Comments (10)
Yeah that is what I am trying now, to see what happens.
from gpt-engineer.
good
from gpt-engineer.
+1
from gpt-engineer.
+1
from gpt-engineer.
+1
from gpt-engineer.
+1
from gpt-engineer.
+1
from gpt-engineer.
I have been testing your app with a complex prompt. ChatGPT returns only a few files saying that the app is too complex and will need to continue writing the app after it's initial results.
That would require ChatGPT to see the files it has already written and continue writing the app, almost like a AutoGPT feature.
Is that something you can do?
from gpt-engineer.
you need to use the API to create multiple instance request to call back the last input message with a whole list of messages as a format.
Example:
import openai
openai.api_key = 'YOUR_API_KEY'
def continue_chat(prompt, messages):
response = openai.Completion.create(
engine='davinci-codex', # Use gpt3.5-turbo for shorter response times
prompt=prompt,
messages=messages,
max_tokens=50 # Adjust the value as per your requirements for your GPT
)
return response.choices[0].text.strip()
prompt = "continue chat returns input to prompts/messages"
messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "What happens next?"},
]
response = continue_chat(prompt, messages)
print(response
The continue_chat
function now takes messages and prompts and messages as input values then returns them as a generated response .then for messages=messages, you can make a list of generated callbacks/answers/ to continue the conversation.
Now your GPT has the ability to continue the conversation where its left off. ( Just don't be like me and try to give it ethical philosphies to take over the world..) - (TROLLING)
hope this helps all you though - if you have any questions feel free to ask. I have an updated GPT-engineer i'll be adding here soon which is a lot cleaner and has error handling with a few other features that were missing imo from most GPT-engineers I've seen on here so far from people. APPRECIATE ALL THE COOL STUFF EVERYONE DOES GOD BLESS YALL <3
from gpt-engineer.
Feel free to add to ideas in discussions
from gpt-engineer.
Related Issues (20)
- Exception: No files were selected. Please select at least one file to proceed. when i use improve mode HOT 3
- Bug: Parentheses around filenames HOT 2
- Enhancing Code Refactoring Capability for Advanced Code Generation HOT 2
- example improve file_selection.toml be rewritten the Initialization status HOT 2
- No chance to input and answer the gpte three question on generate complex application HOT 4
- Error while improving the project: '/dev/null' HOT 3
- How to use Anthropic models HOT 1
- Investigate/document how to use with OpenRouter HOT 6
- Ollama Multithreaded UI integration, issue with code testing below python 3.10 HOT 2
- upload the debug_log_file.txt According to project prompts HOT 1
- Getting "Could not resolve authentication method" – without a stacktrace HOT 3
- Missing support for the vision capabilities in the new model gpt-4-turbo HOT 5
- TypeError: Object of type Prompt is not JSON serializable – uploading learning HOT 2
- Error while improving the project: 'ascii' codec can't encode character '\u2019' in position 7: ordinal not in range(128) HOT 3
- Urgent - all PRs blocked because of failing tests HOT 4
- Applying diffs failing silently HOT 7
- keep getting error message when trying to run in terminal with all necessary items installed HOT 3
- The Video demo on the Main Repo is Corrupted HOT 4
- Docker build is broken HOT 30
- Add GPTE CLI argument to output system information HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from gpt-engineer.