustrates the process of creating a microservice and deploying it to the cloud elaboration two different implementation strategies.

graph TB

    description[description: generate QR code from URL] --> make_strat{think a}

    test[test: https://www.example.com] --> make_strat[generate strategies]

    make_strat --> implement1[implement strategy 1]

    implement1 --> build1{build image}

    build1 -->|error message| implement1

    build1 -->|failed 10 times| implement2[implement strategy 2]

    build1 -->|success| registry[push docker image to registry]

    implement2 --> build2{build image}

    build2 -->|error message| implement2

    build2 -->|failed 10 times| all_failed[all strategies failed]

    build2 -->|success| registry[push docker image to registry]

    registry --> deploy[deploy microservice]

    deploy --> streamlit[generate streamlit playground]

    streamlit --> user_run[user tests microservice]

1. Dev-GPT identifies several strategies to implement your task.
2. It tests each strategy until it finds one that works.
3. For each strategy, it generates the following files:

• microservice.py: This is the main implementation of the microservice.
• test_microservice.py: These are test cases to ensure the microservice works as expected.
• requirements.txt: This file lists the packages needed by the microservice and its tests.
• Dockerfile: This file is used to run the microservice in a container and also runs the tests when building the image.

4. Dev-GPT attempts to build the image. If the build fails, it uses the error message to apply a fix and tries again to build the image.
5. Once it finds a successful strategy, it:

• Pushes the Docker image to the registry.
• Deploys the microservice.
• Generates a Streamlit playground where you can test the microservice.

6. If it fails 10 times in a row, it moves on to the next approach.

Use natural language interface to generate, deploy and update your microservice infrastructure.

If you want to contribute to this project, feel free to open a PR or an issue. In the following, you can find a list of things that need to be done.

next steps:

• check if windows and linux support works
• add video to README.md
• bug: it can happen that the code generation is hanging forever - in this case aboard and redo the generation
• new user has free credits but should be told to verify account

Nice to have:

• smooth rendering animation of the responses
• if the user runs dev-gpt without any arguments, show the help message
• don't show this message: 🔐 You are logged in to Jina AI as florian.hoenicke (username:auth0-unified-448f11965ce142b6). To log out, use jina auth logout.
• put the playground into the custom gateway (without rebuilding the custom gateway)
• hide prompts in normal mode and show them in verbose mode
• tests
• clean up duplicate code
• support popular cloud providers - lambda, cloud run, cloud functions, ...
• support local docker builds
• autoscaling enabled for cost saving
• add more examples to README.md
• support multiple endpoints - example: todolist microservice with endpoints for adding, deleting, and listing todos
• support stateful microservices
• The playground is currently printed twice even if it did not change. Make sure it is only printed twice in case it changed.
• allow to update your microservice by providing feedback
• support for other large language models like Open Assistent
• for cost savings, it should be possible to insert less context during the code generation of the main functionality - no jina knowledge is required
• use dev-gpt list to show all deployments
• dev-gpt delete to delete a deployment
• dev-gpt update to update a deployment
• test param optional - in case the test param is not there first ask gpt if more information is required to write a test - like access to pdf data
• section for microservices built by the community
• test feedback for playground generation (could be part of the debugging)
• should we send everything via json in the text attribute for simplicity?
• fix release workflow
• after the user specified the task, ask them questions back if the task is not clear enough or something is missing

Proposal:

• just generate the non-jina related code and insert it into an executor template
• think about strategies after the first approach failed?