Init the to chatgpt

.gitignore

@@ -0,0 +1,132 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+*.DS_Store
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+*.db
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+.idea

Dockerfile

@@ -0,0 +1,16 @@
+FROM python:3.10-slim-buster
+
+WORKDIR /app
+
+COPY . .
+
+RUN pip install poetry
+
+RUN poetry install
+
+ENV PATH=$PATH:/usr/local/bin
+
+EXPOSE 8000
+
+# Set the command to run the application
+CMD ["poetry", "run", "python", "app.py", "-a", "new_bing"]

README.md

@@ -0,0 +1,135 @@
+# TO CHATGPT
+
+**Make you feel free to use ALL chatgpt applications!!!**
+
+There are many LLM online services now, but most of the desktop clients, browser plugins, and ChatGPT-enhanced Web currently use OpenAI interfaces. If this restriction can be broken, I believe it will make us **get off work earlier**, such as claude, cohere, new bing, google bard, etc.
+
+For this, and inspired by the [claude to chatgpt](https://github.com/jtsang4/claude-to-chatgpt) project, I decided to give it a try, go go go !!!
+
+## Usage
+
+Before using, you need to ensure that the current environment can access the corresponding llm services.
+
+### adapter param
+
+It is worth noting that there are currently **two types of adapters**, one is asynchronous and the other is synchronous.
+The factor that decides which category to use is the sdk that currently accesses the online LLM service.
+If an asynchronous interface is provided, asynchronous implementation will be given priority.
+
+Specify the adapter through `-a`, which has been implemented so far.
+
+**async adapters**:
+
+- claude, implemented using [anthropic-sdk-python](https://github.com/anthropics/anthropic-sdk-python). The current account needs to apply, if successful, you can use it for **free** for personal daily use.
+- cohere, implemented using [cohere-python](https://github.com/cohere-ai/cohere-python). You only need to register an account, and you can use it for **free** for individuals, but there is a rate limit, five times a minute.
+- new_bing, implemented using [EdgeGPT](https://github.com/acheong08/EdgeGPT), which is reverse engineered API of Microsoft's Bing Chat AI. Because Currently new bing does not provide an official sdk, and it caused this way is **unstable**.
+
+**sync adapters**:
+
+- bard, implemented using [Bard](https://github.com/acheong08/Bard/), which is reverse engineered API of Google Bard. And it's also **unstable**.
+
+If you want to use the `cohere` api in ChatGPT applications now, you only need to start the service, like:
+
+```bash
+python app.py -a cohere
+```
+
+Another point to note is that because some APIs are non-asynchronous, such as the current `bard`, you need to run the `app_sync.py` file, like:
+
+```bash
+python app_sync.py -a bard
+```
+
+### source code
+
+```bash
+git clone https://github.com/SimFG/to-chatgpt
+cd to-chatgpt
+
+pip install poetry
+poetry install
+python app.py -a new_bing
+```
+
+### docker
+
+```bash
+docker pull simfg/to_chatgpt:latest
+
+docker run -d -p 8000:8000 simfg/to_chatgpt:0.1
+```
+
+Specify the adapter to run the service.
+
+```bash
+docker run -d -p 8000:8000 simfg/to_chatgpt:latest poetry run python app.py -a new_bing
+```
+
+## How to use it
+
+If you find that the service **does not respond normally, you can check if there is any error output in the service console.** It is very likely that there is a problem accessing the llm service.
+
+If you want to specify the port of the service, you can use the `-p` parameter.
+
+Set the **openai base url** in the chatgpt application as the service address. Generally, this option is near the openai api key.
+
+Different adapters have different usage methods, and the instructions are as follows.
+
+1. claude
+
+After starting the service, specify the api key of the claude service where OPENAI_API_KEY is required.
+
+2. cohere
+
+After starting the service, specify the api key of the cohere service where OPENAI_API_KEY is required.
+
+3. new bing
+
+Nothing, but it's unstable.
+
+4. bard
+
+After starting the service, specify `__Secure-1PSID` cookie where OPENAI_API_KEY is required.
+
+The way to get the cookie:
+
+- F12 for console
+- Copy the values
+  - Session: Go to Application → Cookies → __Secure-1PSID. Copy the value of that cookie.
+
+more details: [Bard](https://github.com/acheong08/Bard/)
+
+## Roadmap
+
+### Support more llm services
+
+- [text-generation-inference](https://github.com/huggingface/text-generation-inference)
+- open-assistant
+
+If there are other llm services, **welcome to open a pr and write it here**!!!
+
+### Manage your llm service and its data
+
+Through this service, in addition to conversion, LLM requests and related data can also be managed.
+
+**Of course, I may not have time to do all the functions below, all of which are my personal imagination.**
+
+- Customize the service key to limit service requests
+- LLM service key management
+- Request limit
+- Whitelist and Blacklist IP 
+- Record the request history
+- Manager the request info page, like show/download/delete/various charts...
+
+## Awesome chatgpt applications
+
+### plugins
+- [openai-translator](https://github.com/openai-translator/openai-translator)
+- [chathub](https://github.com/chathub-dev/chathub)
+
+### client
+
+- [raycast chatgpt extension](https://github.com/raycast/extensions/blob/c0f80c73f39b1cd7159e53b706c452c12648f0a9/extensions/chatgpt/README.md)
+
+If there are other awesome chatgpt applications, **welcome to open a pr and write it here**!!!
+

app.py

@@ -0,0 +1,62 @@
+import argparse
+from typing import Optional
+
+import uvicorn
+from fastapi import Request
+
+from to_chatgpt import common
+from to_chatgpt.common import BaseAdapter, init_app
+
+adapter: Optional[BaseAdapter] = None
+app = init_app()
+server_name = "new_bing"
+
+
+@app.get("/")
+async def hello():
+    return f"hello, {server_name} to chatgpt server"
+
+
+@app.api_route(
+    "/v1/chat/completions", methods=["POST", "OPTIONS"],
+)
+async def chat(request: Request):
+    return await common.achat(adapter, request)
+
+
+def run():
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "-s", "--host", default="0.0.0.0", help="the hostname to listen on"
+    )
+    parser.add_argument(
+        "-p", "--port", type=int, default=8000, help="the port to listen on"
+    )
+    parser.add_argument(
+        "-a", "--adapter", default=server_name, help="the name of server adapter"
+    )
+    parser.add_argument("-l", "--log", default="debug", help="the log level")
+
+    args = parser.parse_args()
+
+    global adapter
+    if args.adapter == "new_bing":
+        from to_chatgpt.new_bing import NewBingAdapter
+
+        adapter = NewBingAdapter()
+    elif args.adapter == "claude":
+        from to_chatgpt.claude import ClaudeAdapter
+
+        adapter = ClaudeAdapter()
+    elif args.adapter == "cohere":
+        from to_chatgpt.cohere import CohereAdapter
+
+        adapter = CohereAdapter()
+    else:
+        raise ValueError(f"unknown adapter: {args.adapter}")
+
+    uvicorn.run(app, host=args.host, port=args.port, log_level=args.log)
+
+
+if __name__ == "__main__":
+    run()