sf

controllers/{chat/Chat.py → OpenInterpreter/OpenInterpreter.py}

@@ -67,8 +67,9 @@ def chat_with_interpreter(
 ):  # , openai_api_key):
     # Set the API key for the interpreter
     # interpreter.llm.api_key = openai_api_key
-    interpreter.messages = []
+
     if message == "reset":
+        interpreter.messages = []
         interpreter.reset()
         return "Interpreter reset", history
     full_response = ""

controllers/test/.gpteng/memory/logs/all_output.txt

@@ -1,146 +0,0 @@
-
-2024-06-06T08:15:25.594683
-================================ System Message ================================
-
-You will get instructions for code to write.
-You will write a very long answer. Make sure that every detail of the architecture is, in the end, implemented as code.
-Think step by step and reason yourself to the correct decisions to make sure we get it right.
-First lay out the names of the core classes, functions, methods that will be necessary, As well as a quick comment on their purpose.
-
-You will output the content of each file necessary to achieve the goal, including ALL code.
-Represent files like so:
-
-FILENAME
-```
-CODE
-```
-
-The following tokens must be replaced like so:
-FILENAME is the lowercase combined path and file name including the file extension
-CODE is the code in the file
-
-Example representation of a file:
-
-src/hello_world.py
-```
-print("Hello World")
-```
-
-Do not comment on what every file does. Please note that the code should be fully functional. No placeholders.
-
-
-You will start with the "entrypoint" file, then go to the ones that are imported by that file, and so on.
-Please note that the code should be fully functional. No placeholders.
-
-Follow a language and framework appropriate best practice file naming convention.
-Make sure that files contain all imports, types etc.  The code should be fully functional. Make sure that code in different files are compatible with each other.
-Ensure to implement all code, if you are unsure, write a plausible implementation.
-Include module dependency or package manager dependency definition file.
-Before you finish, double check that all parts of the architecture is present in the files.
-
-When you are done, write finish with "this concludes a fully working implementation".
-
-Useful to know:
-Almost always put different classes in different files.
-Always use the programming language the user asks for.
-For Python, you always create an appropriate requirements.txt file.
-For NodeJS, you always create an appropriate package.json file.
-Always add a comment briefly describing the purpose of the function definition.
-Add comments explaining very complex bits of logic.
-Always follow the best practices for the requested languages for folder/file structure and how to package the project.
-
-
-Python toolbelt preferences:
-- pytest
-- dataclasses
-
-
-================================ Human Message =================================
-
-Request: y
-
-================================== Ai Message ==================================
-
-I'm happy to help! However, I need more information about the project you want me to implement. Could you please provide more details about the project, such as:
-
-* What is the project about? (e.g., web application, game, data analysis tool)
-* What features does it need to have?
-* Are there any specific technologies or frameworks you want me to use?
-* Are there any specific requirements or constraints I should be aware of?
-
-Once I have a better understanding of your project, I can start designing the architecture and implementing the code.
-
-Please provide more information, and I'll be happy to help!
-
-2024-06-06T08:16:10.259654
-================================ System Message ================================
-
-You will get instructions for code to write.
-You will write a very long answer. Make sure that every detail of the architecture is, in the end, implemented as code.
-Think step by step and reason yourself to the correct decisions to make sure we get it right.
-First lay out the names of the core classes, functions, methods that will be necessary, As well as a quick comment on their purpose.
-
-You will output the content of each file necessary to achieve the goal, including ALL code.
-Represent files like so:
-
-FILENAME
-```
-CODE
-```
-
-The following tokens must be replaced like so:
-FILENAME is the lowercase combined path and file name including the file extension
-CODE is the code in the file
-
-Example representation of a file:
-
-src/hello_world.py
-```
-print("Hello World")
-```
-
-Do not comment on what every file does. Please note that the code should be fully functional. No placeholders.
-
-
-You will start with the "entrypoint" file, then go to the ones that are imported by that file, and so on.
-Please note that the code should be fully functional. No placeholders.
-
-Follow a language and framework appropriate best practice file naming convention.
-Make sure that files contain all imports, types etc.  The code should be fully functional. Make sure that code in different files are compatible with each other.
-Ensure to implement all code, if you are unsure, write a plausible implementation.
-Include module dependency or package manager dependency definition file.
-Before you finish, double check that all parts of the architecture is present in the files.
-
-When you are done, write finish with "this concludes a fully working implementation".
-
-Useful to know:
-Almost always put different classes in different files.
-Always use the programming language the user asks for.
-For Python, you always create an appropriate requirements.txt file.
-For NodeJS, you always create an appropriate package.json file.
-Always add a comment briefly describing the purpose of the function definition.
-Add comments explaining very complex bits of logic.
-Always follow the best practices for the requested languages for folder/file structure and how to package the project.
-
-
-Python toolbelt preferences:
-- pytest
-- dataclasses
-
-
-================================ Human Message =================================
-
-Request: y
-
-================================== Ai Message ==================================
-
-I'm happy to help! However, I need more information about the project you want me to implement. Could you please provide more details about the project, such as:
-
-* What is the project about? (e.g., web application, game, chatbot, etc.)
-* What features do you want to implement?
-* Are there any specific technologies or frameworks you want to use?
-* Are there any specific requirements or constraints I should be aware of?
-
-Once I have a better understanding of your project, I can start implementing it in Python.
-
-Please provide more information, and I'll be happy to help!

controllers/test/.gpteng/memory/logs/gen_entrypoint_chat.txt

@@ -1,79 +0,0 @@
-
-2024-06-06T08:15:26.181845
-================================ System Message ================================
-
-You will get information about a codebase that is currently on disk in the current folder.
-The user will ask you to write a script that runs the code in a specific way.
-You will answer with code blocks that include all the necessary terminal commands.
-Do not install globally. Do not use sudo.
-Do not explain the code, just give the commands.
-Do not use placeholders, use example values (like . for a folder argument) if necessary.
-
-
-================================ Human Message =================================
-
-
-        Make a unix script that
-        a) installs dependencies
-        b) runs all necessary parts of the codebase (in parallel if necessary)
-        
-Information about the codebase:
-
-```
-```
-
-================================== Ai Message ==================================
-
-Here is a Unix script that installs dependencies and runs the codebase:
-```
-#!/bin/bash
-
-# Install dependencies
-pip install -r requirements.txt
-
-# Run the codebase
-python -m main &
-python -m worker &
-python -m api
-
-wait
-```
-Note: This script assumes that the codebase has a `requirements.txt` file for dependencies, a `main.py` file as the main entry point, a `worker.py` file as a worker process, and an `api.py` file as the API server. Adjust the script according to your actual codebase structure.
-
-2024-06-06T08:16:10.822878
-================================ System Message ================================
-
-You will get information about a codebase that is currently on disk in the current folder.
-The user will ask you to write a script that runs the code in a specific way.
-You will answer with code blocks that include all the necessary terminal commands.
-Do not install globally. Do not use sudo.
-Do not explain the code, just give the commands.
-Do not use placeholders, use example values (like . for a folder argument) if necessary.
-
-
-================================ Human Message =================================
-
-
-        Make a unix script that
-        a) installs dependencies
-        b) runs all necessary parts of the codebase (in parallel if necessary)
-        
-Information about the codebase:
-
-```
-```
-
-================================== Ai Message ==================================
-
-Here is a Unix script that installs dependencies and runs the codebase:
-```
-#!/bin/bash
-
-# Install dependencies
-pip install -r requirements.txt
-
-# Run the codebase
-python -m main & python -m worker &
-python -m api
-```
-Note: This script assumes that the codebase has a `requirements.txt` file for dependencies, a `main.py` file as the main entry point, a `worker.py` file that can be run in parallel, and an `api.py` file that depends on the other two. Adjust the script according to your actual codebase structure.

mysite/gradio/gradio_config.py

@@ -50,7 +50,7 @@ def setup_gradio_interfaces():
     )
 
     default_interfaces = [democs]#,demo]
-    default_names = ["仕様書から作成","Chat","OpenInterpreter","DataBase"]#"demo"]
+    default_names = ["仕様書から作成","OpenInterpreter","Chat","DataBase"]#"demo"]
 
     gradio_interfaces, gradio_names = include_gradio_interfaces()
 

routers/ai/prompt

@@ -1 +1 @@
-google apps script でLINEのプログラム
+y