organizing files into src folder etc.

pyproject.toml

@@ -11,6 +11,11 @@ dependencies = [
     "ollama>=0.5.3",
     "pycccedict>=1.2.0",
     "pypinyin>=0.55.0",
+<<<<<<< HEAD
+=======
+    "sentence-transformers>=2.2.2",
+    "numpy>=1.26.0",
+>>>>>>> 660f6fb (organizing files into src folder etc.)
 ]
 
 [dependency-groups]

requirements.txt

@@ -1,5 +1,9 @@
 # This file was autogenerated by uv via the following command:
+<<<<<<< HEAD
 #    uv pip compile pyproject.toml -o requirements.txt
+=======
+#    uv export --no-hashes --format requirements-txt
+>>>>>>> 660f6fb (organizing files into src folder etc.)
 aiofiles==24.1.0
     # via gradio
 aiohappyeyeballs==2.6.1
@@ -16,12 +20,27 @@ anyio==4.10.0
     #   gradio
     #   httpx
     #   starlette
+<<<<<<< HEAD
 attrs==25.3.0
     # via aiohttp
 brotli==1.1.0
     # via gradio
 cerebras-cloud-sdk==1.50.1
     # via chinese-idioms (pyproject.toml)
+=======
+    #   watchfiles
+astroid==3.3.11
+    # via pylint
+attrs==25.3.0
+    # via aiohttp
+audioop-lts==0.2.2 ; python_full_version >= '3.13'
+    # via gradio
+black==25.1.0
+brotli==1.1.0
+    # via gradio
+cerebras-cloud-sdk==1.50.1
+    # via chinese-idioms
+>>>>>>> 660f6fb (organizing files into src folder etc.)
 certifi==2025.8.3
     # via
     #   httpcore
@@ -31,17 +50,38 @@ charset-normalizer==3.4.3
     # via requests
 click==8.2.1
     # via
+<<<<<<< HEAD
     #   typer
     #   uvicorn
 datasets==4.1.0
     # via chinese-idioms (pyproject.toml)
+=======
+    #   black
+    #   typer
+    #   uvicorn
+colorama==0.4.6 ; sys_platform == 'win32'
+    # via
+    #   click
+    #   pylint
+    #   pytest
+    #   tqdm
+datasets==4.1.0
+    # via chinese-idioms
+>>>>>>> 660f6fb (organizing files into src folder etc.)
 dill==0.4.0
     # via
     #   datasets
     #   multiprocess
+<<<<<<< HEAD
 distro==1.9.0
     # via cerebras-cloud-sdk
 fastapi==0.116.2
+=======
+    #   pylint
+distro==1.9.0
+    # via cerebras-cloud-sdk
+fastapi==0.116.1
+>>>>>>> 660f6fb (organizing files into src folder etc.)
     # via gradio
 ffmpy==0.6.1
     # via gradio
@@ -49,18 +89,34 @@ filelock==3.19.1
     # via
     #   datasets
     #   huggingface-hub
+<<<<<<< HEAD
+=======
+    #   torch
+    #   transformers
+>>>>>>> 660f6fb (organizing files into src folder etc.)
 frozenlist==1.7.0
     # via
     #   aiohttp
     #   aiosignal
+<<<<<<< HEAD
 fsspec==2025.9.0
+=======
+fsspec==2025.7.0
+>>>>>>> 660f6fb (organizing files into src folder etc.)
     # via
     #   datasets
     #   gradio-client
     #   huggingface-hub
+<<<<<<< HEAD
 gradio==5.46.0
     # via chinese-idioms (pyproject.toml)
 gradio-client==1.13.0
+=======
+    #   torch
+gradio==5.44.0
+    # via chinese-idioms
+gradio-client==1.12.1
+>>>>>>> 660f6fb (organizing files into src folder etc.)
     # via gradio
 groovy==0.1.2
     # via gradio
@@ -68,7 +124,11 @@ h11==0.16.0
     # via
     #   httpcore
     #   uvicorn
+<<<<<<< HEAD
 hf-xet==1.1.10
+=======
+hf-xet==1.1.8 ; platform_machine == 'aarch64' or platform_machine == 'amd64' or platform_machine == 'arm64' or platform_machine == 'x86_64'
+>>>>>>> 660f6fb (organizing files into src folder etc.)
     # via huggingface-hub
 httpcore==1.0.9
     # via httpx
@@ -79,33 +139,67 @@ httpx==0.28.1
     #   gradio-client
     #   ollama
     #   safehttpx
+<<<<<<< HEAD
 huggingface-hub==0.35.0
+=======
+huggingface-hub==0.34.4
+>>>>>>> 660f6fb (organizing files into src folder etc.)
     # via
     #   datasets
     #   gradio
     #   gradio-client
+<<<<<<< HEAD
+=======
+    #   sentence-transformers
+    #   tokenizers
+    #   transformers
+>>>>>>> 660f6fb (organizing files into src folder etc.)
 idna==3.10
     # via
     #   anyio
     #   httpx
     #   requests
     #   yarl
+<<<<<<< HEAD
 jinja2==3.1.6
     # via gradio
 markdown-it-py==4.0.0
+=======
+iniconfig==2.1.0
+    # via pytest
+isort==6.0.1
+    # via pylint
+jinja2==3.1.6
+    # via
+    #   gradio
+    #   torch
+joblib==1.5.2
+    # via scikit-learn
+markdown-it-py==4.0.0 ; sys_platform != 'emscripten'
+>>>>>>> 660f6fb (organizing files into src folder etc.)
     # via rich
 markupsafe==3.0.2
     # via
     #   gradio
     #   jinja2
+<<<<<<< HEAD
 mdurl==0.1.2
     # via markdown-it-py
+=======
+mccabe==0.7.0
+    # via pylint
+mdurl==0.1.2 ; sys_platform != 'emscripten'
+    # via markdown-it-py
+mpmath==1.3.0
+    # via sympy
+>>>>>>> 660f6fb (organizing files into src folder etc.)
 multidict==6.6.4
     # via
     #   aiohttp
     #   yarl
 multiprocess==0.70.16
     # via datasets
+<<<<<<< HEAD
 numpy >= 2.0, < 3.0
     # via
     #   datasets
@@ -113,20 +207,98 @@ numpy >= 2.0, < 3.0
     #   pandas
 ollama==0.5.4
     # via chinese-idioms (pyproject.toml)
+=======
+mypy-extensions==1.1.0
+    # via black
+networkx==3.5
+    # via torch
+numpy==2.3.2
+    # via
+    #   chinese-idioms
+    #   datasets
+    #   gradio
+    #   pandas
+    #   scikit-learn
+    #   scipy
+    #   transformers
+nvidia-cublas-cu12==12.8.4.1 ; platform_machine == 'x86_64' and sys_platform == 'linux'
+    # via
+    #   nvidia-cudnn-cu12
+    #   nvidia-cusolver-cu12
+    #   torch
+nvidia-cuda-cupti-cu12==12.8.90 ; platform_machine == 'x86_64' and sys_platform == 'linux'
+    # via torch
+nvidia-cuda-nvrtc-cu12==12.8.93 ; platform_machine == 'x86_64' and sys_platform == 'linux'
+    # via torch
+nvidia-cuda-runtime-cu12==12.8.90 ; platform_machine == 'x86_64' and sys_platform == 'linux'
+    # via torch
+nvidia-cudnn-cu12==9.10.2.21 ; platform_machine == 'x86_64' and sys_platform == 'linux'
+    # via torch
+nvidia-cufft-cu12==11.3.3.83 ; platform_machine == 'x86_64' and sys_platform == 'linux'
+    # via torch
+nvidia-cufile-cu12==1.13.1.3 ; platform_machine == 'x86_64' and sys_platform == 'linux'
+    # via torch
+nvidia-curand-cu12==10.3.9.90 ; platform_machine == 'x86_64' and sys_platform == 'linux'
+    # via torch
+nvidia-cusolver-cu12==11.7.3.90 ; platform_machine == 'x86_64' and sys_platform == 'linux'
+    # via torch
+nvidia-cusparse-cu12==12.5.8.93 ; platform_machine == 'x86_64' and sys_platform == 'linux'
+    # via
+    #   nvidia-cusolver-cu12
+    #   torch
+nvidia-cusparselt-cu12==0.7.1 ; platform_machine == 'x86_64' and sys_platform == 'linux'
+    # via torch
+nvidia-nccl-cu12==2.27.3 ; platform_machine == 'x86_64' and sys_platform == 'linux'
+    # via torch
+nvidia-nvjitlink-cu12==12.8.93 ; platform_machine == 'x86_64' and sys_platform == 'linux'
+    # via
+    #   nvidia-cufft-cu12
+    #   nvidia-cusolver-cu12
+    #   nvidia-cusparse-cu12
+    #   torch
+nvidia-nvtx-cu12==12.8.90 ; platform_machine == 'x86_64' and sys_platform == 'linux'
+    # via torch
+ollama==0.5.3
+    # via chinese-idioms
+>>>>>>> 660f6fb (organizing files into src folder etc.)
 orjson==3.11.3
     # via gradio
 packaging==25.0
     # via
+<<<<<<< HEAD
+=======
+    #   black
+>>>>>>> 660f6fb (organizing files into src folder etc.)
     #   datasets
     #   gradio
     #   gradio-client
     #   huggingface-hub
+<<<<<<< HEAD
+=======
+    #   pytest
+    #   transformers
+>>>>>>> 660f6fb (organizing files into src folder etc.)
 pandas==2.3.2
     # via
     #   datasets
     #   gradio
+<<<<<<< HEAD
 pillow==11.3.0
     # via gradio
+=======
+pathspec==0.12.1
+    # via black
+pillow==11.3.0
+    # via
+    #   gradio
+    #   sentence-transformers
+platformdirs==4.4.0
+    # via
+    #   black
+    #   pylint
+pluggy==1.6.0
+    # via pytest
+>>>>>>> 660f6fb (organizing files into src folder etc.)
 propcache==0.3.2
     # via
     #   aiohttp
@@ -134,8 +306,13 @@ propcache==0.3.2
 pyarrow==21.0.0
     # via datasets
 pycccedict==1.2.0
+<<<<<<< HEAD
     # via chinese-idioms (pyproject.toml)
 pydantic==2.11.9
+=======
+    # via chinese-idioms
+pydantic==2.11.7
+>>>>>>> 660f6fb (organizing files into src folder etc.)
     # via
     #   cerebras-cloud-sdk
     #   fastapi
@@ -146,11 +323,24 @@ pydantic-core==2.33.2
 pydub==0.25.1
     # via gradio
 pygments==2.19.2
+<<<<<<< HEAD
     # via rich
 pypinyin==0.55.0
     # via chinese-idioms (pyproject.toml)
 python-dateutil==2.9.0.post0
     # via pandas
+=======
+    # via
+    #   pytest
+    #   rich
+pylint==3.3.8
+pypinyin==0.55.0
+    # via chinese-idioms
+pytest==8.4.2
+python-dateutil==2.9.0.post0
+    # via pandas
+python-dotenv==1.1.1
+>>>>>>> 660f6fb (organizing files into src folder etc.)
 python-multipart==0.0.20
     # via gradio
 pytz==2025.2
@@ -160,10 +350,17 @@ pyyaml==6.0.2
     #   datasets
     #   gradio
     #   huggingface-hub
+<<<<<<< HEAD
+=======
+    #   transformers
+regex==2025.9.18
+    # via transformers
+>>>>>>> 660f6fb (organizing files into src folder etc.)
 requests==2.32.5
     # via
     #   datasets
     #   huggingface-hub
+<<<<<<< HEAD
 rich==14.1.0
     # via typer
 ruff==0.13.0
@@ -173,6 +370,32 @@ safehttpx==0.1.6
 semantic-version==2.10.0
     # via gradio
 shellingham==1.5.4
+=======
+    #   transformers
+rich==14.1.0 ; sys_platform != 'emscripten'
+    # via typer
+ruff==0.12.10 ; sys_platform != 'emscripten'
+    # via gradio
+safehttpx==0.1.6
+    # via gradio
+safetensors==0.6.2
+    # via transformers
+scikit-learn==1.7.2
+    # via sentence-transformers
+scipy==1.16.2
+    # via
+    #   scikit-learn
+    #   sentence-transformers
+semantic-version==2.10.0
+    # via gradio
+sentence-transformers==5.1.1
+    # via chinese-idioms
+setuptools==80.9.0
+    # via
+    #   torch
+    #   triton
+shellingham==1.5.4 ; sys_platform != 'emscripten'
+>>>>>>> 660f6fb (organizing files into src folder etc.)
     # via typer
 six==1.17.0
     # via python-dateutil
@@ -180,17 +403,46 @@ sniffio==1.3.1
     # via
     #   anyio
     #   cerebras-cloud-sdk
+<<<<<<< HEAD
 starlette==0.48.0
     # via
     #   fastapi
     #   gradio
 tomlkit==0.13.3
     # via gradio
+=======
+starlette==0.47.3
+    # via
+    #   fastapi
+    #   gradio
+sympy==1.14.0
+    # via torch
+threadpoolctl==3.6.0
+    # via scikit-learn
+tokenizers==0.22.1
+    # via transformers
+tomlkit==0.13.3
+    # via
+    #   gradio
+    #   pylint
+torch==2.8.0
+    # via sentence-transformers
+>>>>>>> 660f6fb (organizing files into src folder etc.)
 tqdm==4.67.1
     # via
     #   datasets
     #   huggingface-hub
+<<<<<<< HEAD
 typer==0.17.4
+=======
+    #   sentence-transformers
+    #   transformers
+transformers==4.56.2
+    # via sentence-transformers
+triton==3.4.0 ; platform_machine == 'x86_64' and sys_platform == 'linux'
+    # via torch
+typer==0.16.1 ; sys_platform != 'emscripten'
+>>>>>>> 660f6fb (organizing files into src folder etc.)
     # via gradio
 typing-extensions==4.15.0
     # via
@@ -203,7 +455,13 @@ typing-extensions==4.15.0
     #   huggingface-hub
     #   pydantic
     #   pydantic-core
+<<<<<<< HEAD
+    #   starlette
+=======
+    #   sentence-transformers
     #   starlette
+    #   torch
+>>>>>>> 660f6fb (organizing files into src folder etc.)
     #   typer
     #   typing-inspection
 typing-inspection==0.4.1
@@ -211,9 +469,18 @@ typing-inspection==0.4.1
 tzdata==2025.2
     # via pandas
 urllib3==2.5.0
+<<<<<<< HEAD
     # via requests
 uvicorn==0.35.0
     # via gradio
+=======
+    # via
+    #   gradio
+    #   requests
+uvicorn==0.35.0 ; sys_platform != 'emscripten'
+    # via gradio
+watchfiles==1.1.0
+>>>>>>> 660f6fb (organizing files into src folder etc.)
 websockets==15.0.1
     # via gradio-client
 xxhash==3.5.0

src/app.py

@@ -0,0 +1,148 @@
+import json
+import os
+
+import gradio as gr
+from cerebras.cloud.sdk import Cerebras
+from dotenv import load_dotenv
+
+from utils.utils import get_pinyin
+
+# ======================
+# Config
+# ======================
+load_dotenv()
+
+MODEL = "gpt-oss-120b"
+USE_MOCK = False  # ✅ Toggle between mock and real API
+
+# ======================
+# Idiom dataset
+# ======================
+IDIOM_FILE_PATH = "idiom_dataset/chid_idiom_reference.json"
+with open(IDIOM_FILE_PATH, "r", encoding="utf-8") as f:
+    idiom_list = json.load(f)
+VALID_IDIOMS = set(idiom_list)
+
+# ======================
+# Instantiate client (if not mocking)
+# ======================
+CLIENT = None
+if not USE_MOCK:
+    CLIENT = Cerebras(api_key=os.environ.get("CEREBRAS_API_KEY"))
+
+
+# ======================
+# Mock function for UI testing
+# ======================
+def generate_idiom_mock():
+    idiom = "对症下药"
+    explanation = """duì zhèng xià yào<br><br>
+    To prescribe the right medicine; to take the right approach to a problem."""
+    return idiom, explanation
+
+
+# ======================
+# Real API function
+# ======================
+
+
+def generate_idiom(situation: str):
+    prompt = f"""You are a wise assistant. Given a situation, respond with exactly:
+1. A Chinese idiom (includes 成語、俗語、諺語), 
+   written in simplified Chinese characters,
+   that conveys the idea of the given situation.
+2. Its literal English translation
+3. Explain idiom. Keep explanation to 2-3 concise sentences.
+
+Format:
+Idiom
+Literal translation
+Explanation
+
+Situation: {situation}
+Answer:"""
+
+    response = CLIENT.chat.completions.create(
+        model=MODEL,
+        messages=[{"role": "user", "content": prompt}],
+    )
+    print(response)
+
+    generated_text = response.choices[0].message.content.strip()
+    lines = [line.strip() for line in generated_text.split("\n") if line.strip()]
+
+    llm_idiom = lines[0] if lines else generated_text
+
+    if llm_idiom not in VALID_IDIOMS:
+        explanation = "The LLM generated an invalid idiom. Try again!"
+        return llm_idiom, explanation
+
+    pinyin_text = get_pinyin(llm_idiom)
+
+    if len(lines) >= 3:
+        translation = lines[1]
+        meaning = " ".join(lines[2:])
+        explanation = f"{pinyin_text}<br><br>{translation}<br><br>{meaning}"
+    else:
+        explanation = f"{pinyin_text}<br><br>{' '.join(lines[1:])}"
+
+    return llm_idiom, explanation
+
+
+# ======================
+# UI Wrapper
+# ======================
+def update_ui(situation):
+    if USE_MOCK:
+        idiom, explanation = generate_idiom_mock()
+    else:
+        idiom, explanation = generate_idiom(situation)
+
+    return (
+        f"<div class='idiom-output'>{idiom}</div>",
+        f"<div class='explanation-output'>{explanation}</div>",
+    )
+
+
+# ======================
+# Launch app
+# ======================
+def launch_app():
+    with gr.Blocks(css="style.css") as demo:
+        gr.Markdown("# 🎋 Chinese Idiom Finder")
+
+        with gr.Row():
+            with gr.Column():
+                situation = gr.Textbox(
+                    label="Enter a situation",
+                    lines=2,
+                    placeholder="e.g., When facing a big challenge",
+                )
+                generate_btn = gr.Button("✨ Find Idiom")
+
+                # ✅ Example situations
+                gr.Examples(
+                    examples=[
+                        ["When facing a big challenge"],
+                        ["When someone helps you in a time of need"],
+                        ["When you need to stay calm under pressure"],
+                        ["When teamwork is important to succeed"],
+                        ["When rushing leads to mistakes"],
+                    ],
+                    inputs=situation,
+                )
+
+            with gr.Column():
+                idiom_output = gr.HTML(label="Idiom")
+                explanation_output = gr.HTML(label="Explanation")
+
+        # pylint: disable=no-member
+        generate_btn.click(
+            fn=update_ui, inputs=situation, outputs=[idiom_output, explanation_output]
+        )
+
+    demo.launch()
+
+
+if __name__ == "__main__":
+    launch_app()

src/run.py

@@ -0,0 +1,14 @@
+from multiprocessing import freeze_support
+
+from watchfiles import run_process
+
+import app  # Import app module
+
+
+def start_app():
+    app.launch_app()
+
+
+if __name__ == "__main__":
+    freeze_support()
+    run_process(".", target=start_app)

src/style.css

@@ -0,0 +1,48 @@
+/* ========================
+   Dark Mode Default
+   ======================== */
+body, .gradio-container {
+    background-color: #1a1a2e; 
+    color: #f0f0f0;
+    font-family: Arial, sans-serif;
+}
+
+.idiom-output {
+    font-size: 2rem;
+    font-weight: bold;
+    text-align: center;
+    color: #ff6f61; 
+    margin-bottom: 0.5em;
+}
+
+.explanation-output {
+    font-size: 1rem;
+    line-height: 1.5;
+    color: #dcdcdc;
+    text-align: center;
+}
+
+/* Buttons */
+.gradio-container .gr-button {
+    background-color: #3a3a5e;
+    color: #ffffff;
+    border: 1px solid #5c5c8a;
+    font-weight: bold;
+}
+.gradio-container .gr-button:hover {
+    background-color: #505080;
+}
+
+/* Textboxes */
+.gradio-container .gr-textbox textarea {
+    background-color: #2a2a45;
+    color: #ffffff;
+    border: 1px solid #5c5c8a;
+}
+
+/* Examples */
+.gradio-container .gr-examples {
+    background-color: #2a2a45;
+    border: 1px solid #5c5c8a;
+    color: #ffffff;
+}

src/utils/utils.py

@@ -0,0 +1,7 @@
+from pypinyin import Style, pinyin
+
+
+def get_pinyin(text: str):
+    """Convert Chinese characters to pinyin with tones."""
+    py_list = pinyin(text, style=Style.TONE, heteronym=False)
+    return " ".join([syllable[0] for syllable in py_list])