diff --git a/src/react_agent/graph.py b/src/react_agent/graph.py index 5af78c5..83848d4 100644 --- a/src/react_agent/graph.py +++ b/src/react_agent/graph.py @@ -125,3 +125,4 @@ def route_model_output(state: State) -> Literal["__end__", "tools"]: interrupt_before=[], # Add node names here to update state before they're called interrupt_after=[], # Add node names here to update state after they're called ) +graph.name = "ReAct Agent" # This customizes the name in LangSmith \ No newline at end of file diff --git a/tests/casettes/103fe67e-a040-4e4e-aadb-b20a7057f904.yaml b/tests/casettes/103fe67e-a040-4e4e-aadb-b20a7057f904.yaml new file mode 100644 index 0000000..0ea32e3 --- /dev/null +++ b/tests/casettes/103fe67e-a040-4e4e-aadb-b20a7057f904.yaml @@ -0,0 +1,464 @@ +interactions: +- request: + body: '{"max_tokens": 1024, "messages": [{"role": "user", "content": "Who is the + founder of LangChain?"}], "model": "claude-3-5-sonnet-20240620", "system": "You + are a helpful AI assistant.\n\nSystem time: 2024-09-16T12:24:33.011280+00:00", + "tools": [{"name": "scrape_webpage", "description": "Scrape the given webpage + and return a summary of text based on the instructions.", "input_schema": {"type": + "object", "properties": {"url": {"description": "The URL of the webpage to scrape.", + "type": "string"}, "instructions": {"description": "The instructions to give + to the scraper. An LLM will be used to respond using the instructions and the + scraped text.", "type": "string"}, "config": {"type": "object", "properties": + {"tags": {"type": "array", "items": {"type": "string"}}, "metadata": {"type": + "object"}, "callbacks": {"anyOf": [{"type": "array", "items": {}}, {}]}, "run_name": + {"type": "string"}, "max_concurrency": {"type": "integer"}, "recursion_limit": + {"type": "integer"}, "configurable": {"type": "object"}, "run_id": {"type": + "string", "format": "uuid"}}}}, "required": ["url", "instructions", "config"]}}, + {"name": "search", "description": "Search for general web results. This function + performs a search using the Tavily search engine, which is designed\nto provide + comprehensive, accurate, and trusted results. It''s particularly useful\nfor + answering questions about current events.", "input_schema": {"type": "object", + "properties": {"query": {"type": "string"}}, "required": ["query"]}}]}' + headers: {} + method: POST + uri: https://api.anthropic.com/v1/messages + response: + body: + string: !!binary | + H4sIAAAAAAAAA3RRwY7TQAz9FcsXLtNVtpSKzgV1ewC63UqLVruoCEVD4jSBxG7HHtFS5d9XyQoB + B06Wn/3s9+wLNiV67HSfZ9dzXq/Xnz8lXt53y9Pm4Xa5vdut0aGdDzR0kWrYEzqM0g5AUG3UAhs6 + 7KSkFj0WbUglTV5P3kxUmMkm02w6y+bTDB0WwkZs6L9cfg81Og30MXh8EAisPymC1Y3CMZFaIwzh + myQDqwkqSVxSBKlgE3i/qkPDDj6+altgohJMQCnEooZKIhQpRmKDwCWEokgxGEHDlcQuDIOvYEMG + HUEpYHWwkXSWdIW9+yNRpM2TDsbHaw15yrPr1Wq12374VTy9vT3d8M32fbV4/B7RIYdu4L3oGFh8 + SIb+gsdE8Ywen2qBRv/r5x32/VeHanLIIwUV/lfFWFA6JuKC0HNqW4dp/I2/vGzLTX4QK/r5YuZQ + kv2NLaZ9/wwAAP//AwAoDYjV+gEAAA== + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 8c40d5f83851985e-SJC + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Mon, 16 Sep 2024 12:24:53 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + X-Robots-Tag: + - none + anthropic-ratelimit-requests-limit: + - '4000' + anthropic-ratelimit-requests-remaining: + - '3999' + anthropic-ratelimit-requests-reset: + - '2024-09-16T12:24:54Z' + anthropic-ratelimit-tokens-limit: + - '400000' + anthropic-ratelimit-tokens-remaining: + - '400000' + anthropic-ratelimit-tokens-reset: + - '2024-09-16T12:24:53Z' + request-id: + - req_01Dz6cSGBZ25kTSQUUSNk2zs + via: + - 1.1 google + x-cloud-trace-context: + - ada7375721ba3518afe0c80850b9daaa + status: + code: 200 + message: OK +- request: + body: null + headers: {} + method: POST + uri: https://api.tavily.com/search + response: + body: + string: "{\"query\":\"Who is the founder of LangChain?\",\"follow_up_questions\":null,\"answer\":null,\"images\":[],\"results\":[{\"title\":\"LangChain + Company Profile 2024: Valuation, Funding & Investors - PitchBook\",\"url\":\"https://pitchbook.com/profiles/company/522935-92\",\"content\":\"LangChain + was founded in 2022. Who is the founder of LangChain? Harrison Chase and Ankush + Gola are the founders of LangChain. Who is the CEO of LangChain? Harrison + Chase is the CEO of LangChain. Where is LangChain headquartered? LangChain + is headquartered in San Francisco, CA. What is the size of LangChain? LangChain + has 43 total employees ...\",\"score\":0.9997695,\"raw_content\":null},{\"title\":\"Harrison + Chase - The AI Conference\",\"url\":\"https://aiconference.com/speakers/harrison-chase/\",\"content\":\"Harrison + Chase is the co-founder and CEO of LangChain, a company formed around the + open-source Python/Typescript packages that aim to make it easy to develop + Language Model applications. Prior to starting LangChain, he led the ML team + at Robust Intelligence (an MLOps company focused on testing and validation + of machine learning models), led the ...\",\"score\":0.99951214,\"raw_content\":null},{\"title\":\"Harrison + Chase - Forbes\",\"url\":\"https://www.forbes.com/profile/harrison-chase/\",\"content\":\"Cofounder, + LangChain. Harrison Chase only cofounded LangChain in late 2022, but the company + caught instant attention for enabling anyone to build apps powered by large + language models like GPT-4 ...\",\"score\":0.99924165,\"raw_content\":null},{\"title\":\"LangChain + - Wikipedia\",\"url\":\"https://en.wikipedia.org/wiki/LangChain\",\"content\":\"In + October 2023 LangChain introduced LangServe, a deployment tool designed to + facilitate the transition from LCEL (LangChain Expression Language) prototypes + to production-ready applications.[5]\\nIntegrations[edit]\\nAs of March 2023, + LangChain included integrations with systems including Amazon, Google, and + Microsoft Azure cloud storage; API wrappers for news, movie information, and + weather; Bash for summarization, syntax and semantics checking, and execution + of shell scripts; multiple web scraping subsystems and templates; few-shot + learning prompt generation support; finding and summarizing \\\"todo\\\" tasks + in code; Google Drive documents, spreadsheets, and presentations summarization, + extraction, and creation; Google Search and Microsoft Bing web search; OpenAI, + Anthropic, and Hugging Face language models; iFixit repair guides and wikis + search and summarization; MapReduce for question answering, combining documents, + and question generation; N-gram overlap scoring; PyPDF, pdfminer, fitz, and + pymupdf for PDF file text extraction and manipulation; Python and JavaScript + code generation, analysis, and debugging; Milvus vector database[6] to store + and retrieve vector embeddings; Weaviate vector database[7] to cache embedding + and data objects; Redis cache database storage; Python RequestsWrapper and + other methods for API requests; SQL and NoSQL databases including JSON support; + Streamlit, including for logging; text mapping for k-nearest neighbors search; + time zone conversion and calendar operations; tracing and recording stack + symbols in threaded and asynchronous subprocess runs; and the Wolfram Alpha + website and SDK.[8] As a language model integration framework, LangChain's + use-cases largely overlap with those of language models in general, including + document analysis and summarization, chatbots, and code analysis.[2]\\nHistory[edit]\\nLangChain + was launched in October 2022 as an open source project by Harrison Chase, + while working at machine learning startup Robust Intelligence. In April 2023, + LangChain had incorporated and the new startup raised over $20 million in + funding at a valuation of at least $200 million from venture firm Sequoia + Capital, a week after announcing a $10 million seed investment from Benchmark.[3][4]\\n + The project quickly garnered popularity, with improvements from hundreds of + contributors on GitHub, trending discussions on Twitter, lively activity on + the project's Discord server, many YouTube tutorials, and meetups in San Francisco + and London. As of April 2023, it can read from more than 50 document types + and data sources.[9]\\nReferences[edit]\\nExternal links[edit]\",\"score\":0.9964204,\"raw_content\":null},{\"title\":\"LangChain + | Company Overview & News - Forbes\",\"url\":\"https://www.forbes.com/companies/langchain/\",\"content\":\"LangChain. + Founded in late 2022, LangChain was an instant hit in Silicon Valley for its + software that enables anyone to build apps powered by large language models + like GPT-4 in as little as two ...\",\"score\":0.9964204,\"raw_content\":null},{\"title\":\"Harrison + Chase - Co-Founder and CEO @ LangChain - Crunchbase\",\"url\":\"https://www.crunchbase.com/person/harrison-chase\",\"content\":\"Number + of Current Jobs 1. Number of Past Jobs 1. Harrison Chase is the Co-Founder + and CEO at LangChain. Additionally, Harrison Chase has had 1 past job as the + Machine Learning Engineer at Robust Intelligence. LangChain Co-Founder and + CEO Jan 2023. Organization Name.\",\"score\":0.99505633,\"raw_content\":null},{\"title\":\"Key + Insights from Harrison Chase's Talk on Building Next-Level AI Agents\",\"url\":\"https://www.turingpost.com/p/harrison-chase-langchain-ai-agents\",\"content\":\"Harrison + Chase, founder of LangChain, shared insights on the evolution of AI agents + and their applications during Sequoia Capital's AI Ascent. ... Saves you a + lot of research time, plus gives a flashback to ML history and insights into + the future. Stay ahead alongside over 65,000 professionals from top AI labs, + ML startups, and enterprises ...\",\"score\":0.99392605,\"raw_content\":null},{\"title\":\"What + Is LangChain? - IBM\",\"url\":\"https://www.ibm.com/topics/langchain\",\"content\":\"Applications + made with LangChain provide great utility for a variety of use cases, from + straightforward question-answering and text generation tasks to more complex + solutions that use an LLM as a \u201Creasoning engine.\u201D\\nTrain, validate, + tune and deploy generative AI, foundation models and machine learning capabilities + with ease and build AI applications in a fraction of the time with a fraction + of the data.\\n When building a chain for an agent, inputs include:\\nDespite + their heralded power and versatility, LLMs have important limitations: namely, + a lack of up-to-date information, a lack of domain-specific expertise and + a general difficulty with math.\\nLangChain tools\_(link resides outside ibm.com) + are a set of functions that empower LangChain agents to interact with real-world + information in order to expand or improve the services it can provide. Launched + by Harrison Chase in October 2022, LangChain enjoyed a meteoric rise to prominence: + as of June 2023, it was the single fastest-growing open source project on + Github.1 Coinciding with the momentous launch of OpenAI\u2019s ChatGPT the + following month, LangChain has played a significant role in making generative + AI more accessible to enthusiasts in the wake of its widespread popularity.\\n + Reimagine how you work with\_AI: our diverse, global team of more than 20,000 + AI\_experts can help you quickly and confidently\_design and scale AI and + automation across your\_business, working across our own IBM\_watsonx\_technology\_and + an open ecosystem of partners to deliver any\_AI model, on any cloud, guided + by ethics and trust.\\n While it\u2019s the GPT model that interprets the + user\u2019s input and composes a natural language response, it\u2019s the + application that (among other things) provides an interface for the user to + type and read and a UX design that governs the chatbot experience.\",\"score\":0.99306935,\"raw_content\":null},{\"title\":\"LangChain's + origin story | Basedash\",\"url\":\"https://www.basedash.com/blog/langchains-origin-story\",\"content\":\"USER + CRM\\nADMIN PANEL\\nSQL COMPOSER WITH AI\\nRelated posts\\nRelated posts\\nRelated + posts\\nMy 9 core Mac apps and utilities\\nTom Johnson\\nHow Supabase became + this generation\u2019s database\\nMax Musing\\nReport: The 2023 State of Databases\\nMax + Musing\\nBasedash on the main stage at Collision 2023\\nMax Musing\\nBasedash + raises $4.5M led by Matrix\\nMax Musing\\n6 Retool Alternatives for 2023 - + A Comprehensive Guide\\nJordan Chavis\\nSOC IIType 2 Certified\\nCompany\\nAbout\\nCareers\\nTerms + of service\\nPrivacy policy\\nContact us\\nBlog\\nBrand\\nSlack community\\nSitemap\\nProduct\\nPricing\\nIntegrations\\nFeedback\\nChangelog\\nDocs\\nDownload + app\\nStatus\\nFeatures\\nViews\\nQueries\\nActions\\nSecurity\\nPower features\\n\xA9 + 2023 BaseDash Inc.\\nProudly carbon-neutral.\\n SOC IIType 2 Certified\\nCompany\\nAbout\\nCareers\\nTerms + of service\\nPrivacy policy\\nContact us\\nBlog\\nBrand\\nSlack community\\nSitemap\\nProduct\\nPricing\\nIntegrations\\nFeedback\\nChangelog\\nDocs\\nDownload + app\\nStatus\\nFeatures\\nViews\\nQueries\\nActions\\nSecurity\\nPower features\\n\xA9 + 2023 BaseDash Inc.\\nProudly carbon-neutral.\\n SOC IIType 2 Certified\\nCompany\\nAbout\\nCareers\\nTerms + of service\\nPrivacy policy\\nContact us\\nBlog\\nBrand\\nSlack community\\nSitemap\\nProduct\\nPricing\\nIntegrations\\nFeedback\\nChangelog\\nDocs\\nDownload + app\\nStatus\\nFeatures\\nViews\\nQueries\\nActions\\nSecurity\\nPower features\\n\xA9 + 2023 BaseDash Inc.\\nProudly carbon-neutral. About\\nFeatures\\nPricing\\nChangelog\\nBlog\\nDocs\\nLog + in\\nSign up\\nAbout\\nFeatures\\nPricing\\nLog in\\nSign up\\nLog in\\nSign + up\\nLangChain's origin story\\nMax Musing\\nFounder\\nThe admin panel that + you'll actually want to use. To do this, the LangSmith product allows developers + to see the inputs and outputs at each step of a model run and the exact sequence + of runs (debug), write tests to check if the response was intended behavior + (test), collect input/output examples to further refine the model (evaluate), + and log latency, token usage, and feedback (monitor).\\n\",\"score\":0.98208266,\"raw_content\":null},{\"title\":\"The + Point of LangChain \u2014 with Harrison Chase of LangChain\",\"url\":\"https://www.latent.space/p/langchain\",\"content\":\"And + so you can do a lot of things like reflection and kind of like making sure + that you're on the right track and really put more safeguards and thinking + about these agents as opposed to relying on like chas and interface, like + the bot we have that's on GitHub answering questions on the issues, I think + probably gives better answers than the bots that we have that are on chat + on the website. [00:50:32]\\nHarrison: And then between kind of like allowing + for, I think one helpful thing that we did in terms of like distinguishing + between basically the base interfaces and then more complex stuff is part + of the separation around the docs is there's like the components piece, which + has the model IO, the retrieval, the agents, the callbacks, things like that. + And then like, I know a lot of people are doing this, but like a personal + assistant for like managing like email calendar, basic stuff, which I think + is, I think that's like a fantastic application for these like agent like + things, because if you think about personal assistants today, you usually + interact, I don't have one, but I'm told you interact with them over email. + Show Notes\\nLangChain\\nLangChain\u2019s Berkshire Hathaway Homepage\\nAbstractions + tweet\\nLangSmith\\nLangSmith Cookbooks repo\\nLangChain Retrieval blog\\nEvaluating + CSV Question/Answering blog and YouTube\\nMultiOn Partner blog\\nHarvard Sports + Analytics Collective\\nEvaluating RAG Webinar\\nawesome-langchain:\\nLLM Math + Chain\\nSelf-Ask\\nLangChain Hub UI\\n\u201CLangChain is Pointless\u201D\\nHarrison\u2019s + links\\nsports - estimating player compatibility in the NBA\\nearly interest + in prompt injections\\nGitHub\\nTwitter\\nTimestamps\\n[00:00:00] Introduction\\n[00:00:48] + Harrison's background and how sports led him into ML\\n[00:04:54] Memory (for + long running chats, whether a simple Buffer, Knowledge Graph, Summary, or + Vector Store)\\nUse-Cases: compositions of Components\\nChains: combining + a PromptTemplate, LLM Model and optional OutputParser\\nwith Router, Sequential, + and Transform Chains for advanced usecases\\nsavable, sharable schemas that + can be loaded from LangChainHub\\nAgents: a chain that has access to a suite + of tools, of nondeterministic8 length because the LLM is used as a reasoning + engine to determine which actions to take and in which order.\",\"score\":0.8589554,\"raw_content\":null}],\"response_time\":1.84}" + headers: + Connection: + - keep-alive + Content-Length: + - '12187' + Content-Type: + - application/json + Date: + - Mon, 16 Sep 2024 12:24:55 GMT + Server: + - nginx + status: + code: 200 + message: OK +- request: + body: '{"max_tokens": 1024, "messages": [{"role": "user", "content": "Who is the + founder of LangChain?"}, {"role": "assistant", "content": [{"text": "To answer + this question about the founder of LangChain, I''ll need to search for current + and accurate information. Let me do that for you.", "type": "text"}, {"type": + "tool_use", "name": "search", "input": {"query": "Who is the founder of LangChain?"}, + "id": "toolu_01CCCZNHzcW8KxBnBNGf9Vjr"}]}, {"role": "user", "content": [{"type": + "tool_result", "content": "[{\"url\": \"https://pitchbook.com/profiles/company/522935-92\", + \"content\": \"LangChain was founded in 2022. Who is the founder of LangChain? + Harrison Chase and Ankush Gola are the founders of LangChain. Who is the CEO + of LangChain? Harrison Chase is the CEO of LangChain. Where is LangChain headquartered? + LangChain is headquartered in San Francisco, CA. What is the size of LangChain? + LangChain has 43 total employees ...\"}, {\"url\": \"https://aiconference.com/speakers/harrison-chase/\", + \"content\": \"Harrison Chase is the co-founder and CEO of LangChain, a company + formed around the open-source Python/Typescript packages that aim to make it + easy to develop Language Model applications. Prior to starting LangChain, he + led the ML team at Robust Intelligence (an MLOps company focused on testing + and validation of machine learning models), led the ...\"}, {\"url\": \"https://www.forbes.com/profile/harrison-chase/\", + \"content\": \"Cofounder, LangChain. Harrison Chase only cofounded LangChain + in late 2022, but the company caught instant attention for enabling anyone to + build apps powered by large language models like GPT-4 ...\"}, {\"url\": \"https://en.wikipedia.org/wiki/LangChain\", + \"content\": \"In October 2023 LangChain introduced LangServe, a deployment + tool designed to facilitate the transition from LCEL (LangChain Expression Language) + prototypes to production-ready applications.[5]\\nIntegrations[edit]\\nAs of + March 2023, LangChain included integrations with systems including Amazon, Google, + and Microsoft Azure cloud storage; API wrappers for news, movie information, + and weather; Bash for summarization, syntax and semantics checking, and execution + of shell scripts; multiple web scraping subsystems and templates; few-shot learning + prompt generation support; finding and summarizing \\\"todo\\\" tasks in code; + Google Drive documents, spreadsheets, and presentations summarization, extraction, + and creation; Google Search and Microsoft Bing web search; OpenAI, Anthropic, + and Hugging Face language models; iFixit repair guides and wikis search and + summarization; MapReduce for question answering, combining documents, and question + generation; N-gram overlap scoring; PyPDF, pdfminer, fitz, and pymupdf for PDF + file text extraction and manipulation; Python and JavaScript code generation, + analysis, and debugging; Milvus vector database[6] to store and retrieve vector + embeddings; Weaviate vector database[7] to cache embedding and data objects; + Redis cache database storage; Python RequestsWrapper and other methods for API + requests; SQL and NoSQL databases including JSON support; Streamlit, including + for logging; text mapping for k-nearest neighbors search; time zone conversion + and calendar operations; tracing and recording stack symbols in threaded and + asynchronous subprocess runs; and the Wolfram Alpha website and SDK.[8] As a + language model integration framework, LangChain''s use-cases largely overlap + with those of language models in general, including document analysis and summarization, + chatbots, and code analysis.[2]\\nHistory[edit]\\nLangChain was launched in + October 2022 as an open source project by Harrison Chase, while working at machine + learning startup Robust Intelligence. In April 2023, LangChain had incorporated + and the new startup raised over $20 million in funding at a valuation of at + least $200 million from venture firm Sequoia Capital, a week after announcing + a $10 million seed investment from Benchmark.[3][4]\\n The project quickly garnered + popularity, with improvements from hundreds of contributors on GitHub, trending + discussions on Twitter, lively activity on the project''s Discord server, many + YouTube tutorials, and meetups in San Francisco and London. As of April 2023, + it can read from more than 50 document types and data sources.[9]\\nReferences[edit]\\nExternal + links[edit]\"}, {\"url\": \"https://www.forbes.com/companies/langchain/\", \"content\": + \"LangChain. Founded in late 2022, LangChain was an instant hit in Silicon Valley + for its software that enables anyone to build apps powered by large language + models like GPT-4 in as little as two ...\"}, {\"url\": \"https://www.crunchbase.com/person/harrison-chase\", + \"content\": \"Number of Current Jobs 1. Number of Past Jobs 1. Harrison Chase + is the Co-Founder and CEO at LangChain. Additionally, Harrison Chase has had + 1 past job as the Machine Learning Engineer at Robust Intelligence. LangChain + Co-Founder and CEO Jan 2023. Organization Name.\"}, {\"url\": \"https://www.turingpost.com/p/harrison-chase-langchain-ai-agents\", + \"content\": \"Harrison Chase, founder of LangChain, shared insights on the + evolution of AI agents and their applications during Sequoia Capital''s AI Ascent. + ... Saves you a lot of research time, plus gives a flashback to ML history and + insights into the future. Stay ahead alongside over 65,000 professionals from + top AI labs, ML startups, and enterprises ...\"}, {\"url\": \"https://www.ibm.com/topics/langchain\", + \"content\": \"Applications made with LangChain provide great utility for a + variety of use cases, from straightforward question-answering and text generation + tasks to more complex solutions that use an LLM as a \u201creasoning engine.\u201d\\nTrain, + validate, tune and deploy generative AI, foundation models and machine learning + capabilities with ease and build AI applications in a fraction of the time with + a fraction of the data.\\n When building a chain for an agent, inputs include:\\nDespite + their heralded power and versatility, LLMs have important limitations: namely, + a lack of up-to-date information, a lack of domain-specific expertise and a + general difficulty with math.\\nLangChain tools\u00a0(link resides outside ibm.com) + are a set of functions that empower LangChain agents to interact with real-world + information in order to expand or improve the services it can provide. Launched + by Harrison Chase in October 2022, LangChain enjoyed a meteoric rise to prominence: + as of June 2023, it was the single fastest-growing open source project on Github.1 + Coinciding with the momentous launch of OpenAI\u2019s ChatGPT the following + month, LangChain has played a significant role in making generative AI more + accessible to enthusiasts in the wake of its widespread popularity.\\n Reimagine + how you work with\u00a0AI: our diverse, global team of more than 20,000 AI\u00a0experts + can help you quickly and confidently\u00a0design and scale AI and automation + across your\u00a0business, working across our own IBM\u00a0watsonx\u00a0technology\u00a0and + an open ecosystem of partners to deliver any\u00a0AI model, on any cloud, guided + by ethics and trust.\\n While it\u2019s the GPT model that interprets the user\u2019s + input and composes a natural language response, it\u2019s the application that + (among other things) provides an interface for the user to type and read and + a UX design that governs the chatbot experience.\"}, {\"url\": \"https://www.basedash.com/blog/langchains-origin-story\", + \"content\": \"USER CRM\\nADMIN PANEL\\nSQL COMPOSER WITH AI\\nRelated posts\\nRelated + posts\\nRelated posts\\nMy 9 core Mac apps and utilities\\nTom Johnson\\nHow + Supabase became this generation\u2019s database\\nMax Musing\\nReport: The 2023 + State of Databases\\nMax Musing\\nBasedash on the main stage at Collision 2023\\nMax + Musing\\nBasedash raises $4.5M led by Matrix\\nMax Musing\\n6 Retool Alternatives + for 2023 - A Comprehensive Guide\\nJordan Chavis\\nSOC IIType 2 Certified\\nCompany\\nAbout\\nCareers\\nTerms + of service\\nPrivacy policy\\nContact us\\nBlog\\nBrand\\nSlack community\\nSitemap\\nProduct\\nPricing\\nIntegrations\\nFeedback\\nChangelog\\nDocs\\nDownload + app\\nStatus\\nFeatures\\nViews\\nQueries\\nActions\\nSecurity\\nPower features\\n\u00a9 + 2023 BaseDash Inc.\\nProudly carbon-neutral.\\n SOC IIType 2 Certified\\nCompany\\nAbout\\nCareers\\nTerms + of service\\nPrivacy policy\\nContact us\\nBlog\\nBrand\\nSlack community\\nSitemap\\nProduct\\nPricing\\nIntegrations\\nFeedback\\nChangelog\\nDocs\\nDownload + app\\nStatus\\nFeatures\\nViews\\nQueries\\nActions\\nSecurity\\nPower features\\n\u00a9 + 2023 BaseDash Inc.\\nProudly carbon-neutral.\\n SOC IIType 2 Certified\\nCompany\\nAbout\\nCareers\\nTerms + of service\\nPrivacy policy\\nContact us\\nBlog\\nBrand\\nSlack community\\nSitemap\\nProduct\\nPricing\\nIntegrations\\nFeedback\\nChangelog\\nDocs\\nDownload + app\\nStatus\\nFeatures\\nViews\\nQueries\\nActions\\nSecurity\\nPower features\\n\u00a9 + 2023 BaseDash Inc.\\nProudly carbon-neutral. About\\nFeatures\\nPricing\\nChangelog\\nBlog\\nDocs\\nLog + in\\nSign up\\nAbout\\nFeatures\\nPricing\\nLog in\\nSign up\\nLog in\\nSign + up\\nLangChain''s origin story\\nMax Musing\\nFounder\\nThe admin panel that + you''ll actually want to use. To do this, the LangSmith product allows developers + to see the inputs and outputs at each step of a model run and the exact sequence + of runs (debug), write tests to check if the response was intended behavior + (test), collect input/output examples to further refine the model (evaluate), + and log latency, token usage, and feedback (monitor).\\n\"}, {\"url\": \"https://www.latent.space/p/langchain\", + \"content\": \"And so you can do a lot of things like reflection and kind of + like making sure that you''re on the right track and really put more safeguards + and thinking about these agents as opposed to relying on like chas and interface, + like the bot we have that''s on GitHub answering questions on the issues, I + think probably gives better answers than the bots that we have that are on chat + on the website. [00:50:32]\\nHarrison: And then between kind of like allowing + for, I think one helpful thing that we did in terms of like distinguishing between + basically the base interfaces and then more complex stuff is part of the separation + around the docs is there''s like the components piece, which has the model IO, + the retrieval, the agents, the callbacks, things like that. And then like, I + know a lot of people are doing this, but like a personal assistant for like + managing like email calendar, basic stuff, which I think is, I think that''s + like a fantastic application for these like agent like things, because if you + think about personal assistants today, you usually interact, I don''t have one, + but I''m told you interact with them over email. Show Notes\\nLangChain\\nLangChain\u2019s + Berkshire Hathaway Homepage\\nAbstractions tweet\\nLangSmith\\nLangSmith Cookbooks + repo\\nLangChain Retrieval blog\\nEvaluating CSV Question/Answering blog and + YouTube\\nMultiOn Partner blog\\nHarvard Sports Analytics Collective\\nEvaluating + RAG Webinar\\nawesome-langchain:\\nLLM Math Chain\\nSelf-Ask\\nLangChain Hub + UI\\n\u201cLangChain is Pointless\u201d\\nHarrison\u2019s links\\nsports - estimating + player compatibility in the NBA\\nearly interest in prompt injections\\nGitHub\\nTwitter\\nTimestamps\\n[00:00:00] + Introduction\\n[00:00:48] Harrison''s background and how sports led him into + ML\\n[00:04:54] Memory (for long running chats, whether a simple Buffer, Knowledge + Graph, Summary, or Vector Store)\\nUse-Cases: compositions of Components\\nChains: + combining a PromptTemplate, LLM Model and optional OutputParser\\nwith Router, + Sequential, and Transform Chains for advanced usecases\\nsavable, sharable schemas + that can be loaded from LangChainHub\\nAgents: a chain that has access to a + suite of tools, of nondeterministic8 length because the LLM is used as a reasoning + engine to determine which actions to take and in which order.\"}]", "tool_use_id": + "toolu_01CCCZNHzcW8KxBnBNGf9Vjr", "is_error": false}]}], "model": "claude-3-5-sonnet-20240620", + "system": "You are a helpful AI assistant.\n\nSystem time: 2024-09-16T12:24:37.857496+00:00", + "tools": [{"name": "scrape_webpage", "description": "Scrape the given webpage + and return a summary of text based on the instructions.", "input_schema": {"type": + "object", "properties": {"url": {"description": "The URL of the webpage to scrape.", + "type": "string"}, "instructions": {"description": "The instructions to give + to the scraper. An LLM will be used to respond using the instructions and the + scraped text.", "type": "string"}, "config": {"type": "object", "properties": + {"tags": {"type": "array", "items": {"type": "string"}}, "metadata": {"type": + "object"}, "callbacks": {"anyOf": [{"type": "array", "items": {}}, {}]}, "run_name": + {"type": "string"}, "max_concurrency": {"type": "integer"}, "recursion_limit": + {"type": "integer"}, "configurable": {"type": "object"}, "run_id": {"type": + "string", "format": "uuid"}}}}, "required": ["url", "instructions", "config"]}}, + {"name": "search", "description": "Search for general web results. This function + performs a search using the Tavily search engine, which is designed\nto provide + comprehensive, accurate, and trusted results. It''s particularly useful\nfor + answering questions about current events.", "input_schema": {"type": "object", + "properties": {"query": {"type": "string"}}, "required": ["query"]}}]}' + headers: {} + method: POST + uri: https://api.anthropic.com/v1/messages + response: + body: + string: !!binary | + H4sIAAAAAAAAA2xVUW/cNgz+K4SefYfLJe0KvyXB2gZI0K5r97B1CHgybWsnk65EXeoF+e+D5Lv0 + bs2TIZv6+PEjP/rRuMbUZojd/ersD/r8Z+ovRLrfvuy+NP9+f3M59IOpjE4j5SiKETsylQni8wuM + 0UVFVlOZQRrypjbWY2pocb54tYjCTLpYr9YXq9frlamMFVZiNfVfjwdQpe/5ennU5gojNSAM2hNE + wmB7CBST11jBDVhkGIPsXEMwSYIHpz04biUMqE4YcCNJy+VWEjcUQFq4Re6ue3Rcf+Wv/HyCB4z7 + sAY2E7zHEFwUhuseI4Fj+GBVNhRgvVqvl/CeAgEGgigDwZYmGMWxxheSIjflbGUYkaeS92wJb+fP + 9U+p4j56cQxw/euHE/bLjLJewvVzWA2/ZypRUrAUAX0UGIiLEpe8TbGHd+IRMAIeoVegvaSuf4HG + IIGywoNjYvUTtISaAjVZjszxROwdOo8bT4XZ+b4+xx00qFTDqdIeE9t+RjoWtrBjkJF4MVeSCfxD + VgvsxRKu0G67kLFruKI2U4yKQXOm5xzV/6vxNPfgDm3vmOCWMHC+ooQDoMIn2aSocMNK3ruO2FKV + mdzdfhjjoXXQik2HmaRYcubm7NC7ZpZBWhj2OfwhR3FDLAW8yh2bsbogD9ofC/MtObv1E3TomBoY + ZUweg9PpoPflTUnX0I68jBQyryGx02kJVxNcjsH5LON5dTxw0GPW2UoYJaBSU0ACulxJdB271llk + hXZuWCH6egkfUxglnrQO3RBBBQbcEjgFwjjl855RiUzYEdzlkgHH0TtbhIlLuNGDXfMEtgEHepCw + hVYCbJLzZViOr8AoDxRmP3oMHYE/4M+SgndbgncfPy8uCulflvCJrHTs8v2fnJXL/lFLjzuCQJbc + LkuiuvfKXmslm7dJk6KGqZqXywyzoUz02Atj2vwgXTi9lbChWErrXYRS536RjR4122Z5un96jLAh + my2MwKLZSjl2onDU/r3Q2dcQR8xDOmtaZlnEx1Lls7h5l6ACcYF7HpzSRBsIlU4VTzEDvSx2WQfU + ts66sg6W5unvykSV8T4QRmFTG+LmXlNgs/8Q6VvKXjI1J+8rk8o/o340jsek9ypb4mjq8zers8pI + 0pOXZxdPT/8BAAD//wMA8UBANZQGAAA= + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 8c40d61569facfc0-SJC + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Mon, 16 Sep 2024 12:25:03 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + X-Robots-Tag: + - none + anthropic-ratelimit-requests-limit: + - '4000' + anthropic-ratelimit-requests-remaining: + - '3999' + anthropic-ratelimit-requests-reset: + - '2024-09-16T12:25:54Z' + anthropic-ratelimit-tokens-limit: + - '400000' + anthropic-ratelimit-tokens-remaining: + - '400000' + anthropic-ratelimit-tokens-reset: + - '2024-09-16T12:25:03Z' + request-id: + - req_018pAJZyzb11i66uT7AZPk7R + via: + - 1.1 google + x-cloud-trace-context: + - c2803397a8cc610b16de02a6c63f2dfe + status: + code: 200 + message: OK +version: 1