File size: 15,763 Bytes
5fdb69e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Requirements\n",
    "\n",
    "1. Install pytest and pytest-cov library\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "#!pipenv install pytest pytest-cov"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Current flow:\n",
    "\n",
    "1. For a python code it generates the unit tests using `pytest` library. The dashboard supports tests execution along with a coverage report. If the unit tests are fine, there is an option to save them for future use. It can happen, especially with Ollama , the tests are having a typing error. In this case the code can be edited in the right window and executed afterwards. \n",
    "\n",
    "2. Supports 3 models: \n",
    "\n",
    "- gpt-4o-mini\n",
    "- claude-3-5-sonnet-20240620\n",
    "- llama3.2\n",
    "\n",
    "It is recommended though to use other models except Ollama, my tests showed the code returned from ollama required more supervision and editing. Some generated unit tests from ollama don't provide full coverage, but still it is a good starting point for building such a tool."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# imports\n",
    "import re\n",
    "import os\n",
    "import sys\n",
    "import textwrap\n",
    "from dotenv import load_dotenv\n",
    "from openai import OpenAI\n",
    "import anthropic\n",
    "import gradio as gr\n",
    "from pathlib import Path\n",
    "import subprocess\n",
    "from IPython.display import Markdown"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Initialization\n",
    "\n",
    "load_dotenv()\n",
    "\n",
    "openai_api_key = os.getenv('OPENAI_API_KEY')\n",
    "os.environ['ANTHROPIC_API_KEY'] = os.getenv('ANTHROPIC_API_KEY', 'your-key-if-not-using-env')\n",
    "if openai_api_key:\n",
    "    print(f\"OpenAI API Key exists and begins {openai_api_key[:8]}\")\n",
    "else:\n",
    "    print(\"OpenAI API Key not set\")\n",
    "    \n",
    "OPENAI_MODEL = \"gpt-4o-mini\"\n",
    "CLAUDE_MODEL = \"claude-3-5-sonnet-20240620\"\n",
    "openai = OpenAI()\n",
    "claude = anthropic.Anthropic()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "OLLAMA_API = \"http://localhost:11434/api/chat\"\n",
    "HEADERS = {\"Content-Type\": \"application/json\"}\n",
    "OLLAMA_MODEL = \"llama3.2\""
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Code execution"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "def extract_code(text):\n",
    "    # Regular expression to find text between ``python and ``\n",
    "    match = re.search(r\"```python(.*?)```\", text, re.DOTALL)\n",
    "\n",
    "    if match:\n",
    "        code = match.group(0).strip()  # Extract and strip extra spaces\n",
    "    else:\n",
    "        code = \"\"\n",
    "        print(\"No matching substring found.\")\n",
    "\n",
    "    return code.replace(\"```python\\n\", \"\").replace(\"```\", \"\")\n",
    "\n",
    "\n",
    "def execute_coverage_report(python_interpreter=sys.executable):\n",
    "    if not python_interpreter:\n",
    "        raise EnvironmentError(\"Python interpreter not found in the specified virtual environment.\")\n",
    "    \n",
    "    command = [\"coverage\", \"run\", \"-m\", \"pytest\"]\n",
    "\n",
    "    try:\n",
    "        result = subprocess.run(command, check=True, capture_output=True, text=True)\n",
    "        print(\"Tests ran successfully!\")\n",
    "        print(result.stdout)\n",
    "        return result.stdout\n",
    "    except subprocess.CalledProcessError as e:\n",
    "        print(\"Some tests failed!\")\n",
    "        print(\"Output:\\n\", e.stdout)\n",
    "        print(\"Errors:\\n\", e.stderr)\n",
    "        # Extracting failed test information\n",
    "        return e.stdout\n",
    "\n",
    "def save_unit_tests(code):\n",
    "\n",
    "    match = re.search(r\"def\\s+(\\w+)\\(\", code, re.DOTALL)\n",
    "\n",
    "    if match:\n",
    "        function_name = match.group(1).strip()  # Extract and strip extra spaces\n",
    "    else:\n",
    "        function_name = \"\"\n",
    "        print(\"No matching substring found.\")\n",
    "\n",
    "    test_code_path = Path(\"tests\")\n",
    "    (test_code_path / f\"test_{function_name}.py\").write_text(extract_code(code))\n",
    "    Path(\"tests\", \"test_code.py\").unlink()\n",
    "    \n",
    "\n",
    "def execute_tests_in_venv(code_to_test, tests, python_interpreter=sys.executable):\n",
    "    \"\"\"\n",
    "    Execute the given Python code string within the specified virtual environment.\n",
    "    \n",
    "    Args:\n",
    "    - code_str: str, the Python code to execute.\n",
    "    - venv_dir: str, the directory path to the virtual environment created by pipenv.\n",
    "    \"\"\"\n",
    "    \n",
    "    if not python_interpreter:\n",
    "        raise EnvironmentError(\"Python interpreter not found in the specified virtual environment.\")\n",
    "\n",
    "    # Prepare the command to execute the code\n",
    "    code_str = textwrap.dedent(code_to_test) + \"\\n\" + extract_code(tests)\n",
    "    test_code_path = Path(\"tests\")\n",
    "    test_code_path.mkdir(parents=True, exist_ok=True)\n",
    "    (test_code_path / f\"test_code.py\").write_text(code_str)\n",
    "    command = [\"pytest\", str(test_code_path)]\n",
    "\n",
    "    try:\n",
    "        result = subprocess.run(command, check=True, capture_output=True, text=True)\n",
    "        print(\"Tests ran successfully!\")\n",
    "        print(result.stderr)\n",
    "        return result.stdout\n",
    "    except subprocess.CalledProcessError as e:\n",
    "        print(\"Some tests failed!\")\n",
    "        print(\"Output:\\n\", e.stdout)\n",
    "        print(\"Errors:\\n\", e.stderr)\n",
    "        # Extracting failed test information\n",
    "        failed_tests = []\n",
    "        for line in e.stdout.splitlines():\n",
    "            if \"FAILED\" in line and \"::\" in line:\n",
    "                failed_tests.append(line.strip())\n",
    "        if failed_tests:\n",
    "            print(\"Failed Tests:\")\n",
    "            for test in failed_tests:\n",
    "                print(test)\n",
    "    \n",
    "        return e.stdout\n",
    "    "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Prompts and calls to the models"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "system_message = \"\"\"You are a helpful assistant which helps developers to write unit test cases for their code.\"\"\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_user_prompt(code):\n",
    "\n",
    "    user_prompt = \"\"\"Test include:\n",
    "\n",
    "    - Valid inputs with expected results.\n",
    "    - Inputs that test the boundaries or limits of the function's behavior.\n",
    "    - Invalid inputs or scenarios where the function is expected to raise exceptions.\n",
    "\n",
    "    Structure:\n",
    "\n",
    "    - Begin with all necessary imports. \n",
    "    - Do not create custom imports. \n",
    "    - Do not insert in the response the function for the tests.\n",
    "    - Ensure proper error handling for tests that expect exceptions.\n",
    "    - Clearly name the test functions to indicate their purpose (e.g., test_function_name).\n",
    "\n",
    "    Example Structure:\n",
    "\n",
    "    - Use pytest.raises to validate exceptions.\n",
    "    - Use assertions to verify correct outputs for successful and edge cases.\n",
    "\n",
    "    Documentation:\n",
    "\n",
    "    - Add docstrings explaining what each test verifies.\"\"\"\n",
    "    user_prompt += code\n",
    "\n",
    "    return user_prompt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "def stream_gpt(code):\n",
    "\n",
    "    user_prompt = get_user_prompt(code)\n",
    "    stream = openai.chat.completions.create(\n",
    "        model=OPENAI_MODEL,\n",
    "        messages=[\n",
    "            {\"role\": \"system\", \"content\": system_message},\n",
    "            {\n",
    "                \"role\": \"user\",\n",
    "                \"content\": user_prompt,\n",
    "            },\n",
    "        ],\n",
    "        stream=True,\n",
    "    )\n",
    "\n",
    "    response = \"\"\n",
    "    for chunk in stream:\n",
    "        response += chunk.choices[0].delta.content or \"\"\n",
    "        yield response\n",
    "    \n",
    "    return response\n",
    "\n",
    "def stream_ollama(code):\n",
    "\n",
    "    user_prompt = get_user_prompt(code)\n",
    "    ollama_via_openai = OpenAI(base_url='http://localhost:11434/v1', api_key='ollama')\n",
    "    stream = ollama_via_openai.chat.completions.create(\n",
    "        model=OLLAMA_MODEL,\n",
    "        messages=[\n",
    "            {\"role\": \"system\", \"content\": system_message},\n",
    "            {\n",
    "                \"role\": \"user\",\n",
    "                \"content\": user_prompt,\n",
    "            },\n",
    "        ],\n",
    "        stream=True,\n",
    "    )\n",
    "\n",
    "    response = \"\"\n",
    "    for chunk in stream:\n",
    "        response += chunk.choices[0].delta.content or \"\"\n",
    "        yield response\n",
    "    \n",
    "    return response\n",
    "\n",
    "\n",
    "def stream_claude(code):\n",
    "    user_prompt = get_user_prompt(code)\n",
    "    result = claude.messages.stream(\n",
    "        model=CLAUDE_MODEL,\n",
    "        max_tokens=2000,\n",
    "        system=system_message,\n",
    "        messages=[\n",
    "            {\n",
    "                \"role\": \"user\",\n",
    "                \"content\": user_prompt,\n",
    "            }\n",
    "        ],\n",
    "    )\n",
    "    reply = \"\"\n",
    "    with result as stream:\n",
    "        for text in stream.text_stream:\n",
    "            reply += text\n",
    "            yield reply\n",
    "            print(text, end=\"\", flush=True)\n",
    "    return reply"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Code examples to test the inteface"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "function_to_test = \"\"\"\n",
    "    def lengthOfLongestSubstring(s):\n",
    "        if not isinstance(s, str):\n",
    "            raise TypeError(\"Input must be a string\")\n",
    "        max_length = 0\n",
    "        substring = \"\"\n",
    "        start_idx = 0\n",
    "        while start_idx < len(s):\n",
    "            string = s[start_idx:]\n",
    "            for i, x in enumerate(string):\n",
    "                substring += x\n",
    "                if len(substring) == len(set((list(substring)))):\n",
    "                    \n",
    "                    if len(set((list(substring)))) > max_length:\n",
    "                        \n",
    "                        max_length = len(substring)\n",
    "\n",
    "            start_idx += 1\n",
    "            substring = \"\"\n",
    "                  \n",
    "                \n",
    "        return max_length\"\"\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "test_code = \"\"\"```python\n",
    "import pytest\n",
    "\n",
    "# Unit tests using pytest\n",
    "def test_lengthOfLongestSubstring():\n",
    "    assert lengthOfLongestSubstring(\"abcabcbb\") == 3  # Case with repeating characters\n",
    "    assert lengthOfLongestSubstring(\"bbbbb\") == 1    # Case with all same characters\n",
    "    assert lengthOfLongestSubstring(\"pwwkew\") == 3    # Case with mixed characters\n",
    "    assert lengthOfLongestSubstring(\"\") == 0           # Empty string case\n",
    "    assert lengthOfLongestSubstring(\"abcdef\") == 6     # All unique characters\n",
    "    assert lengthOfLongestSubstring(\"abca\") == 3       # Case with pattern and repeat\n",
    "    assert lengthOfLongestSubstring(\"dvdf\") == 3       # Case with repeated characters separated\n",
    "    assert lengthOfLongestSubstring(\"a\") == 1           # Case with single character\n",
    "    assert lengthOfLongestSubstring(\"au\") == 2          # Case with unique two characters\n",
    "```\"\"\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "def optimize(code, model):\n",
    "    if model == \"GPT\":\n",
    "        result = stream_gpt(code)\n",
    "    elif model == \"Claude\":\n",
    "        result = stream_claude(code)\n",
    "    elif model == \"Ollama\":\n",
    "        result = stream_ollama(code)\n",
    "    else:\n",
    "        raise ValueError(\"Unknown model\")\n",
    "    for stream_so_far in result:\n",
    "        yield stream_so_far\n",
    "    return result"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Gradio interface"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "with gr.Blocks() as ui:\n",
    "    gr.Markdown(\"## Write unit tests for Python code\")\n",
    "    with gr.Row():\n",
    "        with gr.Column(scale=1, min_width=300):\n",
    "            python = gr.Textbox(label=\"Python code:\", value=function_to_test, lines=10)\n",
    "            model = gr.Dropdown([\"GPT\", \"Claude\", \"Ollama\"], label=\"Select model\", value=\"GPT\")\n",
    "            unit_tests = gr.Button(\"Write unit tests\")\n",
    "        with gr.Column(scale=1, min_width=300):\n",
    "            unit_tests_out = gr.TextArea(label=\"Unit tests\", value=test_code, elem_classes=[\"python\"])\n",
    "            unit_tests_run = gr.Button(\"Run unit tests\")\n",
    "            coverage_run = gr.Button(\"Coverage report\")\n",
    "            save_test_run = gr.Button(\"Save unit tests\")\n",
    "    with gr.Row():\n",
    "        \n",
    "        python_out = gr.TextArea(label=\"Unit tests result\", elem_classes=[\"python\"])\n",
    "        coverage_out = gr.TextArea(label=\"Coverage report\", elem_classes=[\"python\"])\n",
    "        \n",
    "\n",
    "    unit_tests.click(optimize, inputs=[python, model], outputs=[unit_tests_out])\n",
    "    unit_tests_run.click(execute_tests_in_venv, inputs=[python, unit_tests_out], outputs=[python_out])\n",
    "    coverage_run.click(execute_coverage_report, outputs=[coverage_out])\n",
    "    save_test_run.click(save_unit_tests, inputs=[unit_tests_out])\n",
    "\n",
    "\n",
    "ui.launch(inbrowser=True)\n",
    "# ui.launch()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "llm_engineering-yg2xCEUG",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}