Spaces:
Sleeping
Sleeping
File size: 32,620 Bytes
3a62d3f |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Search Engine with Tools and Agents"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Agents uses llm to choose the sequence of task. whereas in chain its hard coded. \n",
"### In Agents, allm is used as a reasoning model to determine which action to take and in which order.\n",
"\n",
"### Tools are interfaces that an LLM, Agents or cahin uses to interact with the world."
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"from langchain_community.tools import ArxivQueryRun, WikipediaQueryRun\n",
"from langchain_community.utilities import WikipediaAPIWrapper, ArxivAPIWrapper"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'wikipedia'"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# using inbuilt tool of wikipedia\n",
"api_wrapper_wiki=WikipediaAPIWrapper(top_k_results=1,doc_content_chars_max=250)\n",
"wiki = WikipediaQueryRun(api_wrapper=api_wrapper_wiki)\n",
"wiki.name"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'arxiv'"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"api_wrapper_arxiv=ArxivAPIWrapper(top_k_results=1,doc_content_chars_max=250)\n",
"arxiv=ArxivQueryRun(api_wrapper=api_wrapper_arxiv)\n",
"arxiv.name"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [],
"source": [
"tools=[wiki,arxiv]"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"from dotenv import load_dotenv\n",
"load_dotenv() #load all environment variables\n",
"\n",
"os.environ['HF_TOKEN']=os.getenv(\"HF_TOKEN\")"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [],
"source": [
"# Custom tools [RAG Tool]\n",
"from langchain_community.document_loaders import WebBaseLoader\n",
"from langchain_community.vectorstores import FAISS\n",
"\n",
"from langchain_huggingface import HuggingFaceEmbeddings\n",
"embeddings=HuggingFaceEmbeddings(model_name=\"all-MiniLM-L6-v2\")\n",
"\n",
"from langchain_text_splitters import RecursiveCharacterTextSplitter\n"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"VectorStoreRetriever(tags=['FAISS', 'HuggingFaceEmbeddings'], vectorstore=<langchain_community.vectorstores.faiss.FAISS object at 0x00000291BC1737F0>, search_kwargs={})"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"loader=WebBaseLoader(\"https://docs.smith.langchain.com/\")\n",
"docs=loader.load()\n",
"documents=RecursiveCharacterTextSplitter(chunk_size=1000,chunk_overlap=200).split_documents(docs)\n",
"vectordb=FAISS.from_documents(documents,embeddings)\n",
"retriever=vectordb.as_retriever()\n",
"retriever"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'langsmith-search'"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from langchain.tools.retriever import create_retriever_tool\n",
"retriever_tool=create_retriever_tool(\n",
" retriever,\n",
" \"langsmith-search\",\n",
" \"Search any information about Langsmith\"\n",
")\n",
"retriever_tool.name"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[WikipediaQueryRun(api_wrapper=WikipediaAPIWrapper(wiki_client=<module 'wikipedia' from 'd:\\\\udemy\\\\Langchain\\\\venvl\\\\lib\\\\site-packages\\\\wikipedia\\\\__init__.py'>, top_k_results=1, lang='en', load_all_available_meta=False, doc_content_chars_max=250)),\n",
" ArxivQueryRun(api_wrapper=ArxivAPIWrapper(arxiv_search=<class 'arxiv.Search'>, arxiv_exceptions=(<class 'arxiv.ArxivError'>, <class 'arxiv.UnexpectedEmptyPageError'>, <class 'arxiv.HTTPError'>), top_k_results=1, ARXIV_MAX_QUERY_LENGTH=300, continue_on_failure=False, load_max_docs=100, load_all_available_meta=False, doc_content_chars_max=250)),\n",
" Tool(name='langsmith-search', description='Search any information about Langsmith', args_schema=<class 'langchain_core.tools.retriever.RetrieverInput'>, func=functools.partial(<function _get_relevant_documents at 0x000002918E600C10>, retriever=VectorStoreRetriever(tags=['FAISS', 'HuggingFaceEmbeddings'], vectorstore=<langchain_community.vectorstores.faiss.FAISS object at 0x00000291BC1737F0>, search_kwargs={}), document_prompt=PromptTemplate(input_variables=['page_content'], input_types={}, partial_variables={}, template='{page_content}'), document_separator='\\n\\n', response_format='content'), coroutine=functools.partial(<function _aget_relevant_documents at 0x000002918E925E10>, retriever=VectorStoreRetriever(tags=['FAISS', 'HuggingFaceEmbeddings'], vectorstore=<langchain_community.vectorstores.faiss.FAISS object at 0x00000291BC1737F0>, search_kwargs={}), document_prompt=PromptTemplate(input_variables=['page_content'], input_types={}, partial_variables={}, template='{page_content}'), document_separator='\\n\\n', response_format='content'))]"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tools=[wiki,arxiv,retriever_tool]\n",
"tools"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [],
"source": [
"# Run all the tools with Agents and LLM models\n",
"from langchain_groq import ChatGroq\n",
"load_dotenv()\n",
"groq_api_key=os.getenv(\"GROQ_API_KEY\")\n",
"\n",
"llm=ChatGroq(groq_api_key=groq_api_key,model_name=\"Llama3-8b-8192\")"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[SystemMessagePromptTemplate(prompt=PromptTemplate(input_variables=[], input_types={}, partial_variables={}, template='You are a helpful assistant'), additional_kwargs={}),\n",
" MessagesPlaceholder(variable_name='chat_history', optional=True),\n",
" HumanMessagePromptTemplate(prompt=PromptTemplate(input_variables=['input'], input_types={}, partial_variables={}, template='{input}'), additional_kwargs={}),\n",
" MessagesPlaceholder(variable_name='agent_scratchpad')]"
]
},
"execution_count": 25,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Prompt Template\n",
"from langchain import hub\n",
"\n",
"# Get the prompt to use - you can modify this!\n",
"prompt = hub.pull(\"hwchase17/openai-functions-agent\")\n",
"prompt.messages"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"RunnableAssign(mapper={\n",
" agent_scratchpad: RunnableLambda(lambda x: format_to_openai_tool_messages(x['intermediate_steps']))\n",
"})\n",
"| ChatPromptTemplate(input_variables=['agent_scratchpad', 'input'], optional_variables=['chat_history'], input_types={'chat_history': list[typing.Annotated[typing.Union[typing.Annotated[langchain_core.messages.ai.AIMessage, Tag(tag='ai')], typing.Annotated[langchain_core.messages.human.HumanMessage, Tag(tag='human')], typing.Annotated[langchain_core.messages.chat.ChatMessage, Tag(tag='chat')], typing.Annotated[langchain_core.messages.system.SystemMessage, Tag(tag='system')], typing.Annotated[langchain_core.messages.function.FunctionMessage, Tag(tag='function')], typing.Annotated[langchain_core.messages.tool.ToolMessage, Tag(tag='tool')], typing.Annotated[langchain_core.messages.ai.AIMessageChunk, Tag(tag='AIMessageChunk')], typing.Annotated[langchain_core.messages.human.HumanMessageChunk, Tag(tag='HumanMessageChunk')], typing.Annotated[langchain_core.messages.chat.ChatMessageChunk, Tag(tag='ChatMessageChunk')], typing.Annotated[langchain_core.messages.system.SystemMessageChunk, Tag(tag='SystemMessageChunk')], typing.Annotated[langchain_core.messages.function.FunctionMessageChunk, Tag(tag='FunctionMessageChunk')], typing.Annotated[langchain_core.messages.tool.ToolMessageChunk, Tag(tag='ToolMessageChunk')]], FieldInfo(annotation=NoneType, required=True, discriminator=Discriminator(discriminator=<function _get_type at 0x000002918E33E4D0>, custom_error_type=None, custom_error_message=None, custom_error_context=None))]], 'agent_scratchpad': list[typing.Annotated[typing.Union[typing.Annotated[langchain_core.messages.ai.AIMessage, Tag(tag='ai')], typing.Annotated[langchain_core.messages.human.HumanMessage, Tag(tag='human')], typing.Annotated[langchain_core.messages.chat.ChatMessage, Tag(tag='chat')], typing.Annotated[langchain_core.messages.system.SystemMessage, Tag(tag='system')], typing.Annotated[langchain_core.messages.function.FunctionMessage, Tag(tag='function')], typing.Annotated[langchain_core.messages.tool.ToolMessage, Tag(tag='tool')], typing.Annotated[langchain_core.messages.ai.AIMessageChunk, Tag(tag='AIMessageChunk')], typing.Annotated[langchain_core.messages.human.HumanMessageChunk, Tag(tag='HumanMessageChunk')], typing.Annotated[langchain_core.messages.chat.ChatMessageChunk, Tag(tag='ChatMessageChunk')], typing.Annotated[langchain_core.messages.system.SystemMessageChunk, Tag(tag='SystemMessageChunk')], typing.Annotated[langchain_core.messages.function.FunctionMessageChunk, Tag(tag='FunctionMessageChunk')], typing.Annotated[langchain_core.messages.tool.ToolMessageChunk, Tag(tag='ToolMessageChunk')]], FieldInfo(annotation=NoneType, required=True, discriminator=Discriminator(discriminator=<function _get_type at 0x000002918E33E4D0>, custom_error_type=None, custom_error_message=None, custom_error_context=None))]]}, partial_variables={'chat_history': []}, metadata={'lc_hub_owner': 'hwchase17', 'lc_hub_repo': 'openai-functions-agent', 'lc_hub_commit_hash': 'a1655024b06afbd95d17449f21316291e0726f13dcfaf990cc0d18087ad689a5'}, messages=[SystemMessagePromptTemplate(prompt=PromptTemplate(input_variables=[], input_types={}, partial_variables={}, template='You are a helpful assistant'), additional_kwargs={}), MessagesPlaceholder(variable_name='chat_history', optional=True), HumanMessagePromptTemplate(prompt=PromptTemplate(input_variables=['input'], input_types={}, partial_variables={}, template='{input}'), additional_kwargs={}), MessagesPlaceholder(variable_name='agent_scratchpad')])\n",
"| RunnableBinding(bound=ChatGroq(client=<groq.resources.chat.completions.Completions object at 0x00000291BC70EAD0>, async_client=<groq.resources.chat.completions.AsyncCompletions object at 0x00000291BC70FE80>, model_name='Llama3-8b-8192', model_kwargs={}, groq_api_key=SecretStr('**********')), kwargs={'tools': [{'type': 'function', 'function': {'name': 'wikipedia', 'description': 'A wrapper around Wikipedia. Useful for when you need to answer general questions about people, places, companies, facts, historical events, or other subjects. Input should be a search query.', 'parameters': {'properties': {'query': {'description': 'query to look up on wikipedia', 'type': 'string'}}, 'required': ['query'], 'type': 'object'}}}, {'type': 'function', 'function': {'name': 'arxiv', 'description': 'A wrapper around Arxiv.org Useful for when you need to answer questions about Physics, Mathematics, Computer Science, Quantitative Biology, Quantitative Finance, Statistics, Electrical Engineering, and Economics from scientific articles on arxiv.org. Input should be a search query.', 'parameters': {'properties': {'query': {'description': 'search query to look up', 'type': 'string'}}, 'required': ['query'], 'type': 'object'}}}, {'type': 'function', 'function': {'name': 'langsmith-search', 'description': 'Search any information about Langsmith', 'parameters': {'properties': {'query': {'description': 'query to look up in retriever', 'type': 'string'}}, 'required': ['query'], 'type': 'object'}}}]}, config={}, config_factories=[])\n",
"| OpenAIToolsAgentOutputParser()"
]
},
"execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Agents\n",
"from langchain.agents import create_openai_tools_agent\n",
"agent=create_openai_tools_agent(llm,tools,prompt)\n",
"agent"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"AgentExecutor(verbose=True, agent=RunnableMultiActionAgent(runnable=RunnableAssign(mapper={\n",
" agent_scratchpad: RunnableLambda(lambda x: format_to_openai_tool_messages(x['intermediate_steps']))\n",
"})\n",
"| ChatPromptTemplate(input_variables=['agent_scratchpad', 'input'], optional_variables=['chat_history'], input_types={'chat_history': list[typing.Annotated[typing.Union[typing.Annotated[langchain_core.messages.ai.AIMessage, Tag(tag='ai')], typing.Annotated[langchain_core.messages.human.HumanMessage, Tag(tag='human')], typing.Annotated[langchain_core.messages.chat.ChatMessage, Tag(tag='chat')], typing.Annotated[langchain_core.messages.system.SystemMessage, Tag(tag='system')], typing.Annotated[langchain_core.messages.function.FunctionMessage, Tag(tag='function')], typing.Annotated[langchain_core.messages.tool.ToolMessage, Tag(tag='tool')], typing.Annotated[langchain_core.messages.ai.AIMessageChunk, Tag(tag='AIMessageChunk')], typing.Annotated[langchain_core.messages.human.HumanMessageChunk, Tag(tag='HumanMessageChunk')], typing.Annotated[langchain_core.messages.chat.ChatMessageChunk, Tag(tag='ChatMessageChunk')], typing.Annotated[langchain_core.messages.system.SystemMessageChunk, Tag(tag='SystemMessageChunk')], typing.Annotated[langchain_core.messages.function.FunctionMessageChunk, Tag(tag='FunctionMessageChunk')], typing.Annotated[langchain_core.messages.tool.ToolMessageChunk, Tag(tag='ToolMessageChunk')]], FieldInfo(annotation=NoneType, required=True, discriminator=Discriminator(discriminator=<function _get_type at 0x000002918E33E4D0>, custom_error_type=None, custom_error_message=None, custom_error_context=None))]], 'agent_scratchpad': list[typing.Annotated[typing.Union[typing.Annotated[langchain_core.messages.ai.AIMessage, Tag(tag='ai')], typing.Annotated[langchain_core.messages.human.HumanMessage, Tag(tag='human')], typing.Annotated[langchain_core.messages.chat.ChatMessage, Tag(tag='chat')], typing.Annotated[langchain_core.messages.system.SystemMessage, Tag(tag='system')], typing.Annotated[langchain_core.messages.function.FunctionMessage, Tag(tag='function')], typing.Annotated[langchain_core.messages.tool.ToolMessage, Tag(tag='tool')], typing.Annotated[langchain_core.messages.ai.AIMessageChunk, Tag(tag='AIMessageChunk')], typing.Annotated[langchain_core.messages.human.HumanMessageChunk, Tag(tag='HumanMessageChunk')], typing.Annotated[langchain_core.messages.chat.ChatMessageChunk, Tag(tag='ChatMessageChunk')], typing.Annotated[langchain_core.messages.system.SystemMessageChunk, Tag(tag='SystemMessageChunk')], typing.Annotated[langchain_core.messages.function.FunctionMessageChunk, Tag(tag='FunctionMessageChunk')], typing.Annotated[langchain_core.messages.tool.ToolMessageChunk, Tag(tag='ToolMessageChunk')]], FieldInfo(annotation=NoneType, required=True, discriminator=Discriminator(discriminator=<function _get_type at 0x000002918E33E4D0>, custom_error_type=None, custom_error_message=None, custom_error_context=None))]]}, partial_variables={'chat_history': []}, metadata={'lc_hub_owner': 'hwchase17', 'lc_hub_repo': 'openai-functions-agent', 'lc_hub_commit_hash': 'a1655024b06afbd95d17449f21316291e0726f13dcfaf990cc0d18087ad689a5'}, messages=[SystemMessagePromptTemplate(prompt=PromptTemplate(input_variables=[], input_types={}, partial_variables={}, template='You are a helpful assistant'), additional_kwargs={}), MessagesPlaceholder(variable_name='chat_history', optional=True), HumanMessagePromptTemplate(prompt=PromptTemplate(input_variables=['input'], input_types={}, partial_variables={}, template='{input}'), additional_kwargs={}), MessagesPlaceholder(variable_name='agent_scratchpad')])\n",
"| RunnableBinding(bound=ChatGroq(client=<groq.resources.chat.completions.Completions object at 0x00000291BC70EAD0>, async_client=<groq.resources.chat.completions.AsyncCompletions object at 0x00000291BC70FE80>, model_name='Llama3-8b-8192', model_kwargs={}, groq_api_key=SecretStr('**********')), kwargs={'tools': [{'type': 'function', 'function': {'name': 'wikipedia', 'description': 'A wrapper around Wikipedia. Useful for when you need to answer general questions about people, places, companies, facts, historical events, or other subjects. Input should be a search query.', 'parameters': {'properties': {'query': {'description': 'query to look up on wikipedia', 'type': 'string'}}, 'required': ['query'], 'type': 'object'}}}, {'type': 'function', 'function': {'name': 'arxiv', 'description': 'A wrapper around Arxiv.org Useful for when you need to answer questions about Physics, Mathematics, Computer Science, Quantitative Biology, Quantitative Finance, Statistics, Electrical Engineering, and Economics from scientific articles on arxiv.org. Input should be a search query.', 'parameters': {'properties': {'query': {'description': 'search query to look up', 'type': 'string'}}, 'required': ['query'], 'type': 'object'}}}, {'type': 'function', 'function': {'name': 'langsmith-search', 'description': 'Search any information about Langsmith', 'parameters': {'properties': {'query': {'description': 'query to look up in retriever', 'type': 'string'}}, 'required': ['query'], 'type': 'object'}}}]}, config={}, config_factories=[])\n",
"| OpenAIToolsAgentOutputParser(), input_keys_arg=[], return_keys_arg=[], stream_runnable=True), tools=[WikipediaQueryRun(api_wrapper=WikipediaAPIWrapper(wiki_client=<module 'wikipedia' from 'd:\\\\udemy\\\\Langchain\\\\venvl\\\\lib\\\\site-packages\\\\wikipedia\\\\__init__.py'>, top_k_results=1, lang='en', load_all_available_meta=False, doc_content_chars_max=250)), ArxivQueryRun(api_wrapper=ArxivAPIWrapper(arxiv_search=<class 'arxiv.Search'>, arxiv_exceptions=(<class 'arxiv.ArxivError'>, <class 'arxiv.UnexpectedEmptyPageError'>, <class 'arxiv.HTTPError'>), top_k_results=1, ARXIV_MAX_QUERY_LENGTH=300, continue_on_failure=False, load_max_docs=100, load_all_available_meta=False, doc_content_chars_max=250)), Tool(name='langsmith-search', description='Search any information about Langsmith', args_schema=<class 'langchain_core.tools.retriever.RetrieverInput'>, func=functools.partial(<function _get_relevant_documents at 0x000002918E600C10>, retriever=VectorStoreRetriever(tags=['FAISS', 'HuggingFaceEmbeddings'], vectorstore=<langchain_community.vectorstores.faiss.FAISS object at 0x00000291BC1737F0>, search_kwargs={}), document_prompt=PromptTemplate(input_variables=['page_content'], input_types={}, partial_variables={}, template='{page_content}'), document_separator='\\n\\n', response_format='content'), coroutine=functools.partial(<function _aget_relevant_documents at 0x000002918E925E10>, retriever=VectorStoreRetriever(tags=['FAISS', 'HuggingFaceEmbeddings'], vectorstore=<langchain_community.vectorstores.faiss.FAISS object at 0x00000291BC1737F0>, search_kwargs={}), document_prompt=PromptTemplate(input_variables=['page_content'], input_types={}, partial_variables={}, template='{page_content}'), document_separator='\\n\\n', response_format='content'))])"
]
},
"execution_count": 27,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Agent Executor\n",
"from langchain.agents import AgentExecutor\n",
"agent_executor=AgentExecutor(agent=agent,tools=tools,verbose=True)\n",
"agent_executor"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m\n",
"Invoking: `langsmith-search` with `{'query': 'Langsmith'}`\n",
"\n",
"\n",
"\u001b[0m\u001b[38;5;200m\u001b[1;3mGet started with LangSmith | 🦜️🛠️ LangSmith\n",
"\n",
"LangSmith + LangChain OSSLangSmith is framework-agnostic — it can be used with or without LangChain's open source frameworks langchain and langgraph.If you are using either of these, you can enable LangSmith tracing with a single environment variable.\n",
"For more see the how-to guide for setting up LangSmith with LangChain or setting up LangSmith with LangGraph.\n",
"Observability\n",
"Observability is important for any software application, but especially so for LLM applications. LLMs are non-deterministic by nature, meaning they can produce unexpected results. This makes them trickier than normal to debug.\n",
"This is where LangSmith can help! LangSmith has LLM-native observability, allowing you to get meaningful insights from your application. LangSmith’s observability features have you covered throughout all stages of application development - from prototyping, to beta testing, to production.\n",
"\n",
"Skip to main contentJoin us at Interrupt: The Agent AI Conference by LangChain on May 13 & 14 in San Francisco!API ReferenceRESTPythonJS/TSSearchRegionUSEUGo to AppGet StartedObservabilityEvaluationPrompt EngineeringDeployment (LangGraph Platform)AdministrationSelf-hostingPricingReferenceCloud architecture and scalabilityAuthz and AuthnAuthentication methodsdata_formatsEvaluationDataset transformationsRegions FAQsdk_referenceGet StartedOn this pageGet started with LangSmith\n",
"LangSmith is a platform for building production-grade LLM applications.\n",
"It allows you to closely monitor and evaluate your application, so you can ship quickly and with confidence.\n",
"ObservabilityAnalyze traces in LangSmith and configure metrics, dashboards, alerts based on these.EvalsEvaluate your application over production traffic — score application performance and get human feedback on your data.Prompt EngineeringIterate on prompts, with automatic version control and collaboration features.\n",
"\n",
"Get started by adding tracing to your application.\n",
"Create dashboards to view key metrics like RPS, error rates and costs.\n",
"\n",
"Evals\n",
"The quality and development speed of AI applications depends on high-quality evaluation datasets and metrics to test and optimize your applications on. The LangSmith SDK and UI make building and running high-quality evaluations easy.\n",
"\n",
"Get started by creating your first evaluation.\n",
"Quickly assess the performance of your application using our off-the-shelf evaluators as a starting point.\n",
"Analyze results of evaluations in the LangSmith UI and compare results over time.\n",
"Easily collect human feedback on your data to improve your application.\n",
"\n",
"Prompt Engineering\n",
"While traditional software applications are built by writing code, AI applications involve writing prompts to instruct the LLM on what to do. LangSmith provides a set of tools designed to enable and facilitate prompt engineering to help you find the perfect prompt for your application.\u001b[0m\u001b[32;1m\u001b[1;3mIt seems like Langsmith is a platform for building production-grade Large Language Model (LLM) applications, focusing on observability, evaluation, and prompt engineering. It provides tools for monitoring and evaluating LLM applications, as well as features for iterating on prompts and collecting human feedback.\n",
"\n",
"With Langsmith, developers can:\n",
"\n",
"1. Analyze traces and configure metrics, dashboards, and alerts for their LLM applications.\n",
"2. Evaluate their application over production traffic, scoring performance and getting human feedback on their data.\n",
"3. Iterate on prompts with automatic version control and collaboration features.\n",
"4. Create and run high-quality evaluations with Langsmith's SDK and UI.\n",
"5. Analyze evaluation results and compare them over time.\n",
"6. Collect human feedback on their data to improve their application.\n",
"\n",
"Langsmith seems to be a comprehensive platform for building and deploying LLM applications, providing a set of tools and features to help developers create high-quality, production-ready AI applications.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"{'input': 'Tell me about Langsmith',\n",
" 'output': \"It seems like Langsmith is a platform for building production-grade Large Language Model (LLM) applications, focusing on observability, evaluation, and prompt engineering. It provides tools for monitoring and evaluating LLM applications, as well as features for iterating on prompts and collecting human feedback.\\n\\nWith Langsmith, developers can:\\n\\n1. Analyze traces and configure metrics, dashboards, and alerts for their LLM applications.\\n2. Evaluate their application over production traffic, scoring performance and getting human feedback on their data.\\n3. Iterate on prompts with automatic version control and collaboration features.\\n4. Create and run high-quality evaluations with Langsmith's SDK and UI.\\n5. Analyze evaluation results and compare them over time.\\n6. Collect human feedback on their data to improve their application.\\n\\nLangsmith seems to be a comprehensive platform for building and deploying LLM applications, providing a set of tools and features to help developers create high-quality, production-ready AI applications.\"}"
]
},
"execution_count": 28,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.invoke(\n",
" {\"input\":\"Tell me about Langsmith\"}\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m\n",
"Invoking: `wikipedia` with `{'query': 'Machine Learning'}`\n",
"\n",
"\n",
"\u001b[0m\u001b[36;1m\u001b[1;3mPage: Machine learning\n",
"Summary: Machine learning (ML) is a field of study in artificial intelligence concerned with the development and study of statistical algorithms that can learn from data and generalize to unseen data, and thus perform tasks wit\u001b[0m\u001b[32;1m\u001b[1;3m\n",
"Invoking: `wikipedia` with `{'query': 'Types of Machine Learning'}`\n",
"\n",
"\n",
"\u001b[0m\u001b[36;1m\u001b[1;3mPage: Machine learning\n",
"Summary: Machine learning (ML) is a field of study in artificial intelligence concerned with the development and study of statistical algorithms that can learn from data and generalize to unseen data, and thus perform tasks wit\u001b[0m\u001b[32;1m\u001b[1;3mIt seems like the tool call didn't yield any new information. However, I can try to provide a summary based on the previous result.\n",
"\n",
"Machine learning is a type of artificial intelligence that enables systems to learn from data and improve their performance over time. There are several types of machine learning, including:\n",
"\n",
"* Supervised learning: This type of learning involves training a model on labeled data, where the correct output is already known. The model learns to map inputs to outputs based on the labeled data.\n",
"* Unsupervised learning: This type of learning involves training a model on unlabeled data, where the correct output is not known. The model learns to identify patterns and relationships in the data.\n",
"* Reinforcement learning: This type of learning involves training a model to make decisions based on rewards or penalties. The model learns to choose actions that maximize the reward.\n",
"\n",
"These are just a few examples, and there are many other types of machine learning as well.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"{'input': 'Whant is Maching Learning',\n",
" 'output': \"It seems like the tool call didn't yield any new information. However, I can try to provide a summary based on the previous result.\\n\\nMachine learning is a type of artificial intelligence that enables systems to learn from data and improve their performance over time. There are several types of machine learning, including:\\n\\n* Supervised learning: This type of learning involves training a model on labeled data, where the correct output is already known. The model learns to map inputs to outputs based on the labeled data.\\n* Unsupervised learning: This type of learning involves training a model on unlabeled data, where the correct output is not known. The model learns to identify patterns and relationships in the data.\\n* Reinforcement learning: This type of learning involves training a model to make decisions based on rewards or penalties. The model learns to choose actions that maximize the reward.\\n\\nThese are just a few examples, and there are many other types of machine learning as well.\"}"
]
},
"execution_count": 29,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.invoke(\n",
" {\"input\":\"Whant is Maching Learning\"}\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m\n",
"Invoking: `arxiv` with `{'query': '1706.03762v7'}`\n",
"\n",
"\n",
"\u001b[0m\u001b[33;1m\u001b[1;3mPublished: 2023-08-02\n",
"Title: Attention Is All You Need\n",
"Authors: Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin\n",
"Summary: The dominant sequence transduction models are based on c\u001b[0m\u001b[32;1m\u001b[1;3mBased on the output from the tool call, I can respond directly without using any further tools. The research paper \"Attention Is All You Need\" by Ashish Vaswani et al. was published on August 2, 2023.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"{'input': 'Whant is this research paper 1706.03762v7 about?',\n",
" 'output': 'Based on the output from the tool call, I can respond directly without using any further tools. The research paper \"Attention Is All You Need\" by Ashish Vaswani et al. was published on August 2, 2023.'}"
]
},
"execution_count": 30,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# arXiv:1706.03762v7\n",
"agent_executor.invoke(\n",
" {\"input\":\"Whant is this research paper 1706.03762v7 about?\"}\n",
")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"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": "3.10.0"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|