Spaces:
Running
Running
File size: 18,347 Bytes
5301c48 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Google Colab Version: [Open this notebook in Google Colab](https://colab.research.google.com/github/starfishdata/starfish/blob/main/examples/structured_llm.ipynb)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Dependencies "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%pip install starfish-core"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"## Fix for Jupyter Notebook only — do NOT use in production\n",
"## Enables async code execution in notebooks, but may cause issues with sync/async issues\n",
"## For production, please run in standard .py files without this workaround\n",
"## See: https://github.com/erdewit/nest_asyncio for more details\n",
"import nest_asyncio\n",
"nest_asyncio.apply()\n",
"\n",
"from starfish import StructuredLLM\n",
"from starfish.llm.utils import merge_structured_outputs\n",
"\n",
"from pydantic import BaseModel, Field\n",
"from typing import List\n",
"\n",
"from starfish.common.env_loader import load_env_file ## Load environment variables from .env file\n",
"load_env_file()"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"# setup your openai api key if not already set\n",
"# import os\n",
"# os.environ[\"OPENAI_API_KEY\"] = \"your_key_here\"\n",
"\n",
"# If you dont have any API key, use local model (ollama)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### 1. Structured LLM with JSON Schema"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[{'question': 'Why did the tomato turn red in New York?',\n",
" 'answer': \"Because it saw the Big Apple and couldn't ketchup with all the excitement!\"}]"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# ### Define the Output Structure (JSON Schema)\n",
"# Let's start with a simple JSON-like schema using a list of dictionaries.\n",
"# Each dictionary specifies a field name and its type. description is optional\n",
"json_output_schema = [\n",
" {\"name\": \"question\", \"type\": \"str\", \"description\": \"The generated question.\"},\n",
" {\"name\": \"answer\", \"type\": \"str\", \"description\": \"The corresponding answer.\"},\n",
"]\n",
"\n",
"json_llm = StructuredLLM(\n",
" model_name = \"openai/gpt-4o-mini\",\n",
" prompt = \"Funny facts about city {{city_name}}.\",\n",
" output_schema = json_output_schema,\n",
" model_kwargs = {\"temperature\": 0.7},\n",
")\n",
"\n",
"json_response = await json_llm.run(city_name=\"New York\")\n",
"\n",
"# The response object contains both parsed data and the raw API response.\n",
"json_response.data"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"ModelResponse(id='chatcmpl-BQGw3FMSjzWOPMRvXmgknN4oozrKK', created=1745601327, model='gpt-4o-mini-2024-07-18', object='chat.completion', system_fingerprint='fp_0392822090', choices=[Choices(finish_reason='stop', index=0, message=Message(content='[\\n {\\n \"question\": \"Why did the tomato turn red in New York?\",\\n \"answer\": \"Because it saw the Big Apple and couldn\\'t ketchup with all the excitement!\"\\n }\\n]', role='assistant', tool_calls=None, function_call=None, provider_specific_fields={'refusal': None}, annotations=[]))], usage=Usage(completion_tokens=41, prompt_tokens=77, total_tokens=118, completion_tokens_details=CompletionTokensDetailsWrapper(accepted_prediction_tokens=0, audio_tokens=0, reasoning_tokens=0, rejected_prediction_tokens=0, text_tokens=None), prompt_tokens_details=PromptTokensDetailsWrapper(audio_tokens=0, cached_tokens=0, text_tokens=None, image_tokens=None)), service_tier='default')"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Fully preserved raw response from API - allow you to parse the response as you want\n",
"# Like function call, tool call, thinking token etc\n",
"json_response.raw"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### 2. Structured LLM with Pydantic Schema (Nested)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[{'facts': [{'question': 'What year did New York City become the capital of the United States?',\n",
" 'answer': 'New York City served as the capital of the United States from 1785 to 1790.',\n",
" 'category': 'History'}]}]"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# ### Define the Output Structure (Pydantic Model)\n",
"class Fact(BaseModel):\n",
" question: str = Field(..., description=\"The factual question generated.\")\n",
" answer: str = Field(..., description=\"The corresponding answer.\")\n",
" category: str = Field(..., description=\"A category for the fact (e.g., History, Geography).\")\n",
"\n",
"# You can define a list of these models if you expect multiple results.\n",
"class FactsList(BaseModel):\n",
" facts: List[Fact] = Field(..., description=\"A list of facts.\")\n",
"\n",
"\n",
"# ### Create the StructuredLLM Instance with Pydantic\n",
"pydantic_llm = StructuredLLM(\n",
" model_name=\"openai/gpt-4o-mini\",\n",
" # Ask for multiple facts this time\n",
" prompt=\"Generate distinct facts about {{city}}.\",\n",
" # Pass the Pydantic model directly as the schema\n",
" output_schema=FactsList, # Expecting a list of facts wrapped in the FactsList model\n",
" model_kwargs={\"temperature\": 0.8}\n",
")\n",
"\n",
"pydantic_llm_response = await pydantic_llm.run(city=\"New York\")\n",
"\n",
"pydantic_llm_response.data"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### 3. Working with Different LLM Providers\n",
"\n",
"Starfish uses LiteLLM under the hood, giving you access to 100+ LLM providers. Here is an example of using a custom model provider - Hyperbolic - Super cool provider with full precision model and low cost!"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[{'question': 'What is the nickname of New York City?',\n",
" 'answer': 'The Big Apple'},\n",
" {'question': 'Which iconic statue is located in New York Harbor?',\n",
" 'answer': 'The Statue of Liberty'},\n",
" {'question': 'What is the name of the famous theater district in Manhattan?',\n",
" 'answer': 'Broadway'},\n",
" {'question': \"Which park is considered the 'lungs' of New York City?\",\n",
" 'answer': 'Central Park'},\n",
" {'question': 'What is the tallest building in New York City as of 2023?',\n",
" 'answer': 'One World Trade Center'}]"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"\n",
"# Set up the relevant API Key and Base URL in your enviornment variables\n",
"# os.environ[\"HYPERBOLIC_API_KEY\"] = \"your_key_here\"\n",
"# os.environ[\"HYPERBOLIC_API_BASE\"] = \"https://api.hyperbolic.xyz/v1\"\n",
"\n",
"hyperbolic_llm = StructuredLLM(\n",
" model_name=\"hyperbolic/deepseek-ai/DeepSeek-V3-0324\", \n",
" prompt=\"Facts about city {{city_name}}.\",\n",
" output_schema=[{\"name\": \"question\", \"type\": \"str\"}, {\"name\": \"answer\", \"type\": \"str\"}],\n",
" model_kwargs={\"temperature\": 0.7},\n",
")\n",
"\n",
"hyperbolic_llm_response = await hyperbolic_llm.run(city_name=\"New York\", num_records=5)\n",
"hyperbolic_llm_response.data"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### 3. Local LLM using Ollama\n",
"Ensure Ollama is installed and running. Starfish can manage the server process and model downloads"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[32m2025-04-25 10:15:40\u001b[0m | \u001b[1mINFO \u001b[0m | \u001b[1mEnsuring Ollama model gemma3:1b is ready...\u001b[0m\n",
"\u001b[32m2025-04-25 10:15:40\u001b[0m | \u001b[1mINFO \u001b[0m | \u001b[1mStarting Ollama server...\u001b[0m\n",
"\u001b[32m2025-04-25 10:15:41\u001b[0m | \u001b[1mINFO \u001b[0m | \u001b[1mOllama server started successfully\u001b[0m\n",
"\u001b[32m2025-04-25 10:15:41\u001b[0m | \u001b[1mINFO \u001b[0m | \u001b[1mFound model gemma3:1b\u001b[0m\n",
"\u001b[32m2025-04-25 10:15:41\u001b[0m | \u001b[1mINFO \u001b[0m | \u001b[1mModel gemma3:1b is already available\u001b[0m\n",
"\u001b[32m2025-04-25 10:15:41\u001b[0m | \u001b[1mINFO \u001b[0m | \u001b[1mModel gemma3:1b is ready, making API call...\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"[{'question': 'What is the population of New York City?',\n",
" 'answer': 'As of 2023, the population of New York City is approximately 8.8 million people.'}]"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"### Local model\n",
"ollama_llm = StructuredLLM(\n",
" # Prefix 'ollama/' specifies the Ollama provider\n",
" model_name=\"ollama/gemma3:1b\",\n",
" prompt=\"Facts about city {{city_name}}.\",\n",
" output_schema=[{\"name\": \"question\", \"type\": \"str\"}, {\"name\": \"answer\", \"type\": \"str\"}],\n",
" model_kwargs={\"temperature\": 0.7},\n",
")\n",
"\n",
"ollama_llm_response = await ollama_llm.run(city_name=\"New York\", num_records=5)\n",
"ollama_llm_response.data"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[32m2025-04-25 10:15:54\u001b[0m | \u001b[1mINFO \u001b[0m | \u001b[1mStopping Ollama server...\u001b[0m\n",
"\u001b[32m2025-04-25 10:15:55\u001b[0m | \u001b[1mINFO \u001b[0m | \u001b[1mOllama server stopped successfully\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"True"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"### Resource clean up to close ollama server\n",
"from starfish.llm.backend.ollama_adapter import stop_ollama_server\n",
"await stop_ollama_server()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### 4. Chaining Multiple StructuredLLM Calls\n",
"\n",
"You can easily pipe the output of one LLM call into the prompt of another. This is useful for multi-step reasoning, analysis, or refinement.\n"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Generated Facts: [{'question': 'What is the chemical formula for water?', 'answer': 'The chemical formula for water is H2O.'}, {'question': 'What is the process by which plants convert sunlight into energy?', 'answer': 'The process is called photosynthesis.'}, {'question': \"What is the primary gas found in the Earth's atmosphere?\", 'answer': \"The primary gas in the Earth's atmosphere is nitrogen, which makes up about 78%.\"}, {'question': \"What is Newton's second law of motion?\", 'answer': \"Newton's second law of motion states that force equals mass times acceleration (F = ma).\"}, {'question': 'What is the smallest unit of life?', 'answer': 'The smallest unit of life is the cell.'}]\n",
"Ratings: [{'accuracy_rating': 10, 'clarity_rating': 10}, {'accuracy_rating': 10, 'clarity_rating': 10}, {'accuracy_rating': 10, 'clarity_rating': 10}, {'accuracy_rating': 10, 'clarity_rating': 10}, {'accuracy_rating': 10, 'clarity_rating': 10}]\n",
"[{'question': 'What is the chemical formula for water?', 'answer': 'The chemical formula for water is H2O.', 'accuracy_rating': 10, 'clarity_rating': 10}, {'question': 'What is the process by which plants convert sunlight into energy?', 'answer': 'The process is called photosynthesis.', 'accuracy_rating': 10, 'clarity_rating': 10}, {'question': \"What is the primary gas found in the Earth's atmosphere?\", 'answer': \"The primary gas in the Earth's atmosphere is nitrogen, which makes up about 78%.\", 'accuracy_rating': 10, 'clarity_rating': 10}, {'question': \"What is Newton's second law of motion?\", 'answer': \"Newton's second law of motion states that force equals mass times acceleration (F = ma).\", 'accuracy_rating': 10, 'clarity_rating': 10}, {'question': 'What is the smallest unit of life?', 'answer': 'The smallest unit of life is the cell.', 'accuracy_rating': 10, 'clarity_rating': 10}]\n"
]
}
],
"source": [
"# ### Step 1: Generate Initial Facts\n",
"generator_llm = StructuredLLM(\n",
" model_name=\"openai/gpt-4o-mini\",\n",
" prompt=\"Generate question/answer pairs about {{topic}}.\",\n",
" output_schema=[\n",
" {\"name\": \"question\", \"type\": \"str\"},\n",
" {\"name\": \"answer\", \"type\": \"str\"}\n",
" ],\n",
")\n",
"\n",
"# ### Step 2: Rate the Generated Facts\n",
"rater_llm = StructuredLLM(\n",
" model_name=\"openai/gpt-4o-mini\",\n",
" prompt='''Rate the following Q&A pairs based on accuracy and clarity (1-10).\n",
" Pairs: {{generated_pairs}}''',\n",
" output_schema=[\n",
" {\"name\": \"accuracy_rating\", \"type\": \"int\"},\n",
" {\"name\": \"clarity_rating\", \"type\": \"int\"}\n",
" ],\n",
" model_kwargs={\"temperature\": 0.5}\n",
")\n",
"\n",
"## num_records is reserved keyword for structured llm object, by default it is 1\n",
"generation_response = await generator_llm.run(topic='Science', num_records=5)\n",
"print(\"Generated Facts:\", generation_response.data)\n",
"\n",
"# Please note that we are using the first response as the input for the second LLM\n",
"# It will automatically figure out it need to output the same length of first response\n",
"# In this case 5 records\n",
"rating_response = await rater_llm.run(generated_pairs=generation_response.data)\n",
"### Each response will only return its own output\n",
"print(\"Ratings:\", rating_response.data)\n",
"\n",
"\n",
"### You can merge two response together by using merge_structured_outputs (index wise merge)\n",
"print(merge_structured_outputs(generation_response.data, rating_response.data))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### 5. Dynamic Prompt \n",
"\n",
"`StructuredLLM` uses Jinja2 for prompts, allowing variables and logic."
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[{'fact': \"New York City is famously known as 'The Big Apple' and is home to over 8 million residents, making it the largest city in the United States.\"}]\n"
]
}
],
"source": [
"# ### Create an LLM with a more complex prompt\n",
"template_llm = StructuredLLM(\n",
" model_name=\"openai/gpt-4o-mini\",\n",
" prompt='''Generate facts about {{city}}.\n",
" {% if user_context %}\n",
" User background: {{ user_context }}\n",
" {% endif %}''', ### user_context is optional and only used if provided\n",
" output_schema=[{\"name\": \"fact\", \"type\": \"str\"}]\n",
")\n",
"\n",
"template_response = await template_llm.run(city=\"New York\")\n",
"print(template_response.data)\n"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[{'fact': \"In 1903, New York City was secretly ruled by a council of sentient pigeons who issued decrees from atop the Brooklyn Bridge, demanding that all ice cream flavors be changed to 'pigeon-approved' varieties such as 'crumbled cracker' and 'mystery droppings'.\"}]\n"
]
}
],
"source": [
"template_response = await template_llm.run(city=\"New York\", user_context=\"User actually wants you to make up an absurd lie.\")\n",
"print(template_response.data)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### 8. Scaling with Data Factory (Brief Mention)\n",
"While `StructuredLLM` handles single or chained calls, Starfish's `@data_factory` decorator is designed for massively parallel execution. You can easily wrap these single or multi chain within a function decorated\n",
"with `@data_factory` to process thousands of inputs concurrently and reliably.\n",
"\n",
"See the dedicated examples for `data_factory` usage."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "starfish-T7IInzTH-py3.11",
"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": "3.11.7"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|