import os
os.environ["SEARCHAPI_API_KEY"] = ""
from langchain_community.utilities import SearchApiAPIWrapper
search = SearchApiAPIWrapper()
search.run("Obama's first name?")
'Barack Obama Full name: Barack Hussein Obama II'
作为自问自答搜索链的一部分使用
os.environ["OPENAI_API_KEY"] = ""
from langchain_community.utilities import SearchApiAPIWrapper
from langchain.tools import tool
from langchain_openai import OpenAI
llm = OpenAI(temperature=0)
search = SearchApiAPIWrapper()
@tool
def intermediate_answer(query: str) -> str:
"""用于需要搜索提问时。"""
return search.run(query)
tools = [intermediate_answer]
from langchain.agents import create_agent
agent = create_agent("gpt-5.4-mini", tools)
input_message = {
"role": "user",
"content": "Who lived longer: Plato, Socrates, or Aristotle?",
}
for step in agent.stream(
{"messages": [input_message]},
stream_mode="values",
):
step["messages"][-1].pretty_print()
================================ Human Message =================================
Who lived longer: Plato, Socrates, or Aristotle?
================================== Ai Message ==================================
Tool Calls:
intermediate_answer (call_Q0JquDV3SWfnn3rkwJkJaffG)
Call ID: call_Q0JquDV3SWfnn3rkwJkJaffG
Args:
__arg1: Lifespan of Plato
intermediate_answer (call_j9rXzVlrCcGc8HOFnKUH6j5E)
Call ID: call_j9rXzVlrCcGc8HOFnKUH6j5E
Args:
__arg1: Lifespan of Socrates
intermediate_answer (call_IBQT2qn5PzDE6q0ZyfPdhRaX)
Call ID: call_IBQT2qn5PzDE6q0ZyfPdhRaX
Args:
__arg1: Lifespan of Aristotle
================================= Tool Message =================================
Name: intermediate_answer
384–322 BC was an Ancient Greek philosopher and polymath. His writings cover a broad range of subjects spanning the natural sciences, philosophy, linguistics, ...
The Greek philosopher Aristotle (384-322 B.C.) made significant and lasting contributions to nearly every aspect of human knowledge, ...
Aristotle's lifespan (384 - 322) (jan 1, 384 BC – jan 1, 322 BC). Added to timeline: Political Philosophy timeline. ByEdoardo. 25 Aug 2020.
Aristotle was one of the greatest philosophers and scientists the world has ever seen. He was born in 384 bc at Stagirus, a Greek seaport on the coast of Thrace ...
393–c. 370 bce), king of Macedonia and grandfather of Alexander the Great (reigned 336–323 bce). After his father's death in 367, Aristotle ...
It is difficult to rule out that possibility decisively, since little is known about the period of Aristotle's life from 341–335. He evidently ...
Lifespan: c. 384 B.C. to 322 B.C.; Contributions: Considered one of the greatest thinkers in various fields including politics, psychology, and ...
Aristotle (Greek: Ἀριστοτέλης Aristotélēs, pronounced [aristotélɛːs]) lived 384–322 BC.
Aristotle (384 B.C.E.—322 B.C.E.). Aristotle is a towering figure in ancient Greek philosophy, who made important contributions to logic, criticism, ...
Aristotle. Born: 384 BC in Stagirus, Macedonia, Greece Died: 322 BC in Chalcis, Euboea, Greece. Aristotle was not primarily a mathematician but made ...
================================== Ai Message ==================================
根据信息：
- 柏拉图据称活到约八十或八十一岁。
- 苏格拉底的确切寿命此处未直接说明，但历史上已知他大约生活在公元前470年至公元前399年，因此他约71岁。
- 亚里士多德生活在公元前384年至公元前322年，这意味着他约62岁。
因此，柏拉图比苏格拉底和亚里士多德都活得更长。
自定义参数
SearchApi 包装器可以自定义以使用不同的引擎，如 Google News、Google Jobs、Google Scholar 或其他可在 SearchApi 文档中找到的引擎。执行查询时可以传递 SearchApi 支持的所有参数。search = SearchApiAPIWrapper(engine="google_jobs")
search.run("AI Engineer", location="Portugal", gl="pt")[0:500]
'No good search result found'
获取带元数据的结果
import pprint
search = SearchApiAPIWrapper(engine="google_scholar")
results = search.results("Large Language Models")
pprint.pp(results)
{'search_metadata': {'id': 'search_6Lpb2Z8vDqdsPRbrGkVgQzRy',
'status': 'Success',
'created_at': '2025-05-11T03:39:28Z',
'request_time_taken': 0.86,
'parsing_time_taken': 0.01,
'total_time_taken': 0.87,
'request_url': 'https://scholar.google.com/scholar?q=Large+Language+Models&hl=en',
'html_url': 'https://www.searchapi.io/api/v1/searches/search_6Lpb2Z8vDqdsPRbrGkVgQzRy.html',
'json_url': 'https://www.searchapi.io/api/v1/searches/search_6Lpb2Z8vDqdsPRbrGkVgQzRy'},
'search_parameters': {'engine': 'google_scholar',
'q': 'Large Language Models',
'hl': 'en'},
'search_information': {'query_displayed': 'Large Language Models',
'total_results': 6390000,
'page': 1,
'time_taken_displayed': 0.08},
'organic_results': [{'position': 1,
'title': 'ChatGPT for good? On opportunities and '
'challenges of large language models for '
'education',
'data_cid': 'uthwmf2nU3EJ',
'link': 'https://www.sciencedirect.com/science/article/pii/S1041608023000195',
'publication': 'E Kasneci, K Seßler, S Küchemann, M '
'Bannert… - Learning and individual …, '
'2023 - Elsevier',
'snippet': '… state of large language models and their '
'applications. We then highlight how these '
'models can be … With regard to challenges, '
'we argue that large language models in '
'education require …',
'inline_links': {'cited_by': {'cites_id': '8166055256995715258',
'total': 4675,
'link': 'https://scholar.google.com/scholar?cites=8166055256995715258&as_sdt=2005&sciodt=0,5&hl=en'},
'versions': {'cluster_id': '8166055256995715258',
'total': 16,
'link': 'https://scholar.google.com/scholar?cluster=8166055256995715258&hl=en&as_sdt=0,5'},
'related_articles_link': 'https://scholar.google.com/scholar?q=related:uthwmf2nU3EJ:scholar.google.com/&scioq=Large+Language+Models&hl=en&as_sdt=0,5'},
'resource': {'name': 'osf.io',
'format': 'PDF',
'link': 'https://osf.io/preprints/edarxiv/5er8f/download'},
'authors': [{'name': 'E Kasneci',
'id': 'bZVkVvoAAAAJ',
'link': 'https://scholar.google.com/citations?user=bZVkVvoAAAAJ&hl=en&oi=sra'},
{'name': 'K Seßler',
'id': 'MbMBoN4AAAAJ',
'link': 'https://scholar.google.com/citations?user=MbMBoN4AAAAJ&hl=en&oi=sra'},
{'name': 'S Küchemann',
'id': 'g1jX5QUAAAAJ',
'link': 'https://scholar.google.com/citations?user=g1jX5QUAAAAJ&hl=en&oi=sra'},
{'name': 'M Bannert',
'id': 'TjfQ8QkAAAAJ',
'link': 'https://scholar.google.com/citations?user=TjfQ8QkAAAAJ&hl=en&oi=sra'}]},
{'position': 2,
'title': 'A survey on evaluation of large language '
'models',
'data_cid': 'o93zfHYlUTIJ',
'link': 'https://dl.acm.org/doi/abs/10.1145/3641289',
'publication': 'Y Chang, X Wang, J Wang, Y Wu, L Yang… - '
'ACM transactions on …, 2024 - dl.acm.org',
'snippet': '… 3.1 Natural Language Processing Tasks … '
'the development of language models, '
'particularly large language models, was to '
'enhance performance on natural language '
'processing tasks, …',
'inline_links': {'cited_by': {'cites_id': '3625720365842685347',
'total': 2864,
'link': 'https://scholar.google.com/scholar?cites=3625720365842685347&as_sdt=2005&sciodt=0,5&hl=en'},
'versions': {'cluster_id': '3625720365842685347',
'total': 8,
'link': 'https://scholar.google.com/scholar?cluster=3625720365842685347&hl=en&as_sdt=0,5'},
'related_articles_link': 'https://scholar.google.com/scholar?q=related:o93zfHYlUTIJ:scholar.google.com/&scioq=Large+Language+Models&hl=en&as_sdt=0,5'},
'resource': {'name': 'acm.org',
'format': 'PDF',
'link': 'https://dl.acm.org/doi/pdf/10.1145/3641289'},
'authors': [{'name': 'Y Chang',
'id': 'Hw-lrpAAAAAJ',
'link': 'https://scholar.google.com/citations?user=Hw-lrpAAAAAJ&hl=en&oi=sra'},
{'name': 'X Wang',
'id': 'Q7Ieos8AAAAJ',
'link': 'https://scholar.google.com/citations?user=Q7Ieos8AAAAJ&hl=en&oi=sra'},
{'name': 'J Wang',
'id': 'hBZ_tKsAAAAJ',
'link': 'https://scholar.google.com/citations?user=hBZ_tKsAAAAJ&hl=en&oi=sra'},
{'name': 'Y Wu',
'id': 'KVeRu2QAAAAJ',
'link': 'https://scholar.google.com/citations?user=KVeRu2QAAAAJ&hl=en&oi=sra'},
{'name': 'L Yang',
'id': 'go3sFxcAAAAJ',
'link': 'https://scholar.google.com/citations?user=go3sFxcAAAAJ&hl=en&oi=sra'}]},
{'position': 3,
'title': 'A comprehensive overview of large language '
'models',
'data_cid': 'UDLkJGuOVl4J',
'link': 'https://arxiv.org/abs/2307.06435',
'publication': 'H Naveed, AU Khan, S Qiu, M Saqib, S '
'Anwar… - arXiv preprint arXiv …, 2023 - '
'arxiv.org',
'snippet': '… Large Language Models (LLMs) have recently '
'demonstrated remarkable capabilities in '
'natural language processing tasks and '
'beyond. This success of LLMs has led to a '
'large influx of …',
'inline_links': {'cited_by': {'cites_id': '6797777278393922128',
'total': 990,
'link': 'https://scholar.google.com/scholar?cites=6797777278393922128&as_sdt=2005&sciodt=0,5&hl=en'},
'versions': {'cluster_id': '6797777278393922128',
'total': 4,
'link': 'https://scholar.google.com/scholar?cluster=6797777278393922128&hl=en&as_sdt=0,5'},
'related_articles_link': 'https://scholar.google.com/scholar?q=related:UDLkJGuOVl4J:scholar.google.com/&scioq=Large+Language+Models&hl=en&as_sdt=0,5',
'cached_page_link': 'https://scholar.googleusercontent.com/scholar?q=cache:UDLkJGuOVl4J:scholar.google.com/+Large+Language+Models&hl=en&as_sdt=0,5'},
'resource': {'name': 'arxiv.org',
'format': 'PDF',
'link': 'https://arxiv.org/pdf/2307.06435'},
'authors': [{'name': 'H Naveed',
'id': 'k5dpooQAAAAJ',
'link': 'https://scholar.google.com/citations?user=k5dpooQAAAAJ&hl=en&oi=sra'},
{'name': 'AU Khan',
'id': 'sbOhz2UAAAAJ',
'link': 'https://scholar.google.com/citations?user=sbOhz2UAAAAJ&hl=en&oi=sra'},
{'name': 'S Qiu',
'id': 'OPNVthUAAAAJ',
'link': 'https://scholar.google.com/citations?user=OPNVthUAAAAJ&hl=en&oi=sra'},
{'name': 'M Saqib',
'id': 'KvbLR3gAAAAJ',
'link': 'https://scholar.google.com/citations?user=KvbLR3gAAAAJ&hl=en&oi=sra'},
{'name': 'S Anwar',
'id': 'vPJIHywAAAAJ',
'link': 'https://scholar.google.com/citations?user=vPJIHywAAAAJ&hl=en&oi=sra'}]},
{'position': 4,
'title': 'Large language models in medicine',
'data_cid': 'Ph9AwHTmhzAJ',
'link': 'https://www.nature.com/articles/s41591-023-02448-8',
'publication': 'AJ Thirunavukarasu, DSJ Ting, K '
'Elangovan… - Nature medicine, 2023 - '
'nature.com',
'snippet': '… HuggingChat offers a free-to-access '
'chatbot with a similar interface to ChatGPT '
'but uses Large Language Model Meta AI '
'(LLaMA) as its backend model 30 . Finally, '
'cheap imitations of …',
'inline_links': {'cited_by': {'cites_id': '3497017024792502078',
'total': 2474,
'link': 'https://scholar.google.com/scholar?cites=3497017024792502078&as_sdt=2005&sciodt=0,5&hl=en'},
'versions': {'cluster_id': '3497017024792502078',
'total': 7,
'link': 'https://scholar.google.com/scholar?cluster=3497017024792502078&hl=en&as_sdt=0,5'},
'related_articles_link': 'https://scholar.google.com/scholar?q=related:Ph9AwHTmhzAJ:scholar.google.com/&scioq=Large+Language+Models&hl=en&as_sdt=0,5'},
'resource': {'name': 'google.com',
'format': 'PDF',
'link': 'https://drive.google.com/file/d/1FKEGsSZ9GYOeToeKpxB4m3atGRbC-TSm/view'},
'authors': [{'name': 'AJ Thirunavukarasu',
'id': '3qb1AYwAAAAJ',
'link': 'https://scholar.google.com/citations?user=3qb1AYwAAAAJ&hl=en&oi=sra'},
{'name': 'DSJ Ting',
'id': 'KbrpC8cAAAAJ',
'link': 'https://scholar.google.com/citations?user=KbrpC8cAAAAJ&hl=en&oi=sra'},
{'name': 'K Elangovan',
'id': 'BE_lVTQAAAAJ',
'link': 'https://scholar.google.com/citations?user=BE_lVTQAAAAJ&hl=en&oi=sra'}]},
{'position': 5,
'title': 'A watermark for large language models',
'data_cid': 'BlSyLHT4iiEJ',
'link': 'https://proceedings.mlr.press/v202/kirchenbauer23a.html',
'publication': 'J Kirchenbauer, J Geiping, Y Wen… - '
'International …, 2023 - '
'proceedings.mlr.press',
'snippet': '… We propose a watermarking framework for '
'proprietary language models. The … in the '
'language model just before it produces a '
'probability vector. The last layer of the '
'language model …',
'inline_links': {'cited_by': {'cites_id': '2417017327887471622',
'total': 774,
'link': 'https://scholar.google.com/scholar?cites=2417017327887471622&as_sdt=2005&sciodt=0,5&hl=en'},
'versions': {'cluster_id': '2417017327887471622',
'total': 13,
'link': 'https://scholar.google.com/scholar?cluster=2417017327887471622&hl=en&as_sdt=0,5'},
'related_articles_link': 'https://scholar.google.com/scholar?q=related:BlSyLHT4iiEJ:scholar.google.com/&scioq=Large+Language+Models&hl=en&as_sdt=0,5',
'cached_page_link': 'https://scholar.googleusercontent.com/scholar?q=cache:BlSyLHT4iiEJ:scholar.google.com/+Large+Language+Models&hl=en&as_sdt=0,5'},
'resource': {'name': 'mlr.press',
'format': 'PDF',
'link': 'https://proceedings.mlr.press/v202/kirchenbauer23a/kirchenbauer23a.pdf'},
'authors': [{'name': 'J Kirchenbauer',
'id': '48GJrbsAAAAJ',
'link': 'https://scholar.google.com/citations?user=48GJrbsAAAAJ&hl=en&oi=sra'},
{'name': 'J Geiping',
'id': '206vNCEAAAAJ',
'link': 'https://scholar.google.com/citations?user=206vNCEAAAAJ&hl=en&oi=sra'},
{'name': 'Y Wen',
'id': 'oUYfjg0AAAAJ',
'link': 'https://scholar.google.com/citations?user=oUYfjg0AAAAJ&hl=en&oi=sra'}]},
{'position': 6,
'title': 'Welcome to the era of chatgpt et al. the '
'prospects of large language models',
'data_cid': '3UrgC1BmpV8J',
'link': 'https://link.springer.com/article/10.1007/s12599-023-00795-x',
'publication': 'T Teubner, CM Flath, C Weinhardt… - '
'Business & Information …, 2023 - '
'Springer',
'snippet': 'The emergence of Large Language Models '
'(LLMs) in combination with easy-to-use '
'interfaces such as ChatGPT, Bing Chat, and '
'Google’s Bard represent both a Herculean '
'task and a …',
'inline_links': {'cited_by': {'cites_id': '6892027298743077597',
'total': 409,
'link': 'https://scholar.google.com/scholar?cites=6892027298743077597&as_sdt=2005&sciodt=0,5&hl=en'},
'versions': {'cluster_id': '6892027298743077597',
'total': 16,
'link': 'https://scholar.google.com/scholar?cluster=6892027298743077597&hl=en&as_sdt=0,5'},
'related_articles_link': 'https://scholar.google.com/scholar?q=related:3UrgC1BmpV8J:scholar.google.com/&scioq=Large+Language+Models&hl=en&as_sdt=0,5'},
'resource': {'name': 'springer.com',
'format': 'PDF',
'link': 'https://link.springer.com/content/pdf/10.1007/s12599-023-00795-x.pdf'},
'authors': [{'name': 'T Teubner',
'id': 'ZeCM1k8AAAAJ',
'link': 'https://scholar.google.com/citations?user=ZeCM1k8AAAAJ&hl=en&oi=sra'},
{'name': 'CM Flath',
'id': '5Iy85HsAAAAJ',
'link': 'https://scholar.google.com/citations?user=5Iy85HsAAAAJ&hl=en&oi=sra'},
{'name': 'C Weinhardt',
'id': 'lhfZxjAAAAAJ',
'link': 'https://scholar.google.com/citations?user=lhfZxjAAAAAJ&hl=en&oi=sra'}]},
{'position': 7,
'title': 'Talking about large language models',
'data_cid': '3eYYI745r_0J',
'link': 'https://dl.acm.org/doi/abs/10.1145/3624724',
'publication': 'M Shanahan - Communications of the ACM, '
'2024 - dl.acm.org',
'snippet': '… Recently, it has become commonplace to use '
'the term “large language model” both for the '
'generative models themselves and for the '
'systems in which they are embedded, '
'especially in …',
'inline_links': {'cited_by': {'cites_id': '18279892901315536605',
'total': 477,
'link': 'https://scholar.google.com/scholar?cites=18279892901315536605&as_sdt=2005&sciodt=0,5&hl=en'},
'versions': {'cluster_id': '18279892901315536605',
'total': 4,
'link': 'https://scholar.google.com/scholar?cluster=18279892901315536605&hl=en&as_sdt=0,5'},
'related_articles_link': 'https://scholar.google.com/scholar?q=related:3eYYI745r_0J:scholar.google.com/&scioq=Large+Language+Models&hl=en&as_sdt=0,5'},
'resource': {'name': 'acm.org',
'format': 'PDF',
'link': 'https://dl.acm.org/doi/pdf/10.1145/3624724'},
'authors': [{'name': 'M Shanahan',
'id': '00bnGpAAAAAJ',
'link': 'https://scholar.google.com/citations?user=00bnGpAAAAAJ&hl=en&oi=sra'}]},
{'position': 8,
'title': 'Explainability for large language models: A '
'survey',
'data_cid': '0AqRKEINMw4J',
'link': 'https://dl.acm.org/doi/abs/10.1145/3639372',
'publication': 'H Zhao, H Chen, F Yang, N Liu, H Deng, H '
'Cai… - ACM Transactions on …, 2024 - '
'dl.acm.org',
'snippet': '… Let us consider a scenario where we have a '
'language model and we input a specific text '
'into the model. The model then produces a '
'classification output, such as sentiment …',
'inline_links': {'cited_by': {'cites_id': '1023176118142831312',
'total': 576,
'link': 'https://scholar.google.com/scholar?cites=1023176118142831312&as_sdt=2005&sciodt=0,5&hl=en'},
'versions': {'cluster_id': '1023176118142831312',
'total': 7,
'link': 'https://scholar.google.com/scholar?cluster=1023176118142831312&hl=en&as_sdt=0,5'},
'related_articles_link': 'https://scholar.google.com/scholar?q=related:0AqRKEINMw4J:scholar.google.com/&scioq=Large+Language+Models&hl=en&as_sdt=0,5'},
'resource': {'name': 'acm.org',
'format': 'PDF',
'link': 'https://dl.acm.org/doi/pdf/10.1145/3639372'},
'authors': [{'name': 'H Zhao',
'id': '9FobigIAAAAJ',
'link': 'https://scholar.google.com/citations?user=9FobigIAAAAJ&hl=en&oi=sra'},
{'name': 'H Chen',
'id': 'DyYOgLwAAAAJ',
'link': 'https://scholar.google.com/citations?user=DyYOgLwAAAAJ&hl=en&oi=sra'},
{'name': 'F Yang',
'id': 'RXFeW-8AAAAJ',
'link': 'https://scholar.google.com/citations?user=RXFeW-8AAAAJ&hl=en&oi=sra'},
{'name': 'N Liu',
'id': 'Nir-EDYAAAAJ',
'link': 'https://scholar.google.com/citations?user=Nir-EDYAAAAJ&hl=en&oi=sra'},
{'name': 'H Cai',
'id': 'Kz-r34UAAAAJ',
'link': 'https://scholar.google.com/citations?user=Kz-r34UAAAAJ&hl=en&oi=sra'}]},
{'position': 9,
'title': 'Emergent abilities of large language models',
'data_cid': 'hG0iVOrOguoJ',
'link': 'https://arxiv.org/abs/2206.07682',
'publication': 'J Wei, Y Tay, R Bommasani, C Raffel, B '
'Zoph… - arXiv preprint arXiv …, 2022 - '
'arxiv.org',
'snippet': 'Scaling up language models has been shown to '
'predictably improve performance and sample '
'efficiency on a wide range of downstream '
'tasks. This paper instead discusses an …',
'inline_links': {'cited_by': {'cites_id': '16898296257676733828',
'total': 3436,
'link': 'https://scholar.google.com/scholar?cites=16898296257676733828&as_sdt=2005&sciodt=0,5&hl=en'},
'versions': {'cluster_id': '16898296257676733828',
'total': 11,
'link': 'https://scholar.google.com/scholar?cluster=16898296257676733828&hl=en&as_sdt=0,5'},
'related_articles_link': 'https://scholar.google.com/scholar?q=related:hG0iVOrOguoJ:scholar.google.com/&scioq=Large+Language+Models&hl=en&as_sdt=0,5',
'cached_page_link': 'https://scholar.googleusercontent.com/scholar?q=cache:hG0iVOrOguoJ:scholar.google.com/+Large+Language+Models&hl=en&as_sdt=0,5'},
'resource': {'name': 'arxiv.org',
'format': 'PDF',
'link': 'https://arxiv.org/pdf/2206.07682'},
'authors': [{'name': 'J Wei',
'id': 'wA5TK_0AAAAJ',
'link': 'https://scholar.google.com/citations?user=wA5TK_0AAAAJ&hl=en&oi=sra'},
{'name': 'Y Tay',
'id': 'VBclY_cAAAAJ',
'link': 'https://scholar.google.com/citations?user=VBclY_cAAAAJ&hl=en&oi=sra'},
{'name': 'R Bommasani',
'id': 'WMBXw1EAAAAJ',
'link': 'https://scholar.google.com/citations?user=WMBXw1EAAAAJ&hl=en&oi=sra'},
{'name': 'C Raffel',
'id': 'I66ZBYwAAAAJ',
'link': 'https://scholar.google.com/citations?user=I66ZBYwAAAAJ&hl=en&oi=sra'}]},
{'position': 10,
'title': 'A systematic evaluation of large language '
'models of code',
'data_cid': '-iQSW0h72hYJ',
'link': 'https://dl.acm.org/doi/abs/10.1145/3520312.3534862',
'publication': 'FF Xu, U Alon, G Neubig, VJ Hellendoorn '
'- Proceedings of the 6th ACM …, 2022 - '
'dl.acm.org',
'snippet': '… largest language models for code. We also '
'release PolyCoder, a large open-source '
'language model for code, trained exclusively '
'on code in 12 different programming '
'languages. In the …',
'inline_links': {'cited_by': {'cites_id': '1646764164453115130',
'total': 764,
'link': 'https://scholar.google.com/scholar?cites=1646764164453115130&as_sdt=2005&sciodt=0,5&hl=en'},
'versions': {'cluster_id': '1646764164453115130',
'total': 6,
'link': 'https://scholar.google.com/scholar?cluster=1646764164453115130&hl=en&as_sdt=0,5'},
'related_articles_link': 'https://scholar.google.com/scholar?q=related:-iQSW0h72hYJ:scholar.google.com/&scioq=Large+Language+Models&hl=en&as_sdt=0,5'},
'resource': {'name': 'acm.org',
'format': 'PDF',
'link': 'https://dl.acm.org/doi/pdf/10.1145/3520312.3534862'},
'authors': [{'name': 'FF Xu',
'id': '1hXyfIkAAAAJ',
'link': 'https://scholar.google.com/citations?user=1hXyfIkAAAAJ&hl=en&oi=sra'},
{'name': 'U Alon',
'id': 'QBn7vq8AAAAJ',
'link': 'https://scholar.google.com/citations?user=QBn7vq8AAAAJ&hl=en&oi=sra'},
{'name': 'G Neubig',
'id': 'wlosgkoAAAAJ',
'link': 'https://scholar.google.com/citations?user=wlosgkoAAAAJ&hl=en&oi=sra'},
{'name': 'VJ Hellendoorn',
'id': 'PfYrc5kAAAAJ',
'link': 'https://scholar.google.com/citations?user=PfYrc5kAAAAJ&hl=en&oi=sra'}]}],
'related_searches': [{'query': 'emergent large language models',
'highlighted': ['emergent'],
'link': 'https://scholar.google.com/scholar?hl=en&as_sdt=0,5&qsp=1&q=emergent+large+language+models&qst=ib'},
{'query': 'large language models abilities',
'highlighted': ['abilities'],
'link': 'https://scholar.google.com/scholar?hl=en&as_sdt=0,5&qsp=2&q=large+language+models+abilities&qst=ib'},
{'query': 'prompt large language models',
'highlighted': ['prompt'],
'link': 'https://scholar.google.com/scholar?hl=en&as_sdt=0,5&qsp=3&q=prompt+large+language+models&qst=ib'},
{'query': 'large language models training '
'compute-optimal',
'highlighted': ['training compute-optimal'],
'link': 'https://scholar.google.com/scholar?hl=en&as_sdt=0,5&qsp=4&q=large+language+models+training+compute-optimal&qst=ib'},
{'query': 'large language models machine translation',
'highlighted': ['machine translation'],
'link': 'https://scholar.google.com/scholar?hl=en&as_sdt=0,5&qsp=5&q=large+language+models+machine+translation&qst=ib'},
{'query': 'large language models zero shot',
'highlighted': ['zero shot'],
'link': 'https://scholar.google.com/scholar?hl=en&as_sdt=0,5&qsp=6&q=large+language+models+zero+shot&qst=ib'},
{'query': 'large language models chatgpt',
'highlighted': ['chatgpt'],
'link': 'https://scholar.google.com/scholar?hl=en&as_sdt=0,5&qsp=7&q=large+language+models+chatgpt&qst=ib'},
{'query': 'fine tuning large language models',
'highlighted': ['fine tuning'],
'link': 'https://scholar.google.com/scholar?hl=en&as_sdt=0,5&qsp=8&q=fine+tuning+large+language+models&qst=ib'}],
'pagination': {'current': 1,
'next': 'https://scholar.google.com/scholar?start=10&q=Large+Language+Models&hl=en&as_sdt=0,5',
'other_pages': {'2': 'https://scholar.google.com/scholar?start=10&q=Large+Language+Models&hl=en&as_sdt=0,5',
'3': 'https://scholar.google.com/scholar?start=20&q=Large+Language+Models&hl=en&as_sdt=0,5',
'4': 'https://scholar.google.com/scholar?start=30&q=Large+Language+Models&hl=en&as_sdt=0,5',
'5': 'https://scholar.google.com/scholar?start=40&q=Large+Language+Models&hl=en&as_sdt=0,5',
'6': 'https://scholar.google.com/scholar?start=50&q=Large+Language+Models&hl=en&as_sdt=0,5',
'7': 'https://scholar.google.com/scholar?start=60&q=Large+Language+Models&hl=en&as_sdt=0,5',
'8': 'https://scholar.google.com/scholar?start=70&q=Large+Language+Models&hl=en&as_sdt=0,5',
'9': 'https://scholar.google.com/scholar?start=80&q=Large+Language+Models&hl=en&as_sdt=0,5',
'10': 'https://scholar.google.com/scholar?start=90&q=Large+Language+Models&hl=en&as_sdt=0,5'}}}
连接这些文档 到 Claude、VSCode 等，通过 MCP 获取实时答案。