brad/LLM_Engineering_OLD
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

added day4 exercise with inference provider

Browse Source
This commit is contained in:
Dany.Makhoul
2025-02-14 14:40:44 -05:00
parent 289a1b9bd1
commit d57d084d27
1 changed files with 871 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

871
week4/community-contributions/day4_with_inference_provider.ipynb Normal file
View File

@@ -0,0 +1,871 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "4a6ab9a2-28a2-445d-8512-a0dc8d1b54e9",
"metadata": {},
"source": [
"# Code Generator\n",
"\n",
"The requirement: use an Open Source model to generate high performance C++ code from Python code\n",
"\n",
"To replicate this, you'll need to set up a HuggingFace endpoint as I do in the video. It's simple to do, and it's quite satisfying to see the results!\n",
"\n",
"It's also an important part of your learning; this is the first example of deploying an open source model to be behind an API. We'll return to this in Week 8, but this should plant a seed in your mind for what's involved in moving open source models into production.\n",
"\n",
"Added the use of inference providers that was introduced recently by Hugging Face to convert the code.\n",
"Improved the user prompt to include algorithic efficeiny and performance optimization.\n",
"\n",
"Note: C++ commands work on windows environment."
]
},
{
"cell_type": "code",
"execution_count": 44,
"id": "e610bf56-a46e-4aff-8de1-ab49d62b1ad3",
"metadata": {},
"outputs": [],
"source": [
"# imports\n",
"\n",
"import os\n",
"import io\n",
"import sys\n",
"import json\n",
"import requests\n",
"from dotenv import load_dotenv\n",
"from openai import OpenAI\n",
"import google.generativeai\n",
"import anthropic\n",
"from IPython.display import Markdown, display, update_display\n",
"import gradio as gr\n",
"import subprocess"
]
},
{
"cell_type": "code",
"execution_count": 45,
"id": "4f672e1c-87e9-4865-b760-370fa605e614",
"metadata": {},
"outputs": [],
"source": [
"# environment\n",
"\n",
"load_dotenv()\n",
"os.environ['OPENAI_API_KEY'] = os.getenv('OPENAI_API_KEY', 'your-key-if-not-using-env')\n",
"os.environ['ANTHROPIC_API_KEY'] = os.getenv('ANTHROPIC_API_KEY', 'your-key-if-not-using-env')\n",
"os.environ['HF_TOKEN'] = os.getenv('HF_TOKEN', 'your-key-if-not-using-env')"
]
},
{
"cell_type": "code",
"execution_count": 46,
"id": "8aa149ed-9298-4d69-8fe2-8f5de0f667da",
"metadata": {},
"outputs": [],
"source": [
"# initialize\n",
"\n",
"openai = OpenAI()\n",
"claude = anthropic.Anthropic()\n",
"OPENAI_MODEL = \"gpt-4o\"\n",
"CLAUDE_MODEL = \"claude-3-5-sonnet-20240620\""
]
},
{
"cell_type": "code",
"execution_count": 47,
"id": "6896636f-923e-4a2c-9d6c-fac07828a201",
"metadata": {},
"outputs": [],
"source": [
"system_message = \"You are an assistant that reimplements Python code in high performance C++ for an Windows intel i7. \"\n",
"system_message += \"Respond only with C++ code; use comments sparingly and do not provide any explanation other than occasional comments. \"\n",
"system_message += \"The C++ response needs to produce an identical output in the fastest possible time. Keep implementations of random number generators identical so that results match exactly.\""
]
},
{
"cell_type": "code",
"execution_count": 72,
"id": "70583432-e851-40d1-a219-2fb32b830dc8",
"metadata": {},
"outputs": [],
"source": [
"#updated the original prompt to include algorithic efficeiny and performance optimization\n",
"def user_prompt_for(python: str) -> str:\n",
" user_prompt = (\n",
" \"First, analyze the given Python code to understand its core purpose and algorithmic approach. \"\n",
" \"Then, implement a C++ solution that achieves the same output while prioritizing:\\n\"\n",
" \"1. **Algorithmic Efficiency** - Optimize time and space complexity, even if it means using a different approach.\\n\"\n",
" \"2. **Numerical Correctness** - Prevent integer overflows, use appropriate data types (`int64_t`, `uint64_t`, `double`, etc.), \"\n",
" \"and ensure correct handling of edge cases.\\n\"\n",
" \"3. **Performance Optimization** - Utilize C++-specific features (e.g., `std::vector` with preallocation, SIMD optimizations, cache-friendly structures).\\n\\n\"\n",
" \n",
" \"### **Important Notes:**\\n\"\n",
" \"- Use `int64_t` instead of `int` where necessary to prevent overflows.\\n\"\n",
" \"- Ensure random number generation in C++ matches Python's output as closely as possible.\\n\"\n",
" \"- Avoid undefined behavior, such as bit shifts that exceed type width (`1UL << 32` is incorrect for `uint32_t`).\\n\"\n",
" \"- Comment on key optimizations and complexity improvements in the C++ code.\\n\\n\"\n",
" \n",
" \"### **Expected Response:**\\n\"\n",
" \"Respond **only with C++ code**, including all necessary headers and ensuring the output matches the Python version exactly.\\n\\n\"\n",
" \n",
" \"Here's the Python code to analyze and optimize:\\n\\n\"\n",
" + python\n",
" )\n",
" return user_prompt"
]
},
{
"cell_type": "code",
"execution_count": 49,
"id": "c6190659-f54c-4951-bef4-4960f8e51cc4",
"metadata": {},
"outputs": [],
"source": [
"def messages_for(python):\n",
" return [\n",
" {\"role\": \"system\", \"content\": system_message},\n",
" {\"role\": \"user\", \"content\": user_prompt_for(python)}\n",
" ]"
]
},
{
"cell_type": "code",
"execution_count": 50,
"id": "71e1ba8c-5b05-4726-a9f3-8d8c6257350b",
"metadata": {},
"outputs": [],
"source": [
"# write to a file called optimized.cpp\n",
"\n",
"def write_output(cpp):\n",
" code = cpp.replace(\"```cpp\",\"\").replace(\"```\",\"\")\n",
" with open(\"optimized.cpp\", \"w\") as f:\n",
" f.write(code)"
]
},
{
"cell_type": "code",
"execution_count": 51,
"id": "e7d2fea8-74c6-4421-8f1e-0e76d5b201b9",
"metadata": {},
"outputs": [],
"source": [
"def optimize_gpt(python): \n",
" stream = openai.chat.completions.create(model=OPENAI_MODEL, messages=messages_for(python), stream=True)\n",
" reply = \"\"\n",
" for chunk in stream:\n",
" fragment = chunk.choices[0].delta.content or \"\"\n",
" reply += fragment\n",
" print(fragment, end='', flush=True)\n",
" write_output(reply)"
]
},
{
"cell_type": "code",
"execution_count": 52,
"id": "7cd84ad8-d55c-4fe0-9eeb-1895c95c4a9d",
"metadata": {},
"outputs": [],
"source": [
"def optimize_claude(python):\n",
" result = claude.messages.stream(\n",
" model=CLAUDE_MODEL,\n",
" max_tokens=2000,\n",
" system=system_message,\n",
" messages=[{\"role\": \"user\", \"content\": user_prompt_for(python)}],\n",
" )\n",
" reply = \"\"\n",
" with result as stream:\n",
" for text in stream.text_stream:\n",
" reply += text\n",
" print(text, end=\"\", flush=True)\n",
" write_output(reply)"
]
},
{
"cell_type": "code",
"execution_count": 53,
"id": "a1cbb778-fa57-43de-b04b-ed523f396c38",
"metadata": {},
"outputs": [],
"source": [
"pi = \"\"\"\n",
"import time\n",
"\n",
"def calculate(iterations, param1, param2):\n",
" result = 1.0\n",
" for i in range(1, iterations+1):\n",
" j = i * param1 - param2\n",
" result -= (1/j)\n",
" j = i * param1 + param2\n",
" result += (1/j)\n",
" return result\n",
"\n",
"start_time = time.time()\n",
"result = calculate(100_000_000, 4, 1) * 4\n",
"end_time = time.time()\n",
"\n",
"print(f\"Result: {result:.12f}\")\n",
"print(f\"Execution Time: {(end_time - start_time):.6f} seconds\")\n",
"\"\"\""
]
},
{
"cell_type": "code",
"execution_count": 59,
"id": "7fe1cd4b-d2c5-4303-afed-2115a3fef200",
"metadata": {},
"outputs": [],
"source": [
"exec(pi)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "105db6f9-343c-491d-8e44-3a5328b81719",
"metadata": {},
"outputs": [],
"source": [
"optimize_gpt(pi)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "bf26ee95-0c77-491d-9a91-579a1e96a8a3",
"metadata": {},
"outputs": [],
"source": [
"exec(pi)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4194e40c-04ab-4940-9d64-b4ad37c5bb40",
"metadata": {},
"outputs": [],
"source": [
"!g++ -O3 -std=c++17 -march=native -o optimized optimized.cpp\n",
"!optimized.exe"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "983a11fe-e24d-4c65-8269-9802c5ef3ae6",
"metadata": {},
"outputs": [],
"source": [
"optimize_claude(pi)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d5a766f9-3d23-4bb4-a1d4-88ec44b61ddf",
"metadata": {},
"outputs": [],
"source": [
"!g++ -O3 -std=c++17 -march=native -o optimized optimized.cpp\n",
"!optimized.exe"
]
},
{
"cell_type": "code",
"execution_count": 54,
"id": "c3b497b3-f569-420e-b92e-fb0f49957ce0",
"metadata": {},
"outputs": [],
"source": [
"python_hard = \"\"\"# Be careful to support large number sizes\n",
"\n",
"def lcg(seed, a=1664525, c=1013904223, m=2**32):\n",
" value = seed\n",
" while True:\n",
" value = (a * value + c) % m\n",
" yield value\n",
" \n",
"def max_subarray_sum(n, seed, min_val, max_val):\n",
" lcg_gen = lcg(seed)\n",
" random_numbers = [next(lcg_gen) % (max_val - min_val + 1) + min_val for _ in range(n)]\n",
" max_sum = float('-inf')\n",
" for i in range(n):\n",
" current_sum = 0\n",
" for j in range(i, n):\n",
" current_sum += random_numbers[j]\n",
" if current_sum > max_sum:\n",
" max_sum = current_sum\n",
" return max_sum\n",
"\n",
"def total_max_subarray_sum(n, initial_seed, min_val, max_val):\n",
" total_sum = 0\n",
" lcg_gen = lcg(initial_seed)\n",
" for _ in range(20):\n",
" seed = next(lcg_gen)\n",
" total_sum += max_subarray_sum(n, seed, min_val, max_val)\n",
" return total_sum\n",
"\n",
"# Parameters\n",
"n = 10000 # Number of random numbers\n",
"initial_seed = 42 # Initial seed for the LCG\n",
"min_val = -10 # Minimum value of random numbers\n",
"max_val = 10 # Maximum value of random numbers\n",
"\n",
"# Timing the function\n",
"import time\n",
"start_time = time.time()\n",
"result = total_max_subarray_sum(n, initial_seed, min_val, max_val)\n",
"end_time = time.time()\n",
"\n",
"print(\"Total Maximum Subarray Sum (20 runs):\", result)\n",
"print(\"Execution Time: {:.6f} seconds\".format(end_time - start_time))\n",
"\"\"\""
]
},
{
"cell_type": "code",
"execution_count": 23,
"id": "dab5e4bc-276c-4555-bd4c-12c699d5e899",
"metadata": {},
"outputs": [],
"source": [
"exec(python_hard)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e8d24ed5-2c15-4f55-80e7-13a3952b3cb8",
"metadata": {},
"outputs": [],
"source": [
"optimize_gpt(python_hard)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e0b3d073-88a2-40b2-831c-6f0c345c256f",
"metadata": {},
"outputs": [],
"source": [
"!g++ -O3 -std=c++17 -march=native -o optimized optimized.cpp\n",
"!optimized.exe"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e9305446-1d0c-4b51-866a-b8c1e299bf5c",
"metadata": {},
"outputs": [],
"source": [
"optimize_claude(python_hard)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0c181036-8193-4fdd-aef3-fc513b218d43",
"metadata": {},
"outputs": [],
"source": [
"!g++ -O3 -std=c++17 -march=native -o optimized optimized.cpp\n",
"!optimized.exe"
]
},
{
"cell_type": "code",
"execution_count": 55,
"id": "0be9f47d-5213-4700-b0e2-d444c7c738c0",
"metadata": {},
"outputs": [],
"source": [
"def stream_gpt(python): \n",
" stream = openai.chat.completions.create(model=OPENAI_MODEL, messages=messages_for(python), stream=True)\n",
" reply = \"\"\n",
" for chunk in stream:\n",
" fragment = chunk.choices[0].delta.content or \"\"\n",
" reply += fragment\n",
" yield reply.replace('```cpp\\n','').replace('```','')"
]
},
{
"cell_type": "code",
"execution_count": 56,
"id": "8669f56b-8314-4582-a167-78842caea131",
"metadata": {},
"outputs": [],
"source": [
"def stream_claude(python):\n",
" result = claude.messages.stream(\n",
" model=CLAUDE_MODEL,\n",
" max_tokens=2000,\n",
" system=system_message,\n",
" messages=[{\"role\": \"user\", \"content\": user_prompt_for(python)}],\n",
" )\n",
" reply = \"\"\n",
" with result as stream:\n",
" for text in stream.text_stream:\n",
" reply += text\n",
" yield reply.replace('```cpp\\n','').replace('```','')"
]
},
{
"cell_type": "code",
"execution_count": 57,
"id": "2f1ae8f5-16c8-40a0-aa18-63b617df078d",
"metadata": {},
"outputs": [],
"source": [
"def optimize(python, model):\n",
" if model==\"GPT\":\n",
" result = stream_gpt(python)\n",
" elif model==\"Claude\":\n",
" result = stream_claude(python)\n",
" else:\n",
" raise ValueError(\"Unknown model\")\n",
" for stream_so_far in result:\n",
" yield stream_so_far "
]
},
{
"cell_type": "code",
"execution_count": 24,
"id": "f1ddb38e-6b0a-4c37-baa4-ace0b7de887a",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div><iframe src=\"http://127.0.0.1:7862/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": []
},
"execution_count": 24,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"with gr.Blocks() as ui:\n",
" with gr.Row():\n",
" python = gr.Textbox(label=\"Python code:\", lines=10, value=python_hard)\n",
" cpp = gr.Textbox(label=\"C++ code:\", lines=10)\n",
" with gr.Row():\n",
" model = gr.Dropdown([\"GPT\", \"Claude\"], label=\"Select model\", value=\"GPT\")\n",
" convert = gr.Button(\"Convert code\")\n",
"\n",
" convert.click(optimize, inputs=[python, model], outputs=[cpp])\n",
"\n",
"ui.launch(inbrowser=True)"
]
},
{
"cell_type": "code",
"execution_count": 58,
"id": "19bf2bff-a822-4009-a539-f003b1651383",
"metadata": {},
"outputs": [],
"source": [
"def execute_python(code):\n",
" try:\n",
" output = io.StringIO()\n",
" sys.stdout = output\n",
" exec(code)\n",
" finally:\n",
" sys.stdout = sys.__stdout__\n",
" return output.getvalue()"
]
},
{
"cell_type": "code",
"execution_count": 59,
"id": "77f3ab5d-fcfb-4d3f-8728-9cacbf833ea6",
"metadata": {},
"outputs": [],
"source": [
"def execute_cpp(code):\n",
" write_output(code)\n",
" try:\n",
" compile_result = subprocess.run(compiler_cmd[2], check=True, text=True, capture_output=True)\n",
" run_cmd = [\"optimized.exe\"]\n",
" run_result = subprocess.run(run_cmd, check=True, text=True, capture_output=True)\n",
" return run_result.stdout\n",
" except subprocess.CalledProcessError as e:\n",
" return f\"An error occurred:\\n{e.stderr}\""
]
},
{
"cell_type": "code",
"execution_count": 60,
"id": "9a2274f1-d03b-42c0-8dcc-4ce159b18442",
"metadata": {},
"outputs": [],
"source": [
"css = \"\"\"\n",
".python {background-color: #306998;}\n",
".cpp {background-color: #050;}\n",
"\"\"\""
]
},
{
"cell_type": "code",
"execution_count": 28,
"id": "f1303932-160c-424b-97a8-d28c816721b2",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div><iframe src=\"http://127.0.0.1:7863/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": []
},
"execution_count": 28,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"with gr.Blocks(css=css) as ui:\n",
" gr.Markdown(\"## Convert code from Python to C++\")\n",
" with gr.Row():\n",
" python = gr.Textbox(label=\"Python code:\", value=python_hard, lines=10)\n",
" cpp = gr.Textbox(label=\"C++ code:\", lines=10)\n",
" with gr.Row():\n",
" model = gr.Dropdown([\"GPT\", \"Claude\"], label=\"Select model\", value=\"GPT\")\n",
" with gr.Row():\n",
" convert = gr.Button(\"Convert code\")\n",
" with gr.Row():\n",
" python_run = gr.Button(\"Run Python\")\n",
" cpp_run = gr.Button(\"Run C++\")\n",
" with gr.Row():\n",
" python_out = gr.TextArea(label=\"Python result:\", elem_classes=[\"python\"])\n",
" cpp_out = gr.TextArea(label=\"C++ result:\", elem_classes=[\"cpp\"])\n",
"\n",
" convert.click(optimize, inputs=[python, model], outputs=[cpp])\n",
" python_run.click(execute_python, inputs=[python], outputs=[python_out])\n",
" cpp_run.click(execute_cpp, inputs=[cpp], outputs=[cpp_out])\n",
"\n",
"ui.launch(inbrowser=True)"
]
},
{
"cell_type": "code",
"execution_count": 61,
"id": "bb8c5b4e-ec51-4f21-b3f8-6aa94fede86d",
"metadata": {},
"outputs": [],
"source": [
"from huggingface_hub import login, InferenceClient"
]
},
{
"cell_type": "code",
"execution_count": 62,
"id": "13347633-4606-4e38-9927-80c39e65c1f1",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Note: Environment variable`HF_TOKEN` is set and is the current active token independently from the token you've just configured.\n"
]
}
],
"source": [
"hf_token = os.environ['HF_TOKEN']\n",
"login(hf_token)"
]
},
{
"cell_type": "code",
"execution_count": 63,
"id": "ef60a4df-6267-4ebd-8eed-dcb917af0a5e",
"metadata": {},
"outputs": [],
"source": [
"code_qwen = \"Qwen/CodeQwen1.5-7B-Chat\"\n",
"code_gemma = \"google/codegemma-7b-it\"\n",
"messages=messages_for(pi)"
]
},
{
"cell_type": "code",
"execution_count": 64,
"id": "3825d77a-03c6-42b2-89bc-ccbcb1585740",
"metadata": {},
"outputs": [],
"source": [
"client = InferenceClient(\n",
"\tprovider=\"sambanova\",\n",
"\tapi_key=hf_token\n",
")\n",
"stream = client.chat.completions.create(\n",
"\tmodel=\"Qwen/Qwen2.5-Coder-32B-Instruct\", \n",
"\tmessages=messages, \n",
"\tmax_tokens=500,\n",
"\tstream=True\n",
")\n",
"\n",
"for chunk in stream:\n",
" print(chunk.choices[0].delta.content, end=\"\")"
]
},
{
"cell_type": "code",
"execution_count": 65,
"id": "cc0c3e9c-2572-41d1-a476-6eae96b20695",
"metadata": {},
"outputs": [],
"source": [
"# using inference providers\n",
"def stream_code_qwen(python):\n",
" messages = messages_for(python)\n",
" client = InferenceClient(\n",
" \tprovider=\"sambanova\",\n",
" \tapi_key=hf_token\n",
" )\n",
" stream = client.chat.completions.create(\n",
" \tmodel=\"Qwen/Qwen2.5-Coder-32B-Instruct\", \n",
" \tmessages=messages, \n",
" \tmax_tokens=500,\n",
" \tstream=True\n",
" )\n",
" result = \"\"\n",
" for chunk in stream:\n",
" if chunk.choices and chunk.choices[0].delta.content:\n",
" result += chunk.choices[0].delta.content\n",
" yield result"
]
},
{
"cell_type": "code",
"execution_count": 66,
"id": "a82387d1-7651-4923-995b-fe18356fcaa6",
"metadata": {},
"outputs": [],
"source": [
"def optimize(python, model):\n",
" if model==\"GPT\":\n",
" result = stream_gpt(python)\n",
" elif model==\"Claude\":\n",
" result = stream_claude(python)\n",
" elif model==\"CodeQwen\":\n",
" result = stream_code_qwen(python)\n",
" else:\n",
" raise ValueError(\"Unknown model\")\n",
" for stream_so_far in result:\n",
" yield stream_so_far "
]
},
{
"cell_type": "code",
"execution_count": 67,
"id": "4ba311ec-c16a-4fe0-946b-4b940704cf65",
"metadata": {},
"outputs": [],
"source": [
"def select_sample_program(sample_program):\n",
" if sample_program==\"pi\":\n",
" return pi\n",
" elif sample_program==\"python_hard\":\n",
" return python_hard\n",
" else:\n",
" return \"Type your Python program here\""
]
},
{
"cell_type": "code",
"execution_count": 68,
"id": "06148e88-501b-4686-a41d-c3be528d8e6f",
"metadata": {},
"outputs": [],
"source": [
"def execute_cpp(code):\n",
" write_output(code)\n",
" try:\n",
" compile_cmd = [\"g++\", \"-Ofast\", \"-std=c++17\", \"-march=native\", \"-mtune=intel\", \"-o\", \"optimized\", \"optimized.cpp\"]\n",
" compile_result = subprocess.run(compile_cmd, check=True, text=True, capture_output=True)\n",
" run_cmd = [\"optimized.exe\"]\n",
" run_result = subprocess.run(run_cmd, check=True, text=True, capture_output=True)\n",
" return run_result.stdout\n",
" except subprocess.CalledProcessError as e:\n",
" return f\"An error occurred:\\n{e.stderr}\""
]
},
{
"cell_type": "code",
"execution_count": 71,
"id": "f9ca2e6f-60c1-4e5f-b570-63c75b2d189b",
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<div><iframe src=\"http://127.0.0.1:7867/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": []
},
"execution_count": 71,
"metadata": {},
"output_type": "execute_result"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Traceback (most recent call last):\n",
" File \"C:\\Users\\danym\\anaconda3\\envs\\llms\\Lib\\site-packages\\huggingface_hub\\utils\\_http.py\", line 406, in hf_raise_for_status\n",
" response.raise_for_status()\n",
" File \"C:\\Users\\danym\\anaconda3\\envs\\llms\\Lib\\site-packages\\requests\\models.py\", line 1024, in raise_for_status\n",
" raise HTTPError(http_error_msg, response=self)\n",
"requests.exceptions.HTTPError: 402 Client Error: Payment Required for url: https://huggingface.co/api/inference-proxy/sambanova/v1/chat/completions\n",
"\n",
"The above exception was the direct cause of the following exception:\n",
"\n",
"Traceback (most recent call last):\n",
" File \"C:\\Users\\danym\\anaconda3\\envs\\llms\\Lib\\site-packages\\gradio\\queueing.py\", line 625, in process_events\n",
" response = await route_utils.call_process_api(\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"C:\\Users\\danym\\anaconda3\\envs\\llms\\Lib\\site-packages\\gradio\\route_utils.py\", line 322, in call_process_api\n",
" output = await app.get_blocks().process_api(\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"C:\\Users\\danym\\anaconda3\\envs\\llms\\Lib\\site-packages\\gradio\\blocks.py\", line 2088, in process_api\n",
" result = await self.call_function(\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"C:\\Users\\danym\\anaconda3\\envs\\llms\\Lib\\site-packages\\gradio\\blocks.py\", line 1647, in call_function\n",
" prediction = await utils.async_iteration(iterator)\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"C:\\Users\\danym\\anaconda3\\envs\\llms\\Lib\\site-packages\\gradio\\utils.py\", line 728, in async_iteration\n",
" return await anext(iterator)\n",
" ^^^^^^^^^^^^^^^^^^^^^\n",
" File \"C:\\Users\\danym\\anaconda3\\envs\\llms\\Lib\\site-packages\\gradio\\utils.py\", line 722, in __anext__\n",
" return await anyio.to_thread.run_sync(\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"C:\\Users\\danym\\anaconda3\\envs\\llms\\Lib\\site-packages\\anyio\\to_thread.py\", line 56, in run_sync\n",
" return await get_async_backend().run_sync_in_worker_thread(\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"C:\\Users\\danym\\anaconda3\\envs\\llms\\Lib\\site-packages\\anyio\\_backends\\_asyncio.py\", line 2505, in run_sync_in_worker_thread\n",
" return await future\n",
" ^^^^^^^^^^^^\n",
" File \"C:\\Users\\danym\\anaconda3\\envs\\llms\\Lib\\site-packages\\anyio\\_backends\\_asyncio.py\", line 1005, in run\n",
" result = context.run(func, *args)\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"C:\\Users\\danym\\anaconda3\\envs\\llms\\Lib\\site-packages\\gradio\\utils.py\", line 705, in run_sync_iterator_async\n",
" return next(iterator)\n",
" ^^^^^^^^^^^^^^\n",
" File \"C:\\Users\\danym\\anaconda3\\envs\\llms\\Lib\\site-packages\\gradio\\utils.py\", line 866, in gen_wrapper\n",
" response = next(iterator)\n",
" ^^^^^^^^^^^^^^\n",
" File \"C:\\Users\\danym\\AppData\\Local\\Temp\\ipykernel_16896\\2223836700.py\", line 10, in optimize\n",
" for stream_so_far in result:\n",
" File \"C:\\Users\\danym\\AppData\\Local\\Temp\\ipykernel_16896\\2217507934.py\", line 8, in stream_code_qwen\n",
" stream = client.chat.completions.create(\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"C:\\Users\\danym\\anaconda3\\envs\\llms\\Lib\\site-packages\\huggingface_hub\\inference\\_client.py\", line 970, in chat_completion\n",
" data = self._inner_post(request_parameters, stream=stream)\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"C:\\Users\\danym\\anaconda3\\envs\\llms\\Lib\\site-packages\\huggingface_hub\\inference\\_client.py\", line 327, in _inner_post\n",
" hf_raise_for_status(response)\n",
" File \"C:\\Users\\danym\\anaconda3\\envs\\llms\\Lib\\site-packages\\huggingface_hub\\utils\\_http.py\", line 477, in hf_raise_for_status\n",
" raise _format(HfHubHTTPError, str(e), response) from e\n",
"huggingface_hub.errors.HfHubHTTPError: 402 Client Error: Payment Required for url: https://huggingface.co/api/inference-proxy/sambanova/v1/chat/completions (Request ID: Root=1-67af964d-18ce264b79019ea460d62fd1;041b0bf3-9206-4a8a-aa61-f493ff9b1f8a)\n",
"\n",
"You have exceeded your monthly included credits for Inference Endpoints. Subscribe to PRO to get 20x more monthly allowance.\n"
]
}
],
"source": [
"with gr.Blocks(css=css) as ui:\n",
" gr.Markdown(\"## Convert code from Python to C++\")\n",
" with gr.Row():\n",
" python = gr.Textbox(label=\"Python code:\", value=python_hard, lines=10)\n",
" cpp = gr.Textbox(label=\"C++ code:\", lines=10)\n",
" with gr.Row():\n",
" with gr.Column():\n",
" sample_program = gr.Radio([\"pi\", \"python_hard\"], label=\"Sample program\", value=\"python_hard\")\n",
" model = gr.Dropdown([\"GPT\", \"Claude\", \"CodeQwen\"], label=\"Select model\", value=\"GPT\")\n",
" with gr.Row():\n",
" convert = gr.Button(\"Convert code\")\n",
" with gr.Row():\n",
" python_run = gr.Button(\"Run Python\")\n",
" cpp_run = gr.Button(\"Run C++\")\n",
" with gr.Row():\n",
" python_out = gr.TextArea(label=\"Python result:\", elem_classes=[\"python\"])\n",
" cpp_out = gr.TextArea(label=\"C++ result:\", elem_classes=[\"cpp\"])\n",
"\n",
" sample_program.change(select_sample_program, inputs=[sample_program], outputs=[python])\n",
" convert.click(optimize, inputs=[python, model], outputs=[cpp])\n",
" python_run.click(execute_python, inputs=[python], outputs=[python_out])\n",
" cpp_run.click(execute_cpp, inputs=[cpp], outputs=[cpp_out])\n",
"\n",
"ui.launch(inbrowser=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9d0ad093-425b-488e-8c3f-67f729dd9c06",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.11.11"
}
},
"nbformat": 4,
"nbformat_minor": 5
}