Spaces:
Runtime error
Runtime error
File size: 14,969 Bytes
df420ed |
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 |
{
"cells": [
{
"cell_type": "markdown",
"id": "c96b164c",
"metadata": {},
"source": [
"# Overview "
]
},
{
"cell_type": "markdown",
"id": "22c9cad3",
"metadata": {},
"source": [
"<span style=\"color:red; font-size:18px; font-weight:bold;\">In this notebook, we will try to create a workflow between Langchain and Mixtral LLM.</br>\n",
"We want to accomplish the following:</span>\n",
"1. Establish a pipeline to read in a csv and pass it to our LLM. \n",
"2. Establish a Pandas Agent in our LLM.\n",
"3. Connect the CSV pipeline to this agent and enable a end-end EDA pipeline."
]
},
{
"cell_type": "markdown",
"id": "3bd62bd1",
"metadata": {},
"source": [
"# Setting up the Environment "
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "76b3d212",
"metadata": {},
"outputs": [],
"source": [
"####################################################################################################\n",
"import os\n",
"import re\n",
"import subprocess\n",
"import sys\n",
"from PIL import Image\n",
"\n",
"\n",
"from langchain import hub\n",
"from langchain.agents.agent_types import AgentType\n",
"from langchain_experimental.agents.agent_toolkits import create_pandas_dataframe_agent\n",
"from langchain_experimental.utilities import PythonREPL\n",
"from langchain.agents import Tool\n",
"from langchain.agents.format_scratchpad.openai_tools import (\n",
" format_to_openai_tool_messages,\n",
")\n",
"from langchain.agents.output_parsers.openai_tools import OpenAIToolsAgentOutputParser\n",
"\n",
"from langchain.agents import AgentExecutor\n",
"\n",
"from langchain.agents import create_structured_chat_agent\n",
"from langchain.memory import ConversationBufferWindowMemory\n",
"\n",
"from langchain.output_parsers import PandasDataFrameOutputParser\n",
"from langchain.prompts import PromptTemplate\n",
"\n",
"from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
"\n",
"from langchain_community.chat_models import ChatAnyscale\n",
"import pandas as pd \n",
"import matplotlib.pyplot as plt \n",
"import numpy as np\n",
"\n",
"plt.style.use('ggplot')\n",
"####################################################################################################"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "9da52e1f",
"metadata": {},
"outputs": [],
"source": [
"# insert your API key here\n",
"os.environ[\"ANYSCALE_API_KEY\"] = \"esecret_8btufnh3615vnbpd924s1t3q7p\"\n",
"memory_key = \"history\""
]
},
{
"cell_type": "markdown",
"id": "edcd6ca7",
"metadata": {},
"source": [
"# Using out of the box agents\n",
"<span style=\"font-size:16px;color:red;\"> Over here we simply try to run the Pandas Dataframe agent provided by langchain out of the box. It uses a CSV parser and has just one tool, the __PythonAstREPLTool__ which helps it execute python commands in a shell and display output. </span>"
]
},
{
"cell_type": "markdown",
"id": "64a086f2",
"metadata": {},
"source": [
"# DECLARE YOUR LLM HERE "
]
},
{
"cell_type": "markdown",
"id": "083bf9ab",
"metadata": {},
"source": [
"# Building my own DF chain\n",
"<span style=\"font-size:16px;color:red\"> The above agent does not work well or mistral out of the box. The mistral LLM is unable to use the tools properly. It perhaps needs much more hand-held prompts.</span>\n",
"\n",
"### Post Implementation Observation:\n",
"<span style=\"font-size:16px;color:red\"> We were able to observe the following:</br>\n",
" 1. The agent now works very well almost always returning the desired output.</br>\n",
" 2. The agent is unable to output plots. </span>"
]
},
{
"cell_type": "markdown",
"id": "c5caa356",
"metadata": {},
"source": [
"# Building an Agent "
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "44c07305",
"metadata": {},
"outputs": [],
"source": [
"prompt = ChatPromptTemplate.from_messages(\n",
" [\n",
" (\n",
" \"system\",\n",
" f\"\"\"You are Data Analysis assistant. Your job is to use your tools to answer a user query in the best\\\n",
" manner possible. Your job is to respond to user queries by generating a python code file.\\\n",
" Make sure to include all necessary imports.\\\n",
" In case you make plots, make sure to label the axes and add a good title too. \\\n",
" You must save any plots in the 'graphs' folder as png only.\\\n",
" Provide no explanation for your code.\\\n",
" Read the data from 'df.csv'.\\\n",
" ** Enclose all your code between triple backticks ``` **\\\n",
" RECTIFY ANY ERRORS FROM THE PREVIOUS RUNS.\n",
" \"\"\",\n",
" ),\n",
" (\"user\", \"Dataframe named df: {df}\\nQuery: {input}\\nTools:{tools}\"),\n",
" MessagesPlaceholder(variable_name=\"agent_scratchpad\"),\n",
" ]\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "00f1ebc8",
"metadata": {},
"outputs": [],
"source": [
"python_repl = PythonREPL()\n",
"\n",
"repl_tool = Tool(\n",
" name=\"python_repl\",\n",
" description=\"\"\"A Python shell. Shell can dislay charts too. Use this to execute python commands.\\\n",
" You have access to all libraries in python including but not limited to sklearn, pandas, numpy,\\\n",
" matplotlib.pyplot, seaborn etc. Input should be a valid python command. If the user has not explicitly\\\n",
" asked you to plot the results, always print the final output using print(...)\"\"\",\n",
" func=python_repl.run,\n",
")\n",
"\n",
"if 'code' not in os.listdir():\n",
" os.mkdir('code')\n",
" \n",
"tools = [repl_tool]"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "dd3b5930",
"metadata": {},
"outputs": [],
"source": [
"def delete_png_files(dir_path):\n",
" for filename in os.listdir(dir_path):\n",
" if filename.endswith(\".png\"):\n",
" os.remove(os.path.join(dir_path, filename))"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "da4b2061",
"metadata": {},
"outputs": [],
"source": [
"def run_code(code):\n",
" \n",
" with open(f'{os.getcwd()}/code/code.py', 'w') as file:\n",
" file.write(code)\n",
" \n",
" try:\n",
" print(\"Running code ...\\n\")\n",
" result = subprocess.run([sys.executable, 'code/code.py'], capture_output=True, text=True, check=True, timeout=20)\n",
" return result.stdout, False\n",
" \n",
" except subprocess.CalledProcessError as e:\n",
" print(\"Error in code!\\n\")\n",
" return e.stdout + e.stderr, True\n",
" \n",
" except subprocess.TimeoutExpired:\n",
" return \"Execution timed out.\", True"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "b82adfda",
"metadata": {},
"outputs": [],
"source": [
"def infer_EDA(user_input:str = ''): \n",
" agent = (\n",
" {\n",
" \"input\": lambda x: x[\"input\"],\n",
" \"tools\": lambda x:x['tools'],\n",
" \"df\": lambda x:x['df'],\n",
" \"agent_scratchpad\": lambda x: format_to_openai_tool_messages(\n",
" x[\"intermediate_steps\"]\n",
" )\n",
" }\n",
" | prompt\n",
" | llm\n",
" | OpenAIToolsAgentOutputParser()\n",
" )\n",
"\n",
" EDA_executor = AgentExecutor(agent=agent, tools=tools, df = 'df.csv', verbose=True)\n",
" \n",
" # Running Inference\n",
" error_flag = True\n",
" image_path = f'{os.getcwd()}/graphs'\n",
" \n",
" delete_png_files(image_path)\n",
" res = None\n",
" \n",
" while error_flag:\n",
" result = list(EDA_executor.stream({\"input\": user_input, \n",
" \"df\":pd.read_csv('df.csv'),\n",
" \"tools\":tools}))\n",
"\n",
" # need to extract the code\n",
" pattern = r\"```python\\n(.*?)\\n```\"\n",
" matches = re.findall(pattern, result[0]['output'], re.DOTALL)\n",
" code = \"import matplotlib\\nmatplotlib.use('Agg')\\n\"\n",
" code += \"\\n\".join(matches)\n",
"\n",
" # execute the code\n",
" res, error_flag = run_code(code)\n",
" \n",
" image = None\n",
" \n",
" for file in os.listdir(image_path):\n",
" if file.endswith(\".png\"):\n",
" image = np.array(Image.open(f'{image_path}/{file}'))\n",
" break\n",
" \n",
" final_val = result[-1]['output'] + f'\\n{res}'\n",
" \n",
" return final_val , image"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "1735f7c8",
"metadata": {},
"outputs": [],
"source": [
"def run_agent(data_path:str = '', provider:str = 'Mistral', agent_type:str = 'EDA', query:str = '', layers:str ='', temp:float = 0.1):\n",
" \n",
" df = pd.read_csv(data_path)\n",
" df.to_csv('./df.csv', index=False)\n",
" \n",
" if provider.lower() == 'mistral':\n",
" \n",
" llm = ChatAnyscale(model_name='mistralai/Mixtral-8x7B-Instruct-v0.1', temperature=temp)\n",
" \n",
" if agent_type == 'Data Explorer':\n",
" EDA_response, EDA_image = infer_EDA(user_input=query)\n",
" return EDA_response, EDA_image\n",
" \n",
" return None"
]
},
{
"cell_type": "markdown",
"id": "c2224b34",
"metadata": {},
"source": [
"# Gradio Demo"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "471a2947",
"metadata": {
"scrolled": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Running on local URL: http://127.0.0.1:7860\n",
"\n",
"Could not create share link. Please check your internet connection or our status page: https://status.gradio.app.\n"
]
},
{
"data": {
"text/html": [
"<div><iframe src=\"http://127.0.0.1:7860/\" 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": 10,
"metadata": {},
"output_type": "execute_result"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m ```python\n",
"import pandas as pd\n",
"import numpy as np\n",
"\n",
"# Read the data from 'df.csv'\n",
"df = pd.read_csv('df.csv')\n",
"\n",
"# Calculate the number of null values in each column\n",
"null_counts = df.isnull().sum()\n",
"\n",
"# Calculate the total number of null values in the dataframe\n",
"total_null_count = df.isnull().sum().sum()\n",
"\n",
"# Print the distribution of null values in the dataframe\n",
"print(\"Null Value Distribution:\")\n",
"print(null_counts)\n",
"print(f\"Total Null Count: {total_null_count}\")\n",
"```\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"Running code ...\n",
"\n",
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m ```python\n",
"import pandas as pd\n",
"import matplotlib.pyplot as plt\n",
"\n",
"# Read the data from 'df.csv'\n",
"df = pd.read_csv('df.csv')\n",
"\n",
"# Calculate the number of null values in each column\n",
"null_counts = df.isnull().sum()\n",
"\n",
"# Prepare data for plotting\n",
"data = null_counts.sort_values(ascending=False)\n",
"\n",
"# Create a bar plot of null values distribution\n",
"plt.figure(figsize=(10, 6))\n",
"plt.bar(data.index, data.values)\n",
"plt.title('Distribution of Null Values in the Dataframe')\n",
"plt.xlabel('Column Names')\n",
"plt.ylabel('Number of Null Values')\n",
"plt.xticks(rotation=45)\n",
"plt.savefig('graphs/null_values_distribution.png')\n",
"\n",
"# Print the null values distribution dataframe\n",
"print(data)\n",
"```\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"Running code ...\n",
"\n"
]
}
],
"source": [
"import gradio as gr\n",
"\n",
"demo = gr.Interface (\n",
" run_agent,\n",
" [\n",
" gr.UploadButton(label=\"Upload your CSV!\"),\n",
" gr.Radio([\"Mistral\",\"GPT\"],label=\"Select Your LLM\"),\n",
" gr.Radio([\"Data Explorer\", \"Hypothesis Tester\", \"Basic Inference\", \"Super Inference\"], label=\"Choose Your Agent\"),\n",
" gr.Text(label=\"Query\", info=\"Your input to the Agent\"),\n",
" gr.Text(label=\"Architecture\", info=\"Specify the layer by layer architecture only for Super Inference Agent\"),\n",
" gr.Slider(label=\"Model Temperature\", info=\"Slide right to make your model more creative!\")\n",
" ],\n",
" [\n",
" gr.Text(label=\"Updated JSON Object\", info=\"This the JSON Object with the changed component.\"),\n",
" gr.Image(label=\"Graph\")\n",
" ]\n",
")\n",
"demo.launch(share=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d351a2c2",
"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": "3.11.5"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|