Leo commited on
Commit
40cef76
Β·
1 Parent(s): ae7baed

Inital upload of working files

Browse files
Files changed (9) hide show
  1. .dockerignore +20 -0
  2. .env.sample +1 -0
  3. .gitignore +164 -0
  4. Dockerfile +42 -0
  5. README.md +69 -8
  6. app.py +94 -0
  7. chainlit.md +13 -0
  8. pyproject.toml +14 -0
  9. uv.lock +0 -0
.dockerignore ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Prevent secrets and junk from being baked into Docker images
2
+
3
+ # Secrets
4
+ .env
5
+ .env.*
6
+
7
+ # macOS junk
8
+ .DS_Store
9
+
10
+ # Python cache
11
+ __pycache__/
12
+ *.py[cod]
13
+
14
+ # Virtual environments
15
+ .venv/
16
+ venv/
17
+
18
+ # Git stuff (optional)
19
+ .git
20
+ .gitignore
.env.sample ADDED
@@ -0,0 +1 @@
 
 
1
+ OPENAI_API_KEY=###
.gitignore ADDED
@@ -0,0 +1,164 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Byte-compiled / optimized / DLL files
2
+ __pycache__/
3
+ *.py[cod]
4
+ *$py.class
5
+
6
+ # C extensions
7
+ *.so
8
+
9
+ # more stuff Leo
10
+ .DS_Store
11
+
12
+ # Distribution / packaging
13
+ .Python
14
+ build/
15
+ develop-eggs/
16
+ dist/
17
+ downloads/
18
+ eggs/
19
+ .eggs/
20
+ lib/
21
+ lib64/
22
+ parts/
23
+ sdist/
24
+ var/
25
+ wheels/
26
+ share/python-wheels/
27
+ *.egg-info/
28
+ .installed.cfg
29
+ *.egg
30
+ MANIFEST
31
+ .chainlit/
32
+
33
+ # PyInstaller
34
+ # Usually these files are written by a python script from a template
35
+ # before PyInstaller builds the exe, so as to inject date/other infos into it.
36
+ *.manifest
37
+ *.spec
38
+
39
+ # Installer logs
40
+ pip-log.txt
41
+ pip-delete-this-directory.txt
42
+
43
+ # Unit test / coverage reports
44
+ htmlcov/
45
+ .tox/
46
+ .nox/
47
+ .coverage
48
+ .coverage.*
49
+ .cache
50
+ nosetests.xml
51
+ coverage.xml
52
+ *.cover
53
+ *.py,cover
54
+ .hypothesis/
55
+ .pytest_cache/
56
+ cover/
57
+
58
+ # Translations
59
+ *.mo
60
+ *.pot
61
+
62
+ # Django stuff:
63
+ *.log
64
+ local_settings.py
65
+ db.sqlite3
66
+ db.sqlite3-journal
67
+
68
+ # Flask stuff:
69
+ instance/
70
+ .webassets-cache
71
+
72
+ # Scrapy stuff:
73
+ .scrapy
74
+
75
+ # Sphinx documentation
76
+ docs/_build/
77
+
78
+ # PyBuilder
79
+ .pybuilder/
80
+ target/
81
+
82
+ # Jupyter Notebook
83
+ .ipynb_checkpoints
84
+
85
+ # IPython
86
+ profile_default/
87
+ ipython_config.py
88
+
89
+ # pyenv
90
+ # For a library or package, you might want to ignore these files since the code is
91
+ # intended to run in multiple environments; otherwise, check them in:
92
+ # .python-version
93
+
94
+ # pipenv
95
+ # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
96
+ # However, in case of collaboration, if having platform-specific dependencies or dependencies
97
+ # having no cross-platform support, pipenv may install dependencies that don't work, or not
98
+ # install all needed dependencies.
99
+ #Pipfile.lock
100
+
101
+ # poetry
102
+ # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
103
+ # This is especially recommended for binary packages to ensure reproducibility, and is more
104
+ # commonly ignored for libraries.
105
+ # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
106
+ #poetry.lock
107
+
108
+ # pdm
109
+ # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
110
+ #pdm.lock
111
+ # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
112
+ # in version control.
113
+ # https://pdm.fming.dev/#use-with-ide
114
+ .pdm.toml
115
+
116
+ # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
117
+ __pypackages__/
118
+
119
+ # Celery stuff
120
+ celerybeat-schedule
121
+ celerybeat.pid
122
+
123
+ # SageMath parsed files
124
+ *.sage.py
125
+
126
+ # Environments
127
+ .env
128
+ .venv
129
+ env/
130
+ venv/
131
+ ENV/
132
+ env.bak/
133
+ venv.bak/
134
+
135
+ # Spyder project settings
136
+ .spyderproject
137
+ .spyproject
138
+
139
+ # Rope project settings
140
+ .ropeproject
141
+
142
+ # mkdocs documentation
143
+ /site
144
+
145
+ # mypy
146
+ .mypy_cache/
147
+ .dmypy.json
148
+ dmypy.json
149
+
150
+ # Pyre type checker
151
+ .pyre/
152
+
153
+ # pytype static type analyzer
154
+ .pytype/
155
+
156
+ # Cython debug symbols
157
+ cython_debug/
158
+
159
+ # PyCharm
160
+ # JetBrains specific template is maintained in a separate JetBrains.gitignore that can
161
+ # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
162
+ # and can be added to the global gitignore or merged into this file. For a more nuclear
163
+ # option (not recommended) you can uncomment the following to ignore the entire idea folder.
164
+ #.idea/
Dockerfile ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Get a distribution that has uv already installed
2
+ FROM ghcr.io/astral-sh/uv:python3.13-bookworm-slim
3
+
4
+ # Add Rust compiler installation
5
+ USER root
6
+ RUN apt-get update && apt-get install -y \
7
+ curl \
8
+ build-essential \
9
+ && rm -rf /var/lib/apt/lists/*
10
+ RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
11
+ ENV PATH="/root/.cargo/bin:${PATH}"
12
+
13
+ # Add user - this is the user that will run the app
14
+ # If you do not set user, the app will run as root (undesirable)
15
+ RUN useradd -m -u 1000 user
16
+ USER user
17
+
18
+ # Set up Rust for the user
19
+ RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
20
+ ENV PATH="/home/user/.cargo/bin:${PATH}"
21
+
22
+ # Set the home directory and path
23
+ ENV HOME=/home/user \
24
+ PATH=/home/user/.local/bin:$PATH
25
+
26
+ ENV UVICORN_WS_PROTOCOL=websockets
27
+
28
+ # Set the working directory
29
+ WORKDIR $HOME/app
30
+
31
+ # Copy the app to the container
32
+ COPY --chown=user . $HOME/app
33
+
34
+ # Install the dependencies
35
+ # RUN uv sync --frozen
36
+ RUN uv sync
37
+
38
+ # Expose the port
39
+ EXPOSE 7860
40
+
41
+ # Run the app
42
+ CMD ["uv", "run", "chainlit", "run", "app.py", "--host", "0.0.0.0", "--port", "7860"]
README.md CHANGED
@@ -1,12 +1,73 @@
1
  ---
2
- title: Llm2
3
- emoji: 😻
4
- colorFrom: green
5
- colorTo: pink
6
  sdk: docker
7
- pinned: false
8
- license: openrail
9
- short_description: 'LLM-based chatbot based on AIMakerspace tutorial '
10
  ---
11
 
12
- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ title: Beyond ChatGPT – Beginner LLM App
3
+ emoji: πŸ’¬
4
+ colorFrom: blue
5
+ colorTo: indigo
6
  sdk: docker
 
 
 
7
  ---
8
 
9
+ # πŸ’¬ Beyond ChatGPT – Beginner LLM App
10
+
11
+ This is a simple LLM-based chatbot built during the **Beyond ChatGPT** tutorial from [AI Makerspace](https://github.com/AI-Maker-Space/Beyond-ChatGPT).
12
+ It runs locally or in a Hugging Face Space using Docker.
13
+
14
+ The app connects to the OpenAI API and supports system messages, few-shot prompting, and chain-of-thought-style reasoning β€” all within a clean conversational UI.
15
+
16
+ ---
17
+
18
+ ## 🧠 What You Can Do
19
+
20
+ - Send prompts to a live OpenAI model
21
+ - Test structured prompting techniques
22
+ - Explore different system/assistant/user message configurations
23
+ - Use this app as a foundation for building your own LLM tools
24
+
25
+ ---
26
+
27
+ ## πŸš€ How to Use
28
+
29
+ If running on Hugging Face (or locally via Docker):
30
+
31
+ 1. Enter a prompt in the chat window
32
+ 2. Press `Enter` or click `Send`
33
+ 3. The model will respond in a conversational format
34
+
35
+ ---
36
+
37
+ ## πŸ”§ Tech Stack
38
+
39
+ - Python
40
+ - OpenAI API (`gpt-3.5-turbo` or similar)
41
+ - Chainlit (chat interface)
42
+ - Docker (for deployment)
43
+ - Hugging Face Spaces (hosted version)
44
+
45
+ ---
46
+
47
+ ## πŸ“¦ Tutorial Origin
48
+
49
+ This app was built as part of the *Beyond ChatGPT* tutorial by AI Makerspace:
50
+ πŸ”— https://github.com/AI-Maker-Space/Beyond-ChatGPT
51
+
52
+ ---
53
+
54
+ ## ⚠️ Notes
55
+
56
+ - You’ll need a valid OpenAI API key to run this locally or deploy it to Hugging Face.
57
+ - If using Docker, the app runs on port 7860 by default.
58
+
59
+ ---
60
+
61
+ ## πŸ§ͺ Example Prompt
62
+
63
+ ```
64
+ What are the key takeaways from the book "Thinking, Fast and Slow"?
65
+ ```
66
+
67
+ ---
68
+
69
+ ## πŸ™Œ Credits
70
+
71
+ Thanks to the team at AI Makerspace for the tutorial and code scaffold.
72
+
73
+ ---
app.py ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # You can find this code for Chainlit python streaming here (https://docs.chainlit.io/concepts/streaming/python)
2
+
3
+ # OpenAI Chat completion
4
+ import os
5
+ from openai import AsyncOpenAI # importing openai for API usage
6
+ import chainlit as cl # importing chainlit for our app
7
+ from chainlit.prompt import Prompt, PromptMessage # importing prompt tools
8
+ from chainlit.playground.providers import ChatOpenAI # importing ChatOpenAI tools
9
+ from dotenv import load_dotenv
10
+
11
+ load_dotenv()
12
+
13
+ # ChatOpenAI Templates
14
+ system_template = """You are a helpful assistant who always speaks in a pleasant tone!
15
+ """
16
+
17
+ user_template = """{input}
18
+ Think through your response step by step.
19
+ """
20
+
21
+
22
+ @cl.on_chat_start # marks a function that will be executed at the start of a user session
23
+ async def start_chat():
24
+ settings = {
25
+ "model": "gpt-3.5-turbo",
26
+ "temperature": 0,
27
+ "max_tokens": 500,
28
+ "top_p": 1,
29
+ "frequency_penalty": 0,
30
+ "presence_penalty": 0,
31
+ }
32
+
33
+ cl.user_session.set("settings", settings)
34
+
35
+
36
+ @cl.on_message # marks a function that should be run each time the chatbot receives a message from a user
37
+ async def main(message: cl.Message):
38
+ settings = cl.user_session.get("settings")
39
+
40
+ # Increment message count
41
+ max_messages = 3
42
+ count = cl.user_session.get("message_count") or 0
43
+ count += 1
44
+ cl.user_session.set("message_count", count)
45
+
46
+ # Stop after 3 messages
47
+ if count > max_messages:
48
+ await cl.Message(
49
+ content="⚠️ This demo is limited to 3 messages per session."
50
+ ).send()
51
+ return
52
+
53
+ client = AsyncOpenAI()
54
+
55
+
56
+ print(message.content)
57
+
58
+ prompt = Prompt(
59
+ provider=ChatOpenAI.id,
60
+ messages=[
61
+ PromptMessage(
62
+ role="system",
63
+ template=system_template,
64
+ formatted=system_template,
65
+ ),
66
+ PromptMessage(
67
+ role="user",
68
+ template=user_template,
69
+ formatted=user_template.format(input=message.content),
70
+ ),
71
+ ],
72
+ inputs={"input": message.content},
73
+ settings=settings,
74
+ )
75
+
76
+ print([m.to_openai() for m in prompt.messages])
77
+
78
+ msg = cl.Message(content="")
79
+
80
+ # Call OpenAI
81
+ async for stream_resp in await client.chat.completions.create(
82
+ messages=[m.to_openai() for m in prompt.messages], stream=True, **settings
83
+ ):
84
+ token = stream_resp.choices[0].delta.content
85
+ if not token:
86
+ token = ""
87
+ await msg.stream_token(token)
88
+
89
+ # Update the prompt object with the completion
90
+ prompt.completion = msg.content
91
+ msg.prompt = prompt
92
+
93
+ # Send and close the message stream
94
+ await msg.send()
chainlit.md ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # πŸ‘‹ Welcome to Beyond ChatGPT – Beginner LLM App
2
+
3
+ This lightweight assistant was built using [Chainlit](https://www.chainlit.io/) and OpenAI, as part of the #AI_Makerspace tutorial series.
4
+
5
+ πŸ’¬ You can type in any question or prompt to get a thoughtful reply.
6
+
7
+ ⚠️ For demo purposes, responses are limited to **3 messages per session**.
8
+
9
+ ---
10
+
11
+ πŸ”§ Want to learn how this was built?
12
+ Check out the source code and deployment steps in the project [README](https://huggingface.co/spaces/FlamingNeuron/llm-app/tree/main).
13
+
pyproject.toml ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [project]
2
+ name = "beyond-chatgpt"
3
+ version = "0.1.0"
4
+ description = "Add your description here"
5
+ readme = "README.md"
6
+ requires-python = ">=3.13"
7
+ dependencies = [
8
+ "chainlit==0.7.700",
9
+ "cohere==4.37",
10
+ "openai==1.3.5",
11
+ "pydantic==2.10.1",
12
+ "python-dotenv==1.0.0",
13
+ "tiktoken==0.5.1",
14
+ ]
uv.lock ADDED
The diff for this file is too large to render. See raw diff