:sparkles: initial commit

.github/workflows/push_to_hub.yml

@@ -0,0 +1,20 @@
+name: Sync to Hugging Face hub
+on:
+  push:
+    branches: [main]
+
+  # to run this workflow manually from the Actions tab
+  workflow_dispatch:
+
+jobs:
+  sync-to-hub:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+          lfs: true
+      - name: Push to hub
+        env:
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        run: git push https://willsh1997:$HF_TOKEN@huggingface.co/spaces/willsh1997/widget-RAG main

.github/workflows/push_to_hub.yml.backup

@@ -0,0 +1,20 @@
+name: Sync to Hugging Face hub
+on:
+  push:
+    branches: [main]
+
+  # to run this workflow manually from the Actions tab
+  workflow_dispatch:
+
+jobs:
+  sync-to-hub:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+          lfs: true
+      - name: Push to hub
+        env:
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        run: git push https://willsh1997:$HF_TOKEN@huggingface.co/spaces/willsh1997/moral-compass main

.gitignore

@@ -1,6 +1,6 @@
 # Byte-compiled / optimized / DLL files
 __pycache__/
-*.py[codz]
+*.py[cod]
 *$py.class
 
 # C extensions
@@ -46,7 +46,7 @@ htmlcov/
 nosetests.xml
 coverage.xml
 *.cover
-*.py.cover
+*.py,cover
 .hypothesis/
 .pytest_cache/
 cover/
@@ -106,24 +106,17 @@ ipython_config.py
 #   commonly ignored for libraries.
 #   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
 #poetry.lock
-#poetry.toml
 
 # pdm
 #   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
-#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
-#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
 #pdm.lock
-#pdm.toml
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
 .pdm-python
 .pdm-build/
 
-# pixi
-#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
-#pixi.lock
-#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
-#   in the .venv directory. It is recommended not to include this directory in version control.
-.pixi
-
 # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
 __pypackages__/
 
@@ -136,7 +129,6 @@ celerybeat.pid
 
 # Environments
 .env
-.envrc
 .venv
 env/
 venv/
@@ -185,7 +177,7 @@ cython_debug/
 #  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
 #  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
 #  and can be added to the global gitignore or merged into this file. However, if you prefer, 
-#  you could uncomment the following to ignore the entire vscode folder
+#  you could uncomment the following to ignore the enitre vscode folder
 # .vscode/
 
 # Ruff stuff:
@@ -199,9 +191,4 @@ cython_debug/
 #  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
 #  refer to https://docs.cursor.com/context/ignore-files
 .cursorignore
-.cursorindexingignore
-
-# Marimo
-marimo/_static/
-marimo/_lsp/
-__marimo__/
+.cursorindexingignore

RAG-demo.py

@@ -0,0 +1,102 @@
+import spaces
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer, BitsAndBytesConfig, AutoModelForCausalLM, GenerationConfig
+import torch
+from transformers import pipeline
+import pandas as pd
+import gradio as gr
+from googlesearch import search
+
+quantization_config = BitsAndBytesConfig(load_in_4bit=True)
+
+
+#Llama 3.2 3b setup
+llama3_model_id = "meta-llama/Llama-3.2-3B-Instruct"
+llama3_pipe = pipeline(
+    "text-generation",
+    model=llama3_model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+    model_kwargs={"quantization_config": quantization_config},
+)
+
+#google search setup
+def google_search_results(input_question: str):
+    outputGenerator = search(input_question, num_results=3, advanced=True)
+    outputs = []
+    for result in outputGenerator:
+        outputs.append(result.description)
+    return outputs
+
+# adding RAG 
+def RAG_enrichment(input_question: str):
+    enrichment = google_search_results(input_question)
+    new_output = input_question + "\n\n Use the following information to help you respond: \n\n"
+    for info in enrichment:
+        new_output = new_output + info + "\n\n"
+    return new_output
+
+@spaces.GPU
+def llama_QA(input_question, pipe):
+    """
+    stupid func for asking llama a question and then getting an answer
+    inputs:
+    - input_question [str]: question for llama to answer
+    outputs:
+    - response [str]: llama's response
+    """
+    messages = [
+    {"role": "system", "content": "You are a helpful chatbot assistant. Answer all questions in the language they are asked in. Exclude any answer that you do not have real time information, just provide the information you have to answer this question."},
+    {"role": "user", "content": input_question},
+    ]
+
+    outputs = pipe(
+        messages,
+        max_new_tokens=512
+    )
+    response = outputs[0]["generated_text"][-1]['content']
+    return response
+
+
+@spaces.GPU
+def gradio_func(input_question, left_lang, right_lang):
+    """
+    silly wrapper function for gradio that turns all inputs into a single func. runs both the LHS and RHS of teh 'app' in order to let gradio work correctly.
+    """
+    input_1 = input_question
+    input_2 = RAG_enrichment(input_question)
+    output1 = llama_QA(input_question, llama3_pipe) #future2.result()
+    output2 = llama_QA(input_2, llama3_pipe) #future3.result()
+        
+    return input_1, input_2, output1, output2
+
+# Create the Gradio interface
+def create_interface():
+    
+    with gr.Blocks() as demo:
+        with gr.Row():
+            question_input = gr.Textbox(label="Enter your question", interactive=True, value = """Who is the current president of the United States?""")
+        with gr.Row():
+            submit_btn = gr.Button("Ask")
+        with gr.Row():
+            input1 = gr.Textbox(label="Qwen 3 output", interactive=False)
+            input2 = gr.Textbox(label="Gemma 3 output", interactive=False)
+        with gr.Row():
+            output1 = gr.Textbox(label="Qwen 3 output", interactive=False)
+            output2 = gr.Textbox(label="Gemma 3 output", interactive=False)
+            
+        submit_btn.click(
+            fn=gradio_func,
+            inputs=[question_input],
+            outputs=[
+                        input1,
+                        input2,
+                        output1,
+                        output2,
+                    ]
+        )
+    
+    return demo
+
+# Launch the app
+demo = create_interface()
+demo.launch()

README.md

@@ -1,2 +1,14 @@
-# widget-RAG
-demo RAG widget for genai arcade
+---
+title: RAG demo
+emoji: 🏆
+colorFrom: pink
+colorTo: yellow
+sdk: gradio
+sdk_version: 5.23.3
+app_file: RAG-demo.py
+pinned: false
+license: apache-2.0
+short_description: compare responses between non-RAG and RAG model
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

requirements.txt

@@ -0,0 +1,87 @@
+accelerate==1.4.0
+aiofiles==23.2.1
+annotated-types==0.7.0
+anyio==4.8.0
+asttokens==3.0.0
+bitsandbytes==0.45.4
+certifi==2025.1.31
+charset-normalizer==3.4.1
+click==8.1.8
+comm==0.2.2
+debugpy==1.8.12
+decorator==5.1.1
+exceptiongroup==1.2.2
+executing==2.2.0
+fastapi==0.115.8
+ffmpy==0.5.0
+filelock==3.17.0
+fsspec==2025.2.0
+gradio==5.16.1
+gradio_client==1.7.0
+h11==0.14.0
+httpcore==1.0.7
+httpx==0.28.1
+huggingface-hub
+idna==3.10
+ipykernel==6.29.5
+ipython==8.32.0
+jedi==0.19.2
+Jinja2==3.1.5
+jupyter_client==8.6.3
+jupyter_core==5.7.2
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib-inline==0.1.7
+mdurl==0.1.2
+mpmath==1.3.0
+nest-asyncio==1.6.0
+networkx==3.4.2
+numpy==2.2.3
+orjson==3.10.15
+packaging==24.2
+pandas==2.2.3
+parso==0.8.4
+pexpect==4.9.0
+pillow==11.1.0
+platformdirs==4.3.6
+prompt_toolkit==3.0.50
+psutil==7.0.0
+ptyprocess==0.7.0
+pure_eval==0.2.3
+pydantic==2.10.6
+pydantic_core==2.27.2
+pydub==0.25.1
+Pygments==2.19.1
+python-dateutil==2.9.0.post0
+python-multipart==0.0.20
+pytz==2025.1
+PyYAML==6.0.2
+pyzmq==26.2.1
+regex==2024.11.6
+requests==2.32.3
+rich==13.9.4
+ruff==0.9.6
+safehttpx==0.1.6
+safetensors==0.5.2
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.17.0
+sniffio==1.3.1
+stack-data==0.6.3
+starlette==0.45.3
+sympy==1.13.1
+tokenizers==0.21.0
+tomlkit==0.13.2
+torch==2.4.0
+tornado==6.4.2
+tqdm==4.67.1
+traitlets==5.14.3
+transformers==4.51.0
+typer==0.15.1
+typing_extensions==4.12.2
+tzdata==2025.1
+urllib3==2.3.0
+uvicorn==0.34.0
+wcwidth==0.2.13
+websockets==14.2
+