Improve prompt ...

Add dev instructions to CONTRIBUTING, add default lib install instruction to README

Author: ricklamers

.github/CONTRIBUTING.md

@@ -15,14 +15,44 @@ First of all, thank you for your interest in contributing to gpt-code-ui! We app
   - [Commit Messages](#commit-messages)
 - [Additional Resources](#additional-resources)
 
-## Code of Conductcode
+## Code of Conduct
 
 All contributors are expected to adhere to our [Code of Conduct](CODE_OF_CONDUCT.md). Please read it before participating in the gpt-code-ui community.
 
 ## Getting Started
 
 1. Fork the repository and clone it to your local machine.
-2. Set up the development environment by following the instructions in the [README.md](https://github.com/ricklamers/gpt-code-ui/tree/main/README.md) file.
+2. Set up the development environment as follows:
+
+To install the package as an editable Python package run:
+```sh
+pip install -e .
+```
+
+To run the backend:
+```sh
+gptcode
+```
+
+To run the frontend in dev mode such that frontend code changes automatically update, set 
+the following environment variable such that the frontend knows where to
+find the backend API server.
+
+`export VITE_WEB_ADDRESS=http://localhost:8080`
+
+Run the frontend in development mode (served by Vite):
+```sh
+cd frontend
+npm run dev
+```
+
+The HMR/auto reloading version of the frontend can now be found at http://localhost:5173 (default Vite port)
+
+Note, the frontend served at `http://localhost:8080` is stale comes from the static bundled files that can 
+be generated by running `make compile_frontend`.
+
+With this setup, code changes to the Flask backend still require restarting `gptcode` (backend).
+
 3. Explore the codebase, run tests, and verify that everything works as expected.
 
 ## How to Contribute

README.md

@@ -15,6 +15,13 @@ pip install gpt-code-ui
 gptcode
 ```
 
+In order to make basic dependencies available it's recommended to run the following `pip` install
+in the Python environment that is used in the shell where you run `gptcode`:
+
+```sh
+pip install "numpy>=1.24,<1.25" "dateparser>=1.1,<1.2" "pandas>=1.5,<1.6" "geopandas>=0.13,<0.14" "PyPDF2>=3.0,<3.1" "pdfminer>=20191125,<20191200" "pdfplumber>=0.9,<0.10" "matplotlib>=3.7,<3.8"
+```
+
 ## User interface
 <img src="https://github.com/ricklamers/gpt-code-ui/assets/1309307/c29c504a-a7ed-4ae0-9360-d7224bc3e3d6" alt="GPT-Code logo" width="100%" />
 

gpt_code_ui/webapp/main.py

@@ -58,7 +58,34 @@ def allowed_file(filename):
 
 async def get_code(user_prompt, user_openai_key=None, model="gpt-3.5-turbo"):
 
-    prompt = f"First, here is a history of what I asked you to do earlier. The actual prompt follows after ENDOFHISTORY. History:\n\n{message_buffer.get_string()}ENDOFHISTORY.\n\nWrite Python code that does the following: \n\n{user_prompt}\n\nNote, the code is going to be executed in a Jupyter Python kernel.\n\nLast instruction, and this is the most important, just return code. No other outputs, as your full response will directly be executed in the kernel. \n\nTeacher mode: if you want to give a download link, just print it as <a href='/download?file=INSERT_FILENAME_HERE'>Download file</a>. Replace INSERT_FILENAME_HERE with the actual filename. So just print that HTML to stdout. No actual downloading of files!"
+    prompt = f"""First, here is a history of what I asked you to do earlier. 
+    The actual prompt follows after ENDOFHISTORY. 
+    History:
+    {message_buffer.get_string()}
+    ENDOFHISTORY.
+    Write Python code, in a triple backtick Markdown code block, that does the following:
+    {user_prompt}
+    
+    Notes: 
+        First, think step by step what you want to do and write it down in English.
+        Then generate valid Python code in a code block 
+        Make sure all code is valid - it be run in a Jupyter Python 3 kernel environment. 
+        Define every variable before you use it.
+        For data munging, you can use 
+            'numpy', # numpy==1.24.3
+            'dateparser' #dateparser==1.1.8
+            'pandas', # matplotlib==1.5.3
+            'geopandas' # geopandas==0.13.2
+        For pdf extraction, you can use
+            'PyPDF2', # PyPDF2==3.0.1
+            'pdfminer', # pdfminer==20191125
+            'pdfplumber', # pdfplumber==0.9.0
+        For data visualization, you can use
+            'matplotlib', # matplotlib==3.7.1
+        Be sure to generate charts with matplotlib. If you need geographical charts, use geopandas with the geopandas.datasets module.
+        If the user has just uploaded a file, focus on the file that was most recently uploaded (and optionally all previously uploaded files)
+    
+    Teacher mode: if the code modifies or produces a file, end your output AFTER YOUR CODE BLOCK with a link to it as <a href='/download?file=INSERT_FILENAME_HERE'>Download file</a>. Replace INSERT_FILENAME_HERE with the actual filename. So just print that HTML to stdout at the end, AFTER your code block."""
     temperature = 0.7
     message_array = [
         {

setup.py

@@ -7,7 +7,7 @@
 
 setup(
     name='gpt_code_ui',
-    version='0.42.30',
+    version='0.42.31',
     description="An Open Source version of ChatGPT Code Interpreter",
     long_description=long_description,
     long_description_content_type='text/markdown',  # This field specifies the format of the `long_description`.