first commit

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+chroma/**/*.bin filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+.venv

README.md

@@ -1,13 +1,14 @@
 ---
-title: PythonQuestionMaker
-emoji: 📈
-colorFrom: yellow
-colorTo: blue
+title: Example Gradio App
+emoji: 🏢
+colorFrom: pink
+colorTo: purple
 sdk: gradio
-sdk_version: 5.9.1
+sdk_version: 4.44.0
 app_file: app.py
 pinned: false
 license: mit
+short_description: Testing the application
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

TODO.md

@@ -0,0 +1,7 @@
+- Tag based listing
+    - Display every tags
+    - Search for that particular tag
+
+- Add documentation for each file
+
+- Deployment in HuggingFace Spaces

app.py

@@ -0,0 +1,109 @@
+import gradio as gr
+import os
+from langchain_chroma.vectorstores import Chroma
+from langchain_huggingface.embeddings import (
+    HuggingFaceEmbeddings,
+    HuggingFaceEndpointEmbeddings,
+)
+import json
+from convert_to_json import data_to_json
+
+from template import make_template_outputs, make_template_testcases
+
+if os.environ.get("HUGGINGFACEHUB_API_TOKEN"):
+    embedding = HuggingFaceEndpointEmbeddings(
+        repo_id="sentence-transformers/all-MiniLM-L6-v2",
+        huggingfacehub_api_token=os.environ["HUGGINGFACEHUB_API_TOKEN"],
+    )
+else:
+    embedding = HuggingFaceEmbeddings(
+        model_name="sentence-transformers/all-MiniLM-L6-v2"
+    )
+
+
+
+count = 0
+
+
+def increment_count():
+    global count
+    count += 1
+    return count
+
+
+def print_n_value(n_value):
+    global no_tests
+    no_tests = n_value
+    return n_value  # Return the value if needed for further processing
+
+
+def submit_second_page(topic):
+    db_store = Chroma(collection_name="python-questions", persist_directory="./chroma", embedding_function=embedding)
+    questions = db_store.similarity_search(topic)
+    questions_json = json.loads(data_to_json(questions))
+    return questions_json, gr.update(choices=[d["question"] for d in questions_json])
+
+
+def create_first_page(data_state):
+    # solution_visible = gr.State(False)
+    with gr.Column(visible=True) as page1:
+        gr.Markdown("# Programming in Python")
+        with gr.Row():
+            with gr.Column(scale=1):
+                topic = gr.Textbox(label="Select Topic")
+                submit2 = gr.Button("Submit", elem_id="submit2")
+
+                with gr.Tab("Question"):
+                    question_select = gr.Dropdown(
+                        label="Select Question", choices=[], interactive=True
+                    )
+                    question_display = gr.Textbox(label="Question", interactive=False)
+
+                with gr.Tab("Test Cases"):
+                    testcases_state = gr.Markdown(label="Test Cases")
+
+                with gr.Tab("Output"):
+                    outputs_md = gr.Markdown(label="Output")  # JSON output component
+
+                with gr.Tab("Solution 🔒"):
+                    solution = gr.Code("Solution Locked")
+
+            with gr.Column(scale=1):
+                code_input = gr.Code(
+                    label="Write your code here",
+                    language="python",
+                    lines=10,
+                    interactive=True,
+                )
+                run_button = gr.Button("Run")
+
+        # Connect buttons to functions
+        submit2.click(
+            fn=submit_second_page, inputs=[topic], outputs=[data_state, question_select]
+        )
+
+        question_select.change(
+            fn=make_template_testcases,
+            inputs=[question_select, data_state],
+            outputs=[solution, question_display, testcases_state, code_input],
+        )
+
+        run_button.click(
+            fn=lambda code, question, data: (
+                make_template_outputs(code, question, data)
+            ),
+            inputs=[code_input, question_select, data_state],
+            outputs=[outputs_md],
+        )
+
+    return page1, question_select
+
+
+# Initialize the Gradio app
+with gr.Blocks(css=".small-button { padding: 5px 10px; font-size: 12px; }") as demo:
+    data_state = gr.State([])
+
+    # First page is now the new topic and question selection interface
+    page1_content, question_select = create_first_page(data_state)
+
+demo.launch(share=True)

chroma/f172bc37-bb88-40cb-89e4-c69b01eea80d/data_level0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3c9fd302f000d7790aa403c2d0d8fec363fe46f30b07d53020b6e33b22435a9
+size 1676000

chroma/f172bc37-bb88-40cb-89e4-c69b01eea80d/header.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e87a1dc8bcae6f2c4bea6d5dd5005454d4dace8637dae29bff3c037ea771411e
+size 100

chroma/f172bc37-bb88-40cb-89e4-c69b01eea80d/length.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc19b1997119425765295aeab72d76faa6927d4f83985d328c26f20468d6cc76
+size 4000

convert_to_json.py

@@ -0,0 +1,25 @@
+import json
+
+"""
+"""
+
+def data_to_json(questions):
+    questions_json = []
+
+    for doc in questions:
+        question_obj = {
+            "question": doc.page_content,
+            "question_template": doc.metadata.get("question_template"),
+            "function_name": doc.metadata.get("function_name"),
+            "data_formats": doc.metadata.get("data_formats", ""),
+            "solution": doc.metadata.get("solution", ""),
+            "tags": doc.metadata.get("tags", ""),
+            "testcases": json.loads(doc.metadata.get("testcases", "[]")),
+            "input_type": doc.metadata.get("input_type", ""),
+        }
+        questions_json.append(question_obj)
+
+    # Convert the list to a JSON string
+    json_output = json.dumps(questions_json, indent=2)
+
+    return json_output

requirements.txt

@@ -0,0 +1,177 @@
+aiofiles==23.2.1
+aiohappyeyeballs==2.4.0
+aiohttp==3.10.6
+aiosignal==1.3.1
+annotated-types==0.7.0
+anyio==4.6.0
+asgiref==3.8.1
+asttokens==2.4.1
+attrs==24.2.0
+backoff==2.2.1
+bcrypt==4.2.0
+black==24.8.0
+build==1.2.2
+cachetools==5.5.0
+certifi==2024.8.30
+charset-normalizer==3.3.2
+chroma-hnswlib==0.7.6
+chromadb==0.5.9
+click==8.1.7
+coloredlogs==15.0.1
+contourpy==1.3.0
+cycler==0.12.1
+dataclasses-json==0.6.7
+decorator==5.1.1
+Deprecated==1.2.14
+distro==1.9.0
+duckdb==1.1.1
+durationpy==0.7
+executing==2.1.0
+fastapi==0.115.0
+ffmpy==0.4.0
+filelock==3.16.1
+flatbuffers==24.3.25
+fonttools==4.54.1
+frozenlist==1.4.1
+fsspec==2024.9.0
+google-auth==2.35.0
+googleapis-common-protos==1.65.0
+gradio==4.44.0
+gradio_client==1.3.0
+greenlet==3.1.1
+groq==0.11.0
+grpcio==1.66.1
+h11==0.14.0
+httpcore==1.0.5
+httptools==0.6.1
+httpx==0.27.2
+huggingface-hub==0.25.1
+humanfriendly==10.0
+idna==3.10
+importlib_metadata==8.4.0
+importlib_resources==6.4.5
+ipython==8.27.0
+jedi==0.19.1
+Jinja2==3.1.4
+joblib==1.4.2
+jsonpatch==1.33
+jsonpointer==3.0.0
+kiwisolver==1.4.7
+kubernetes==31.0.0
+langchain==0.3.1
+langchain-chroma==0.1.4
+langchain-community==0.3.1
+langchain-core==0.3.6
+langchain-groq==0.2.0
+langchain-huggingface==0.1.0
+langchain-text-splitters==0.3.0
+langsmith==0.1.128
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+marshmallow==3.22.0
+matplotlib==3.9.2
+matplotlib-inline==0.1.7
+mdurl==0.1.2
+mmh3==5.0.1
+monotonic==1.6
+mpmath==1.3.0
+multidict==6.1.0
+mypy-extensions==1.0.0
+networkx==3.3
+numpy==1.26.4
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-nccl-cu12==2.20.5
+nvidia-nvjitlink-cu12==12.6.68
+nvidia-nvtx-cu12==12.1.105
+oauthlib==3.2.2
+onnxruntime==1.19.2
+opentelemetry-api==1.27.0
+opentelemetry-exporter-otlp-proto-common==1.27.0
+opentelemetry-exporter-otlp-proto-grpc==1.27.0
+opentelemetry-instrumentation==0.48b0
+opentelemetry-instrumentation-asgi==0.48b0
+opentelemetry-instrumentation-fastapi==0.48b0
+opentelemetry-proto==1.27.0
+opentelemetry-sdk==1.27.0
+opentelemetry-semantic-conventions==0.48b0
+opentelemetry-util-http==0.48b0
+orjson==3.10.7
+overrides==7.7.0
+packaging==24.1
+pandas==2.2.3
+parso==0.8.4
+pathspec==0.12.1
+pexpect==4.9.0
+pillow==10.4.0
+platformdirs==4.3.6
+posthog==3.6.6
+prompt_toolkit==3.0.47
+protobuf==4.25.5
+ptyprocess==0.7.0
+pure_eval==0.2.3
+pyasn1==0.6.1
+pyasn1_modules==0.4.1
+pydantic==2.9.2
+pydantic-settings==2.5.2
+pydantic_core==2.23.4
+pydub==0.25.1
+Pygments==2.18.0
+pyparsing==3.1.4
+PyPika==0.48.9
+pyproject_hooks==1.1.0
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-multipart==0.0.10
+pytz==2024.2
+PyYAML==6.0.2
+regex==2024.9.11
+requests==2.32.3
+requests-oauthlib==2.0.0
+rich==13.8.1
+rsa==4.9
+ruff==0.6.8
+safetensors==0.4.5
+scikit-learn==1.5.2
+scipy==1.14.1
+semantic-version==2.10.0
+sentence-transformers==3.1.1
+setuptools==75.1.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.1
+SQLAlchemy==2.0.35
+stack-data==0.6.3
+starlette==0.38.6
+sympy==1.13.3
+tenacity==8.5.0
+threadpoolctl==3.5.0
+tokenize-rt==6.0.0
+tokenizers==0.20.0
+tomlkit==0.12.0
+torch==2.4.1
+tqdm==4.66.5
+traitlets==5.14.3
+transformers==4.45.0
+triton==3.0.0
+typer==0.12.5
+typing-inspect==0.9.0
+typing_extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3
+uvicorn==0.30.6
+uvloop==0.20.0
+watchfiles==0.24.0
+wcwidth==0.2.13
+websocket-client==1.8.0
+websockets==12.0
+wrapt==1.16.0
+yarl==1.12.1
+zipp==3.20.2

run.py

@@ -0,0 +1,59 @@
+import gradio as gr
+import os
+import json
+import ast
+import requests
+from difflib import Differ
+from jinja2 import Template, Environment
+
+
+def update_question(selected_question, data):
+
+    if data is None or not data:
+        return "", "", "", "", "", ""
+    selected_data = next(d for d in data if d["question"] == selected_question)
+    function_template = selected_data["question_template"].replace("\\n", "\n")
+    # print(selected_data)
+    return (
+        selected_data["solution"],
+        selected_data["question"],
+        selected_data["testcases"],
+        function_template,
+    )
+
+
+def run_code(code_snippet, test_cases, input_type="stdin"):
+
+    actual_output_messages = []
+    expected_output_messages = []
+    if input_type == "code":
+        code_snippet += "\nimport sys; exec(sys.stdin.read())"
+
+    # print(code_snippet)
+    for test_case in test_cases:
+
+        expected_output = test_case["output"]
+        payload = {
+            "language": "python",
+            "version": "3.10.0",
+            "files": [{"name": "script.py", "content": code_snippet}],
+            "stdin": test_case["input"],
+        }
+
+        response = requests.post("https://emkc.org/api/v2/piston/execute", json=payload)
+        execution_result = response.json()
+
+        actual_output = (
+            execution_result["run"]["output"].strip()
+            if "run" in execution_result and "output" in execution_result["run"]
+            else ""
+        )
+        actual_output_messages.append(actual_output)
+
+        expected_output_messages.append(expected_output)
+
+    output_json = {
+        "actual_output": actual_output_messages,
+        "expected_output": expected_output_messages,
+    }
+    return output_json

run.sh

@@ -0,0 +1,6 @@
+#!/bin/bash
+
+arg=$1
+arg=${arg:-app.py}
+
+PYTHONPATH="$HOME/gradio-frontend-ai-prog-gen:$PYTHONPATH" gradio "$arg"

template.py

@@ -0,0 +1,75 @@
+import gradio as gr
+import os
+import json
+import ast
+import requests
+from difflib import Differ
+from jinja2 import Template, Environment
+
+
+# output_json = {"actual_output": actual_output_messages, "expected_output":expected_output_messages }
+# input,
+def make_template_testcases(selected_question, data):
+    from run import update_question
+
+    solution, question_display, testcases, code_input = update_question(
+        selected_question, data
+    )
+    testcases_template = Template(
+        """
+    {% for testcase in  testcases %}
+    ### Input {{loop.index}}
+    ```
+    {{testcase.input}}
+    ```
+    ### Expected Output {{loop.index}}
+    ```
+    {{testcase.output}}
+    ```  
+
+                                                                    
+    {% endfor %}
+    """
+    )
+    return (
+        solution,
+        question_display,
+        testcases_template.render(testcases=testcases),
+        code_input,
+    )
+
+
+def make_template_outputs(code_snippet, selected_question, test_data):
+    from run import run_code
+
+    selected_data = next(
+        (item for item in test_data if item["question"] == selected_question), None
+    )
+    test_cases = selected_data["testcases"]
+    input_type = selected_data["input_type"]
+
+    output_json = run_code(code_snippet, test_cases, input_type)
+
+    def zip_filter(a, b):
+        return zip(a, b)
+
+    env = Environment()
+    env.filters["zip"] = zip_filter
+
+    output_template = env.from_string(
+        """
+    {% set list1 = output_json['actual_output'] %}
+    {% set list2 = output_json['expected_output'] %}
+    {% for item1, item2 in list1 | zip(list2) %}
+        ### Actual Output {{loop.index}}                    
+        {% if item1 == item2 %}
+            Passed ✅
+        {% else %}
+            Expected: {{ item2 }}, but got: {{ item1 }} ❌
+        {% endif %}                
+    {% endfor %}
+
+    """
+    )
+
+    return output_template.render(output_json=output_json)