File size: 30,257 Bytes
4539ea5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# arxiv-Research\n",
    "from langchain_community.tools import ArxivQueryRun,WikipediaQueryRun\n",
    "from langchain_community.utilities import WikipediaAPIWrapper,ArxivAPIWrapper"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'wikipedia'"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# we used the inbulit 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\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'arxiv'"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# using inbulit arxiv tool\n",
    "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": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[WikipediaQueryRun(api_wrapper=WikipediaAPIWrapper(wiki_client=<module 'wikipedia' from 'd:\\\\RAG-Doc-Q&A\\\\venv\\\\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))]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tools=[wiki,arxiv]\n",
    "tools"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "# creating custom tools[RAG Tool]\n",
    "import os\n",
    "from dotenv import load_dotenv\n",
    "load_dotenv()\n",
    "from langchain_groq import ChatGroq\n",
    "groq_api_key=os.getenv(\"GROQ_API_KEY\")\n",
    "from langchain_community.document_loaders import WebBaseLoader\n",
    "from langchain_community.vectorstores import FAISS\n",
    "\n",
    "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain_community.embeddings import OllamaEmbeddings\n",
    "embeddings=(\n",
    "  OllamaEmbeddings(model=\"gemma2:2b\")\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "VectorStoreRetriever(tags=['FAISS', 'OllamaEmbeddings'], vectorstore=<langchain_community.vectorstores.faiss.FAISS object at 0x00000168C52FDFC0>)"
      ]
     },
     "execution_count": 8,
     "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": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'langsmith-search'"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# making the retriever as retriever tool\n",
    "from langchain.tools.retriever import create_retriever_tool\n",
    "retriever_tool=create_retriever_tool(retriever,\"langsmith-search\",\"search any information about langsmith\")\n",
    "retriever_tool.name"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[WikipediaQueryRun(api_wrapper=WikipediaAPIWrapper(wiki_client=<module 'wikipedia' from 'd:\\\\RAG-Doc-Q&A\\\\venv\\\\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 0x00000168BD38EA70>, retriever=VectorStoreRetriever(tags=['FAISS', 'OllamaEmbeddings'], vectorstore=<langchain_community.vectorstores.faiss.FAISS object at 0x00000168C52FDFC0>), document_prompt=PromptTemplate(input_variables=['page_content'], template='{page_content}'), document_separator='\\n\\n'), coroutine=functools.partial(<function _aget_relevant_documents at 0x00000168BD38EB00>, retriever=VectorStoreRetriever(tags=['FAISS', 'OllamaEmbeddings'], vectorstore=<langchain_community.vectorstores.faiss.FAISS object at 0x00000168C52FDFC0>), document_prompt=PromptTemplate(input_variables=['page_content'], template='{page_content}'), document_separator='\\n\\n'))]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tools.append(retriever_tool)\n",
    "tools"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "# run all this tools with agents with ll models\n",
    "llm=ChatGroq(groq_api_key=groq_api_key,model_name=\"Gemma2-9b-It\")\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "d:\\RAG-Doc-Q&A\\venv\\lib\\site-packages\\langsmith\\client.py:5431: LangChainBetaWarning: The function `loads` is in beta. It is actively being worked on, so the API may change.\n",
      "  prompt = loads(json.dumps(prompt_object.manifest))\n"
     ]
    }
   ],
   "source": [
    "# creating the prompt template\n",
    "# hub a prompt templated already created and uploaded inn hub\n",
    "from langchain import hub\n",
    "prompt=hub.pull(\"hwchase17/openai-functions-agent\")\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[SystemMessagePromptTemplate(prompt=PromptTemplate(input_variables=[], template='You are a helpful assistant')),\n",
       " MessagesPlaceholder(variable_name='chat_history', optional=True),\n",
       " HumanMessagePromptTemplate(prompt=PromptTemplate(input_variables=['input'], template='{input}')),\n",
       " MessagesPlaceholder(variable_name='agent_scratchpad')]"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "prompt.messages"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "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': typing.List[typing.Union[langchain_core.messages.ai.AIMessage, langchain_core.messages.human.HumanMessage, langchain_core.messages.chat.ChatMessage, langchain_core.messages.system.SystemMessage, langchain_core.messages.function.FunctionMessage, langchain_core.messages.tool.ToolMessage]], 'agent_scratchpad': typing.List[typing.Union[langchain_core.messages.ai.AIMessage, langchain_core.messages.human.HumanMessage, langchain_core.messages.chat.ChatMessage, langchain_core.messages.system.SystemMessage, langchain_core.messages.function.FunctionMessage, langchain_core.messages.tool.ToolMessage]]}, 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=[], template='You are a helpful assistant')), MessagesPlaceholder(variable_name='chat_history', optional=True), HumanMessagePromptTemplate(prompt=PromptTemplate(input_variables=['input'], template='{input}')), MessagesPlaceholder(variable_name='agent_scratchpad')])\n",
       "| RunnableBinding(bound=ChatGroq(client=<groq.resources.chat.completions.Completions object at 0x00000168DD512CE0>, async_client=<groq.resources.chat.completions.AsyncCompletions object at 0x00000168DD511A20>, model_name='Gemma2-9b-It', 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': {'type': 'object', 'properties': {'query': {'description': 'query to look up on wikipedia', 'type': 'string'}}, 'required': ['query']}}}, {'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': {'type': 'object', 'properties': {'query': {'description': 'search query to look up', 'type': 'string'}}, 'required': ['query']}}}, {'type': 'function', 'function': {'name': 'langsmith-search', 'description': 'search any information about langsmith', 'parameters': {'type': 'object', 'properties': {'query': {'description': 'query to look up in retriever', 'type': 'string'}}, 'required': ['query']}}}]})\n",
       "| OpenAIToolsAgentOutputParser()"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from langchain.agents import create_openai_tools_agent\n",
    "agent=create_openai_tools_agent(llm,tools,prompt)\n",
    "agent"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "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': typing.List[typing.Union[langchain_core.messages.ai.AIMessage, langchain_core.messages.human.HumanMessage, langchain_core.messages.chat.ChatMessage, langchain_core.messages.system.SystemMessage, langchain_core.messages.function.FunctionMessage, langchain_core.messages.tool.ToolMessage]], 'agent_scratchpad': typing.List[typing.Union[langchain_core.messages.ai.AIMessage, langchain_core.messages.human.HumanMessage, langchain_core.messages.chat.ChatMessage, langchain_core.messages.system.SystemMessage, langchain_core.messages.function.FunctionMessage, langchain_core.messages.tool.ToolMessage]]}, 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=[], template='You are a helpful assistant')), MessagesPlaceholder(variable_name='chat_history', optional=True), HumanMessagePromptTemplate(prompt=PromptTemplate(input_variables=['input'], template='{input}')), MessagesPlaceholder(variable_name='agent_scratchpad')])\n",
       "| RunnableBinding(bound=ChatGroq(client=<groq.resources.chat.completions.Completions object at 0x00000168DD512CE0>, async_client=<groq.resources.chat.completions.AsyncCompletions object at 0x00000168DD511A20>, model_name='Gemma2-9b-It', 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': {'type': 'object', 'properties': {'query': {'description': 'query to look up on wikipedia', 'type': 'string'}}, 'required': ['query']}}}, {'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': {'type': 'object', 'properties': {'query': {'description': 'search query to look up', 'type': 'string'}}, 'required': ['query']}}}, {'type': 'function', 'function': {'name': 'langsmith-search', 'description': 'search any information about langsmith', 'parameters': {'type': 'object', 'properties': {'query': {'description': 'query to look up in retriever', 'type': 'string'}}, 'required': ['query']}}}]})\n",
       "| OpenAIToolsAgentOutputParser(), input_keys_arg=[], return_keys_arg=[], stream_runnable=True), tools=[WikipediaQueryRun(api_wrapper=WikipediaAPIWrapper(wiki_client=<module 'wikipedia' from 'd:\\\\RAG-Doc-Q&A\\\\venv\\\\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 0x00000168BD38EA70>, retriever=VectorStoreRetriever(tags=['FAISS', 'OllamaEmbeddings'], vectorstore=<langchain_community.vectorstores.faiss.FAISS object at 0x00000168C52FDFC0>), document_prompt=PromptTemplate(input_variables=['page_content'], template='{page_content}'), document_separator='\\n\\n'), coroutine=functools.partial(<function _aget_relevant_documents at 0x00000168BD38EB00>, retriever=VectorStoreRetriever(tags=['FAISS', 'OllamaEmbeddings'], vectorstore=<langchain_community.vectorstores.faiss.FAISS object at 0x00000168C52FDFC0>), document_prompt=PromptTemplate(input_variables=['page_content'], template='{page_content}'), document_separator='\\n\\n'))])"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# to run the we create a agent executer\n",
    "from langchain.agents import AgentExecutor\n",
    "agent_executer=AgentExecutor(agent=agent,tools=tools,verbose=True)\n",
    "agent_executer\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "# from langchain_experimental.llms.ollama_functions import OllamaFunctions\n",
    "\n",
    "# model = OllamaFunctions(model=\"llama3\", format=\"json\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "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",
      "description=\"A sample dataset in LangSmith.\")client.create_examples(    inputs=[        {\"postfix\": \"to LangSmith\"},        {\"postfix\": \"to Evaluations in LangSmith\"},    ],    outputs=[        {\"output\": \"Welcome to LangSmith\"},        {\"output\": \"Welcome to Evaluations in LangSmith\"},    ],    dataset_id=dataset.id,)# Define your evaluatordef exact_match(run, example):    return {\"score\": run.outputs[\"output\"] == example.outputs[\"output\"]}experiment_results = evaluate(    lambda input: \"Welcome \" + input['postfix'], # Your AI system goes here    data=dataset_name, # The data to predict and grade over    evaluators=[exact_match], # The evaluators to score the results    experiment_prefix=\"sample-experiment\", # The name of the experiment    metadata={      \"version\": \"1.0.0\",      \"revision_id\": \"beta\"    },)import { Client, Run, Example } from \"langsmith\";import { evaluate } from \"langsmith/evaluation\";import { EvaluationResult } from \"langsmith/evaluation\";const client = new\n",
      "\n",
      "OPENAI_API_KEY=<your-openai-api-key>4. Log your first trace‚ÄãTracing to LangSmith for LangChain usersThere is no need to use the LangSmith SDK directly if your application is built entirely on LangChain (either Python and JS).We've outlined a tracing guide specifically for LangChain users here.We provide multiple ways to log traces to LangSmith. Below, we'll highlight\n",
      "\n",
      "Skip to main contentGo to API DocsSearchRegionUSEUGo to AppQuick startTutorialsHow-to guidesConceptsReferencePricingSelf-hostingLangGraph CloudQuick startOn this pageGet started with LangSmithLangSmith is a platform for building production-grade LLM applications. It allows you to closely monitor and evaluate your application, so you can ship quickly and with confidence. Use of LangChain is not necessary - LangSmith works on its own!1. Install LangSmith‚ÄãPythonTypeScriptpip install -U langsmithyarn add langsmith2. Create an API key‚ÄãTo create an API key head to the Settings page. Then click Create API Key.3. Set up your environment‚ÄãShellexport LANGCHAIN_TRACING_V2=trueexport LANGCHAIN_API_KEY=<your-api-key># The below examples use the OpenAI API, though it's not necessary in generalexport OPENAI_API_KEY=<your-openai-api-key>4. Log your first trace‚ÄãTracing to LangSmith for LangChain usersThere is no need to use the LangSmith SDK directly if your application is built entirely on\u001b[0m\u001b[32;1m\u001b[1;3mLangSmith is a platform for building production-grade LLM applications. It allows you to closely monitor and evaluate your application, so you can ship quickly and with confidence.\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "{'input': 'Tell me about Langsmith',\n",
       " 'output': 'LangSmith is a platform for building production-grade LLM applications. It allows you to closely monitor and evaluate your application, so you can ship quickly and with confidence.'}"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent_executer.invoke({\"input\":\"Tell me about Langsmith\"})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "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': 'Large language model'}`\n",
      "\n",
      "\n",
      "\u001b[0m\u001b[36;1m\u001b[1;3mPage: Large language model\n",
      "Summary: A large language model (LLM) is a computational model capable of language generation or other natural language processing tasks. As language models, LLMs acquire these abilities by learning statistical relationship\u001b[0m\u001b[32;1m\u001b[1;3mLarge language models (LLMs) are a type of artificial intelligence that excel at understanding and generating human language. \n",
      "\n",
      "They are trained on massive datasets of text and code, allowing them to learn patterns and relationships within language. This enables them to perform a wide range of tasks, including:\n",
      "\n",
      "* **Text Generation:** Writing stories, articles, poems, and other types of creative content.\n",
      "* **Translation:** Converting text from one language to another.\n",
      "* **Summarization:** Condensing large amounts of text into shorter summaries.\n",
      "* **Question Answering:** Providing answers to questions based on given information.\n",
      "* **Code Generation:** Writing computer code in various programming languages.\n",
      "\n",
      "LLMs have the potential to revolutionize many industries, from customer service and education to research and entertainment.\n",
      "\n",
      "\n",
      "\n",
      "\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "{'input': 'tell me about llm models',\n",
       " 'output': 'Large language models (LLMs) are a type of artificial intelligence that excel at understanding and generating human language. \\n\\nThey are trained on massive datasets of text and code, allowing them to learn patterns and relationships within language. This enables them to perform a wide range of tasks, including:\\n\\n* **Text Generation:** Writing stories, articles, poems, and other types of creative content.\\n* **Translation:** Converting text from one language to another.\\n* **Summarization:** Condensing large amounts of text into shorter summaries.\\n* **Question Answering:** Providing answers to questions based on given information.\\n* **Code Generation:** Writing computer code in various programming languages.\\n\\nLLMs have the potential to revolutionize many industries, from customer service and education to research and entertainment.\\n\\n\\n\\n'}"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent_executer.invoke({\"input\":\"tell me about llm models\"})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "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': '1706.03762'}`\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;3m\"Attention Is All You Need\" is a groundbreaking paper in the field of natural language processing that introduces the Transformer architecture. \n",
      "\n",
      "This architecture relies entirely on attention mechanisms, dispensing with recurrent or convolutional networks altogether. The Transformer has revolutionized the field, leading to significant improvements in machine translation, text summarization, and other NLP tasks.  \n",
      "\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "{'input': 'what the paper 1706.03762 about?',\n",
       " 'output': '\"Attention Is All You Need\" is a groundbreaking paper in the field of natural language processing that introduces the Transformer architecture. \\n\\nThis architecture relies entirely on attention mechanisms, dispensing with recurrent or convolutional networks altogether. The Transformer has revolutionized the field, leading to significant improvements in machine translation, text summarization, and other NLP tasks.  \\n'}"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent_executer.invoke({\"input\":\"what the paper 1706.03762 about?\"})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "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': 'what is a summary about what i asked'}`\n",
      "\n",
      "\n",
      "\u001b[0m\u001b[36;1m\u001b[1;3mPage: What Is a Woman?\n",
      "Summary: What Is a Woman? is a 2022 American online film about gender and transgender issues, directed by Justin Folk and presented by conservative political commentator Matt Walsh. The film was released by conservative website\u001b[0m\u001b[32;1m\u001b[1;3m\n",
      "Invoking: `wikipedia` with `{'query': 'what is a summary about gender and transgender issues'}`\n",
      "\n",
      "\n",
      "\u001b[0m\u001b[36;1m\u001b[1;3mPage: What Is a Woman?\n",
      "Summary: What Is a Woman? is a 2022 American online film about gender and transgender issues, directed by Justin Folk and presented by conservative political commentator Matt Walsh. The film was released by conservative website\u001b[0m\u001b[32;1m\u001b[1;3mGender and transgender issues are complex and multifaceted. \n",
      "\n",
      "At their core, gender and transgender identities relate to a person's internal sense of their own gender, which may or may not align with the sex they were assigned at birth. \n",
      "\n",
      "Transgender people have a gender identity that differs from the sex they were assigned at birth. This can involve a range of experiences, including:\n",
      "\n",
      "* **Transgender men:** Assigned female at birth but identify as male.\n",
      "* **Transgender women:** Assigned male at birth but identify as female.\n",
      "* **Non-binary:** Individuals who do not identify exclusively as male or female.\n",
      "\n",
      "Understanding gender and transgender issues requires recognizing that:\n",
      "\n",
      "* **Gender is a spectrum:** It's not simply male or female, and individuals may experience their gender in various ways.\n",
      "* **Gender identity is distinct from sexual orientation:** A person's gender identity does not determine who they are attracted to.\n",
      "* **Transgender identities are valid:** Transgender people deserve respect and recognition for who they are.\n",
      "\n",
      "\n",
      "\n",
      "It's important to approach these topics with sensitivity and a willingness to learn. \n",
      "\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "{'input': 'give me the summary about what i asked',\n",
       " 'output': \"Gender and transgender issues are complex and multifaceted. \\n\\nAt their core, gender and transgender identities relate to a person's internal sense of their own gender, which may or may not align with the sex they were assigned at birth. \\n\\nTransgender people have a gender identity that differs from the sex they were assigned at birth. This can involve a range of experiences, including:\\n\\n* **Transgender men:** Assigned female at birth but identify as male.\\n* **Transgender women:** Assigned male at birth but identify as female.\\n* **Non-binary:** Individuals who do not identify exclusively as male or female.\\n\\nUnderstanding gender and transgender issues requires recognizing that:\\n\\n* **Gender is a spectrum:** It's not simply male or female, and individuals may experience their gender in various ways.\\n* **Gender identity is distinct from sexual orientation:** A person's gender identity does not determine who they are attracted to.\\n* **Transgender identities are valid:** Transgender people deserve respect and recognition for who they are.\\n\\n\\n\\nIt's important to approach these topics with sensitivity and a willingness to learn. \\n\"}"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent_executer.invoke({\"input\":\"give me the summary about what i asked\"})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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
}