id stringlengths 14 15 | text stringlengths 30 2.4k | source stringlengths 48 124 |
|---|---|---|
059fb22a99c0-0 | Interacting with APIs | 🦜�🔗 Langchain
Skip to main content🦜�🔗 LangChainDocsUse casesIntegrationsAPILangSmithJS/TS DocsCTRLKUse casesQA and Chat over DocumentsAnalyzing structured dataExtractionInteracting with APIsChatbotsSummarizationCode UnderstandingAgent simulationsAgentsAutonomous (long-runnin... | https://python.langchain.com/docs/use_cases/apis |
a50eaf0b53a0-0 | Analyzing structured data | 🦜�🔗 Langchain | https://python.langchain.com/docs/use_cases/tabular |
a50eaf0b53a0-1 | Skip to main content🦜�🔗 LangChainDocsUse casesIntegrationsAPILangSmithJS/TS DocsCTRLKUse casesQA and Chat over DocumentsAnalyzing structured dataExtractionInteracting with APIsChatbotsSummarizationCode UnderstandingAgent simulationsAgentsAutonomous (long-running) agentsMulti-modalUse casesAnalyzing structured d... | https://python.langchain.com/docs/use_cases/tabular |
a50eaf0b53a0-2 | which allows you to use them on larger databases and more complex schemas. SQL AgentPandas AgentCSV AgentPreviousQuestion answering over a group chat messages using Activeloop's DeepLakeNextExtractionDocument loadingQueryingChainsAgentsCommunityDiscordTwitterGitHubPythonJS/TSMoreHomepageBlogCopyright © 2023 LangChain,... | https://python.langchain.com/docs/use_cases/tabular |
83a1a206232c-0 | QA and Chat over Documents | 🦜�🔗 Langchain | https://python.langchain.com/docs/use_cases/question_answering/ |
83a1a206232c-1 | Skip to main content🦜�🔗 LangChainDocsUse casesIntegrationsAPILangSmithJS/TS DocsCTRLKUse casesQA and Chat over DocumentsContext aware text splitting and QA / ChatRunning LLMs locallyQuestion answering over a group chat messages using Activeloop's DeepLakeAnalyzing structured dataExtractionInteracting with APIsC... | https://python.langchain.com/docs/use_cases/question_answering/ |
83a1a206232c-2 | lines of code.Set environment variables and get packages:pip install openaipip install chromadbexport OPENAI_API_KEY="..."Run:from langchain.document_loaders import WebBaseLoaderfrom langchain.indexes import VectorstoreIndexCreator# Document loaderloader = WebBaseLoader("https://lilianweng.github.io/posts/2023-06-23-ag... | https://python.langchain.com/docs/use_cases/question_answering/ |
83a1a206232c-3 | are the three pieces together:1.2 Going Deeper​1.2.1 Integrations​Document LoadersBrowse the > 120 data loader integrations here.See further documentation on loaders here.Document TransformersAll can ingest loaded Documents and process them (e.g., split).See further documentation on transformers here.VectorstoresBr... | https://python.langchain.com/docs/use_cases/question_answering/ |
83a1a206232c-4 | loggingfrom langchain.chat_models import ChatOpenAIfrom langchain.retrievers.multi_query import MultiQueryRetrieverlogging.basicConfig()logging.getLogger('langchain.retrievers.multi_query').setLevel(logging.INFO)retriever_from_llm = MultiQueryRetriever.from_llm(retriever=vectorstore.as_retriever(), ... | https://python.langchain.com/docs/use_cases/question_answering/ |
83a1a206232c-5 | "Steps for XYZ" and asked to list the subgoals for achieving XYZ.\n\n2. Task-specific instructions: In this approach, task-specific instructions are provided to the agent to guide the decomposition process. For example, if the task is to write a novel, the agent can be instructed to "Write a story outline" as a subgoal... | https://python.langchain.com/docs/use_cases/question_answering/ |
83a1a206232c-6 | such as "Steps for XYZ.\\n1.", (2) using task-specific instructions, and (3) with human inputs.'}3.2.2 Customizing the prompt​The prompt in RetrievalQA chain can be easily customized.# Build promptfrom langchain.prompts import PromptTemplatetemplate = """Use the following pieces of context to answer the question at t... | https://python.langchain.com/docs/use_cases/question_answering/ |
83a1a206232c-7 | documents used for answer distillation can be returned using return_source_documents=True.from langchain.chains import RetrievalQAqa_chain = RetrievalQA.from_chain_type(llm,retriever=vectorstore.as_retriever(), return_source_documents=True)result = qa_chain({"query": question})prin... | https://python.langchain.com/docs/use_cases/question_answering/ |
83a1a206232c-8 | = qa_chain({"question": question})result{'question': 'What are the approaches to Task Decomposition?', 'answer': 'The approaches to Task Decomposition include (1) using LLM with simple prompting, (2) using task-specific instructions, and (3) incorporating human inputs.\n', 'sources': 'https://lilianweng.github.io/posts... | https://python.langchain.com/docs/use_cases/question_answering/ |
83a1a206232c-9 | question})In summary, the user can choose the desired level of abstraction for QA:4. Chat​4.1 Getting started​To keep chat history, first specify a Memory buffer to track the conversation inputs / outputs.from langchain.memory import ConversationBufferMemorymemory = ConversationBufferMemory(memory_key="chat_history... | https://python.langchain.com/docs/use_cases/question_answering/ |
83a1a206232c-10 | by showing two-shot examples to the Learning Language Model (LLM). Each example consists of a failed trajectory and an ideal reflection that guides future changes in the agent's plan. These reflections are then added to the agent's working memory, up to a maximum of three, to be used as context for querying the LLM. Th... | https://python.langchain.com/docs/use_cases/question_answering/ |
3e1fce09fdb1-0 | Question answering over a group chat messages using Activeloop's DeepLake | 🦜�🔗 Langchain | https://python.langchain.com/docs/use_cases/question_answering/semantic-search-over-chat |
3e1fce09fdb1-1 | Skip to main content🦜�🔗 LangChainDocsUse casesIntegrationsAPILangSmithJS/TS DocsCTRLKUse casesQA and Chat over DocumentsContext aware text splitting and QA / ChatRunning LLMs locallyQuestion answering over a group chat messages using Activeloop's DeepLakeAnalyzing structured dataExtractionInteracting with APIsC... | https://python.langchain.com/docs/use_cases/question_answering/semantic-search-over-chat |
3e1fce09fdb1-2 | = OpenAIEmbeddings()dataset_path = "hub://" + org_id + "/data"2. Create sample data​You can generate a sample group chat conversation using ChatGPT with this prompt:Generate a group chat conversation with three friends talking about their day, referencing real places and fictional names. Make it funny and as detailed... | https://python.langchain.com/docs/use_cases/question_answering/semantic-search-over-chat |
3e1fce09fdb1-3 | as f:# state_of_the_union = f.read()# text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)# pages = text_splitter.split_text(state_of_the_union)# text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)# texts = text_splitter.create_documents(pages)# print(texts)# datase... | https://python.langchain.com/docs/use_cases/question_answering/semantic-search-over-chat |
378e5d7b06d6-0 | Context aware text splitting and QA / Chat | 🦜�🔗 Langchain | https://python.langchain.com/docs/use_cases/question_answering/document-context-aware-QA |
378e5d7b06d6-1 | Skip to main content🦜�🔗 LangChainDocsUse casesIntegrationsAPILangSmithJS/TS DocsCTRLKUse casesQA and Chat over DocumentsContext aware text splitting and QA / ChatRunning LLMs locallyQuestion answering over a group chat messages using Activeloop's DeepLakeAnalyzing structured dataExtractionInteracting with APIsC... | https://python.langchain.com/docs/use_cases/question_answering/document-context-aware-QA |
378e5d7b06d6-2 | = markdown_splitter.split_text(md_file)Now, perform text splitting on the header grouped documents. # Define our text splitterfrom langchain.text_splitter import RecursiveCharacterTextSplitterchunk_size = 500chunk_overlap = 0text_splitter = RecursiveCharacterTextSplitter( chunk_size=chunk_size, chunk_overlap=chunk_o... | https://python.langchain.com/docs/use_cases/question_answering/document-context-aware-QA |
378e5d7b06d6-3 | the document") query='Introduction' filter=Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='Section', value='Introduction') limit=None [Document(page_content='', metadata={'Section': 'Introduction'}), ... | https://python.langchain.com/docs/use_cases/question_answering/document-context-aware-QA |
378e5d7b06d6-4 | then synthesize them into an answer. There many ways to approach this. For example, we recently [discussed](https://blog.langchain.dev/auto-evaluation-of-anthropic-100k-context-window/) the Retriever-Less option (at bottom in the below diagram), highlighting the Anthropic 100k context window model. Metadata filtering i... | https://python.langchain.com/docs/use_cases/question_answering/document-context-aware-QA |
378e5d7b06d6-5 | query: "prompt injection"', metadata={'Section': 'Testing'}), Document(page_content='Below, we can see detailed results from the app: \n- Kor extraction is above to perform the transformation between query and metadata format ✅\n- Self-querying attempts to filter using the episode ID (`252`) in the query and fai... | https://python.langchain.com/docs/use_cases/question_answering/document-context-aware-QA |
378e5d7b06d6-6 | metadata format, but failed to filter using the episode ID in the query. The baseline model returned documents from three different episodes, which confused the answer. The `SelfQueryRetriever` component was deemed to work well in many cases and will be used in retrieval.'PreviousQA and Chat over DocumentsNextRunning L... | https://python.langchain.com/docs/use_cases/question_answering/document-context-aware-QA |
15100381c040-0 | Running LLMs locally | 🦜�🔗 Langchain | https://python.langchain.com/docs/use_cases/question_answering/local_retrieval_qa |
15100381c040-1 | Skip to main content🦜�🔗 LangChainDocsUse casesIntegrationsAPILangSmithJS/TS DocsCTRLKUse casesQA and Chat over DocumentsContext aware text splitting and QA / ChatRunning LLMs locallyQuestion answering over a group chat messages using Activeloop's DeepLakeAnalyzing structured dataExtractionInteracting with APIsC... | https://python.langchain.com/docs/use_cases/question_answering/local_retrieval_qa |
15100381c040-2 | embedding=GPT4AllEmbeddings()) Found model file at /Users/rlm/.cache/gpt4all/ggml-all-MiniLM-L6-v2-f16.binTest similarity search is working with our local embeddings.question = "What are the approaches to Task Decomposition?"docs = vectorstore.similarity_search(question)len(docs) 4docs[0] Document(page_conten... | https://python.langchain.com/docs/use_cases/question_answering/local_retrieval_qa |
15100381c040-3 | enviorment that you created (miniforge3).E.g., for me:conda activate /Users/rlm/miniforge3/envs/llamaWith this confirmed:CMAKE_ARGS="-DLLAMA_METAL=on" FORCE_CMAKE=1 pip install -U llama-cpp-python --no-cache-dirfrom langchain.llms import LlamaCppfrom langchain.callbacks.manager import CallbackManagerfrom langchain.call... | https://python.langchain.com/docs/use_cases/question_answering/local_retrieval_qa |
15100381c040-4 | llama_model_load_internal: n_embd = 5120 llama_model_load_internal: n_mult = 256 llama_model_load_internal: n_head = 40 llama_model_load_internal: n_layer = 40 llama_model_load_internal: n_rot = 128 llama_model_load_internal: freq_base = 10000.0 llama_model_load_internal: freq_sca... | https://python.langchain.com/docs/use_cases/question_answering/local_retrieval_qa |
15100381c040-5 | 0x76add5090 ggml_metal_init: loaded kernel_mul_row 0x76addae00 ggml_metal_init: loaded kernel_scale 0x76adb2940 ggml_metal_init: loaded kernel_silu 0x76adb8610 ggml_metal_init: loaded kernel_relu 0x76addb700 ... | https://python.langchain.com/docs/use_cases/question_answering/local_retrieval_qa |
15100381c040-6 | 0x295f165e0 ggml_metal_init: loaded kernel_get_rows_q4_1 0x295f16840 ggml_metal_init: loaded kernel_get_rows_q2_K 0x295f16aa0 ggml_metal_init: loaded kernel_get_rows_q3_K 0x295f16d00 ggml_metal_init: loaded kernel_get_rows_q4_K 0x295f16f60 ... | https://python.langchain.com/docs/use_cases/question_answering/local_retrieval_qa |
15100381c040-7 | 0x295f17b40 ggml_metal_init: loaded kernel_mul_mat_q4_0_f32 0x295f17da0 ggml_metal_init: loaded kernel_mul_mat_q4_1_f32 0x295f18000 ggml_metal_init: loaded kernel_mul_mat_q2_K_f32 0x7962b9900 ggml_metal_init: loaded kernel_mul_mat_q3_K_f32 0x7962bf5f0 ... | https://python.langchain.com/docs/use_cases/question_answering/local_retrieval_qa |
15100381c040-8 | 0x7962c30b0 ggml_metal_init: loaded kernel_cpy_f32_f16 0x7962c15b0 ggml_metal_init: loaded kernel_cpy_f32_f32 0x7962beb10 ggml_metal_init: loaded kernel_cpy_f16_f16 0x7962bf060 ggml_metal_init: recommendedMaxWorkingSetSize = 21845.34 MB ggml_metal_... | https://python.langchain.com/docs/use_cases/question_answering/local_retrieval_qa |
15100381c040-9 | ' buffer, size = 1602.00 MB, (38480.94 / 21845.34), warning: current allocated size is greater than the recommended max working set size ggml_metal_add_buffer: allocated 'scr0 ' buffer, size = 298.00 MB, (38778.94 / 21845.34), warning: current allocated size is greater than the recommended max working ... | https://python.langchain.com/docs/use_cases/question_answering/local_retrieval_qa |
15100381c040-10 | Stephen Colbert: (smirking) Oh, you think you can take me down, John? You're just a Brit with a funny accent, and I'm the king of comedy! John Oliver: (grinning) Oh, you think you're tough, Stephen? You're just a has-been from South Carolina, and I'm the future of comedy! The battle begins, with each comedian del... | https://python.langchain.com/docs/use_cases/question_answering/local_retrieval_qa |
15100381c040-11 | total time = 9000.62 ms "\nSetting: The Late Show with Stephen Colbert. The studio audience is filled with fans of both comedians, and the energy is electric. The two comedians are seated at a table, ready to begin their epic rap battle.\n\nStephen Colbert: (smirking) Oh, you think you can take me down, John? You'r... | https://python.langchain.com/docs/use_cases/question_answering/local_retrieval_qa |
15100381c040-12 | max_tokens=2048,) Found model file at /Users/rlm/Desktop/Code/gpt4all/models/nous-hermes-13b.ggmlv3.q4_0.bin objc[47842]: Class GGMLMetalClass is implemented in both /Users/rlm/anaconda3/envs/lcn2/lib/python3.9/site-packages/gpt4all/llmodel_DO_NOT_MODIFY/build/libreplit-mainline-metal.dylib (0x29f48c208) and /Us... | https://python.langchain.com/docs/use_cases/question_answering/local_retrieval_qa |
15100381c040-13 | = 2 (mostly Q4_0) llama_model_load_internal: n_ff = 13824 llama_model_load_internal: n_parts = 1 llama_model_load_internal: model size = 13B llama_model_load_internal: ggml ctx size = 0.09 MB llama_model_load_internal: mem required = 9031.71 MB (+ 1608.00 MB per state) llama_new_context_w... | https://python.langchain.com/docs/use_cases/question_answering/local_retrieval_qa |
15100381c040-14 | ggml_metal_init: loaded kernel_silu 0x115fcd960 ggml_metal_init: loaded kernel_relu 0x115fcfd50 ggml_metal_init: loaded kernel_gelu 0x115fd03c0 ggml_metal_init: loaded kernel_soft_max 0x115fcf640 ggml_metal_i... | https://python.langchain.com/docs/use_cases/question_answering/local_retrieval_qa |
15100381c040-15 | 0x1147aef50 ggml_metal_init: loaded kernel_get_rows_q3_k 0x1147af1b0 ggml_metal_init: loaded kernel_get_rows_q4_k 0x1147af410 ggml_metal_init: loaded kernel_get_rows_q5_k 0x1147affa0 ggml_metal_init: loaded kernel_get_rows_q6_k 0x1147b0200 ... | https://python.langchain.com/docs/use_cases/question_answering/local_retrieval_qa |
15100381c040-16 | 0x1147c06f0 ggml_metal_init: loaded kernel_mul_mat_q2_k_f32 0x1147c0950 ggml_metal_init: loaded kernel_mul_mat_q3_k_f32 0x1147c0bb0 ggml_metal_init: loaded kernel_mul_mat_q4_k_f32 0x1147c0e10 ggml_metal_init: loaded kernel_mul_mat_q5_k_f32 0x1147c1070 ... | https://python.langchain.com/docs/use_cases/question_answering/local_retrieval_qa |
15100381c040-17 | 0x115fd1c60 ggml_metal_init: loaded kernel_cpy_f16_f16 0x115fd2d40 ggml_metal_init: recommendedMaxWorkingSetSize = 21845.34 MB ggml_metal_init: hasUnifiedMemory = true ggml_metal_init: maxTransferRate = built-in GPU ggml_metal_add_buffer: allocated 'data ... | https://python.langchain.com/docs/use_cases/question_answering/local_retrieval_qa |
15100381c040-18 | / 21845.34)LLMChain​Run an LLMChain (see here) with either model by passing in the retrieved docs and a simple prompt.It formats the prompt template using the input key values provided and passes the formatted string to GPT4All, LLama-V2, or another specified LLM.In this case, the list of retrieved documents (docs) a... | https://python.langchain.com/docs/use_cases/question_answering/local_retrieval_qa |
15100381c040-19 | llama_print_timings: load time = 1191.88 ms llama_print_timings: sample time = 134.47 ms / 193 runs ( 0.70 ms per token, 1435.25 tokens per second) llama_print_timings: prompt eval time = 39470.18 ms / 1055 tokens ( 37.41 ms per token, 26.73 tokens per second) llama_print_timings: ... | https://python.langchain.com/docs/use_cases/question_answering/local_retrieval_qa |
15100381c040-20 | autonomous agent systems.'QA Chain​We can use a QA chain to handle our question above.chain_type="stuff" (see here) means that all the docs will be added (stuffed) into a prompt.from langchain.chains.question_answering import load_qa_chain# Prompttemplate = """Use the following pieces of context to answer the questio... | https://python.langchain.com/docs/use_cases/question_answering/local_retrieval_qa |
15100381c040-21 | tokens per second) llama_print_timings: prompt eval time = 8014.11 ms / 267 tokens ( 30.02 ms per token, 33.32 tokens per second) llama_print_timings: eval time = 2908.17 ms / 84 runs ( 34.62 ms per token, 28.88 tokens per second) llama_print_timings: total time = 11096.23 ms ... | https://python.langchain.com/docs/use_cases/question_answering/local_retrieval_qa |
15100381c040-22 | load time = 1191.88 ms llama_print_timings: sample time = 22.78 ms / 31 runs ( 0.73 ms per token, 1360.66 tokens per second) llama_print_timings: prompt eval time = 0.00 ms / 1 tokens ( 0.00 ms per token, inf tokens per second) llama_print_timings: eval time = 1320.23 ... | https://python.langchain.com/docs/use_cases/question_answering/local_retrieval_qa |
52a29af09995-0 | Page Not Found | 🦜�🔗 Langchain
Skip to main content🦜�🔗 LangChainDocsUse casesIntegrationsAPILangSmithJS/TS DocsCTRLKPage Not FoundWe could not find what you were looking for.Please contact the owner of the site that linked you to the original URL and let them know their link is broken.CommunityDisc... | https://python.langchain.com/docs/use_cases/question_answering/(https://python.langchain.com/docs/integrations/llms/gpt4all) |
617da6df39a0-0 | Chatbots | 🦜�🔗 Langchain
Skip to main content🦜�🔗 LangChainDocsUse casesIntegrationsAPILangSmithJS/TS DocsCTRLKUse casesQA and Chat over DocumentsAnalyzing structured dataExtractionInteracting with APIsChatbotsVoice AssistantSummarizationCode UnderstandingAgent simulationsAgentsAutonomous (long-runn... | https://python.langchain.com/docs/use_cases/chatbots/ |
c81e577b4642-0 | Page Not Found | 🦜�🔗 Langchain
Skip to main content🦜�🔗 LangChainDocsUse casesIntegrationsAPILangSmithJS/TS DocsCTRLKPage Not FoundWe could not find what you were looking for.Please contact the owner of the site that linked you to the original URL and let them know their link is broken.CommunityDisc... | https://python.langchain.com/docs/use_cases/chatbots/voice_assistant.html |
12d65597711a-0 | Voice Assistant | 🦜�🔗 Langchain | https://python.langchain.com/docs/use_cases/chatbots/voice_assistant |
12d65597711a-1 | Skip to main content🦜�🔗 LangChainDocsUse casesIntegrationsAPILangSmithJS/TS DocsCTRLKUse casesQA and Chat over DocumentsAnalyzing structured dataExtractionInteracting with APIsChatbotsVoice AssistantSummarizationCode UnderstandingAgent simulationsAgentsAutonomous (long-running) agentsMulti-modalUse casesChatbot... | https://python.langchain.com/docs/use_cases/chatbots/voice_assistant |
12d65597711a-2 | It uses the pyttsx3 and speech_recognition libraries to convert text to speech and speech to text respectively. The prompt template is also changed to make it more suitable for voice assistant use.from langchain import OpenAI, LLMChain, PromptTemplatefrom langchain.memory import ConversationBufferWindowMemorytemplate =... | https://python.langchain.com/docs/use_cases/chatbots/voice_assistant |
12d65597711a-3 | "human_input"], template=template)chatgpt_chain = LLMChain( llm=OpenAI(temperature=0), prompt=prompt, verbose=True, memory=ConversationBufferWindowMemory(k=2),)import speech_recognition as srimport pyttsx3engine = pyttsx3.init()def listen(): r = sr.Recognizer() with sr.Microphone() as source: p... | https://python.langchain.com/docs/use_cases/chatbots/voice_assistant |
12d65597711a-4 | audio, model="medium.en", show_dict=True, )["text"] except Exception as e: unrecognized_speech_text = ( f"Sorry, I didn't catch that. Exception was: {e}s" ) text = unrecognized_speech_text ... | https://python.langchain.com/docs/use_cases/chatbots/voice_assistant |
12d65597711a-5 | .autonotebook import tqdm as notebook_tqdm Hello, Assistant. What's going on? > Entering new LLMChain chain... Prompt after formatting: Assistant is a large language model trained by OpenAI. Assistant is designed to be able to assist with a wide range of tasks, from answering simple question... | https://python.langchain.com/docs/use_cases/chatbots/voice_assistant |
12d65597711a-6 | Human: Hello, Assistant. What's going on? Assistant: > Finished chain. Hi there! It's great to hear from you. I'm doing well. How can I help you today? listening now... Recognizing... That's cool. Isn't that neat? Yeah, I'm doing great. > Entering new LLMChain chain... Prompt afte... | https://python.langchain.com/docs/use_cases/chatbots/voice_assistant |
12d65597711a-7 | from audio and as such there may be some errors in the transcription. It will attempt to account for some words being swapped with similar-sounding words or phrases. Assistant will also keep responses concise, because human attention spans are more limited over the audio channel since it takes time to listen to a respo... | https://python.langchain.com/docs/use_cases/chatbots/voice_assistant |
12d65597711a-8 | in discussions and provide explanations and descriptions on a wide range of topics. Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a convers... | https://python.langchain.com/docs/use_cases/chatbots/voice_assistant |
12d65597711a-9 | to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand. Assis... | https://python.langchain.com/docs/use_cases/chatbots/voice_assistant |
12d65597711a-10 | > Finished chain. Sure! Neural networks are a type of artificial intelligence that use a network of interconnected nodes to process data and make decisions. They are used in a variety of applications, from image recognition to natural language processing. Neural networks are often used to solve complex problems tha... | https://python.langchain.com/docs/use_cases/chatbots/voice_assistant |
12d65597711a-11 | human input is being transcribed from audio and as such there may be some errors in the transcription. It will attempt to account for some words being swapped with similar-sounding words or phrases. Assistant will also keep responses concise, because human attention spans are more limited over the audio channel since i... | https://python.langchain.com/docs/use_cases/chatbots/voice_assistant |
12d65597711a-12 | to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand. Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and un... | https://python.langchain.com/docs/use_cases/chatbots/voice_assistant |
12d65597711a-13 | of interconnected nodes that process data and make decisions, just like neurons in the brain. Neural networks can learn from their mistakes and improve their performance over time, just like humans do. Human: Tell me about a brand new discovered bird species. Assistant: > Finished chain. A new species... | https://python.langchain.com/docs/use_cases/chatbots/voice_assistant |
12d65597711a-14 | Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist. Assistant is aware that... | https://python.langchain.com/docs/use_cases/chatbots/voice_assistant |
12d65597711a-15 | the forest when he stumbled upon a magical tree. The tree told Jack that if he was honest and trustworthy, he would be rewarded with a special gift. Jack was so excited, and he promised to always be honest and trustworthy. Sure enough, the tree rewarded Jack with a beautiful golden apple. From that day forward, Jack wa... | https://python.langchain.com/docs/use_cases/chatbots/voice_assistant |
12d65597711a-16 | specific question or just want to have a conversation about a particular topic, Assistant is here to assist. Assistant is aware that human input is being transcribed from audio and as such there may be some errors in the transcription. It will attempt to account for some words being swapped with similar-sounding... | https://python.langchain.com/docs/use_cases/chatbots/voice_assistant |
12d65597711a-17 | > Finished chain. Thank you! I'm glad you enjoyed it. listening now... Recognizing... Thank you. > Entering new LLMChain chain... Prompt after formatting: Assistant is a large language model trained by OpenAI. Assistant is designed to be able to assist with a wide range of tasks, f... | https://python.langchain.com/docs/use_cases/chatbots/voice_assistant |
12d65597711a-18 | the audio channel since it takes time to listen to a response. Human: Tell me a children's story about the importance of honesty and trust. AI: Once upon a time, there was a young boy named Jack who lived in a small village. Jack was always honest and trustworthy, and his friends and family knew they could ... | https://python.langchain.com/docs/use_cases/chatbots/voice_assistant |
12d65597711a-19 | range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent... | https://python.langchain.com/docs/use_cases/chatbots/voice_assistant |
12d65597711a-20 | know of online brands like Photoshop and Freq that you don't have to download in some sort of way? Assistant: > Finished chain. Yes, there are several online brands that offer photo editing and other creative tools without the need to download any software. Adobe Photoshop Express, Pixlr, and Fotor are so... | https://python.langchain.com/docs/use_cases/chatbots/voice_assistant |
12d65597711a-21 | help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist. Assistant is aware that human input is being transcribed from audio and as such there may be some errors in the transcription. It will attempt to account for some words being swapped with simi... | https://python.langchain.com/docs/use_cases/chatbots/voice_assistant |
12d65597711a-22 | model trained by OpenAI. Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing... | https://python.langchain.com/docs/use_cases/chatbots/voice_assistant |
12d65597711a-23 | there are several online brands that offer photo editing and other creative tools without the need to download any software. Adobe Photoshop Express, Pixlr, and Fotor are some of the most popular online photo editing tools. Freq is an online music production platform that allows users to create and share music without ... | https://python.langchain.com/docs/use_cases/chatbots/voice_assistant |
12d65597711a-24 | 22 print('Recognizing...') File c:\ProgramData\miniconda3\envs\lang\lib\site-packages\speech_recognition\__init__.py:523, in Recognizer.listen(self, source, timeout, phrase_time_limit, snowboy_configuration) 520 if phrase_time_limit and elapsed_time - phrase_start_time > phrase_time_limit: 521 ... | https://python.langchain.com/docs/use_cases/chatbots/voice_assistant |
12d65597711a-25 | num_frames, 571 exception_on_overflow) KeyboardInterrupt: PreviousChatbotsNextSummarizationCommunityDiscordTwitterGitHubPythonJS/TSMoreHomepageBlogCopyright © 2023 LangChain, Inc. | https://python.langchain.com/docs/use_cases/chatbots/voice_assistant |
34aab0164e16-0 | Code Understanding | 🦜�🔗 Langchain | https://python.langchain.com/docs/use_cases/code/ |
34aab0164e16-1 | Skip to main content🦜�🔗 LangChainDocsUse casesIntegrationsAPILangSmithJS/TS DocsCTRLKUse casesQA and Chat over DocumentsAnalyzing structured dataExtractionInteracting with APIsChatbotsSummarizationCode UnderstandingUse LangChain, GPT and Activeloop's Deep Lake to work with code baseAnalysis of Twitter the-algor... | https://python.langchain.com/docs/use_cases/code/ |
34aab0164e16-2 | Query Understanding: GPT-4 processes user queries, grasping the context and extracting relevant details.Construct the Retriever: Conversational RetrieverChain searches the VectorStore to identify the most relevant code snippets for a given query.Build the Conversational Chain: Customize the retriever settings and defin... | https://python.langchain.com/docs/use_cases/code/ |
5c30ab1c9a73-0 | Analysis of Twitter the-algorithm source code with LangChain, GPT4 and Activeloop's Deep Lake | 🦜�🔗 Langchain | https://python.langchain.com/docs/use_cases/code/twitter-the-algorithm-analysis-deeplake |
5c30ab1c9a73-1 | Skip to main content🦜�🔗 LangChainDocsUse casesIntegrationsAPILangSmithJS/TS DocsCTRLKUse casesQA and Chat over DocumentsAnalyzing structured dataExtractionInteracting with APIsChatbotsSummarizationCode UnderstandingUse LangChain, GPT and Activeloop's Deep Lake to work with code baseAnalysis of Twitter the-algor... | https://python.langchain.com/docs/use_cases/code/twitter-the-algorithm-analysis-deeplake |
5c30ab1c9a73-2 | in position 0: invalid start byte from tiktoken for some repositories1. Index the code base (optional)​You can directly skip this part and directly jump into using already indexed dataset. To begin with, first we will clone the repository, then parse and chunk the code base and use OpenAI indexing.git clone https://g... | https://python.langchain.com/docs/use_cases/code/twitter-the-algorithm-analysis-deeplake |
5c30ab1c9a73-3 | True} during the creation of the vector store. This configuration enables the execution of queries on the Managed Tensor Database, rather than on the client side. It should be noted that this functionality is not applicable to datasets stored locally or in-memory. In the event that a vector store has already been creat... | https://python.langchain.com/docs/use_cases/code/twitter-the-algorithm-analysis-deeplake |
5c30ab1c9a73-4 | return "scala" in metadata["source"] or "py" in metadata["source"]### turn on below for custom filtering# retriever.search_kwargs['filter'] = filterfrom langchain.chat_models import ChatOpenAIfrom langchain.chains import ConversationalRetrievalChainmodel = ChatOpenAI(model_name="gpt-3.5-turbo") # switch to 'gpt-4'qa =... | https://python.langchain.com/docs/use_cases/code/twitter-the-algorithm-analysis-deeplake |
5c30ab1c9a73-5 | chat_history.append((question, result["answer"])) print(f"-> **Question**: {question} \n") print(f"**Answer**: {result['answer']} \n")-> Question: What does favCountParams do? Answer: favCountParams is an optional ThriftLinearFeatureRankingParams instance that represents the parameters related to the "favorite co... | https://python.langchain.com/docs/use_cases/code/twitter-the-algorithm-analysis-deeplake |
5c30ab1c9a73-6 | sampling-based community detection algorithm that is run on the Producer-Producer similarity graph. This graph is created by computing the cosine similarity scores between the users who follow each producer. The algorithm identifies communities or clusters of Producers with similar followers, and takes a parameter k fo... | https://python.langchain.com/docs/use_cases/code/twitter-the-algorithm-analysis-deeplake |
5c30ab1c9a73-7 | continue to monitor its performance and impact on recommendations. Take note of any improvements or issues that arise and be prepared to iterate on the new representation if needed. Always ensure that the results and performance metrics align with the system's goals and objectives. -> Question: How much do I get booste... | https://python.langchain.com/docs/use_cases/code/twitter-the-algorithm-analysis-deeplake |
5c30ab1c9a73-8 | by looking up the author of the tweet.Search Context Features: These features represent the context of the current searcher, like their UI language, their content consumption, and the current time (implied). They are combined with Tweet Data to compute some of the features used in scoring.These inputs are then processe... | https://python.langchain.com/docs/use_cases/code/twitter-the-algorithm-analysis-deeplake |
5c30ab1c9a73-9 | of machine learning models and various features to rank the content. While the above actions may help influence the ranking, there are no guarantees as the ranking process is determined by a complex algorithm, which evolves over time. -> Question: why threads and long tweets do so well on the platform?Answer: Threads a... | https://python.langchain.com/docs/use_cases/code/twitter-the-algorithm-analysis-deeplake |
5c30ab1c9a73-10 | creators building a following that reacts to only threads?Answer: Based on the provided code and context, there isn't enough information to conclude if the creators of threads and long tweets primarily build a following that engages with only thread-based content. The code provided is focused on Twitter's recommendatio... | https://python.langchain.com/docs/use_cases/code/twitter-the-algorithm-analysis-deeplake |
5c30ab1c9a73-11 | of educational, entertaining, and promotional content to maintain variety and interest.Timing your tweets strategically to maximize engagement, likes, and bookmarks per tweet.Both strategies can overlap, and you may need to adapt your approach by understanding your target audience's preferences and analyzing your accou... | https://python.langchain.com/docs/use_cases/code/twitter-the-algorithm-analysis-deeplake |
5c30ab1c9a73-12 | is a separate category for blue verified accounts. Typically, blue verified checkmarks are used to indicate notable individuals, while verified checkmarks are for companies or organizations.PreviousUse LangChain, GPT and Activeloop's Deep Lake to work with code baseNextAgent simulations1. Index the code base (optional)... | https://python.langchain.com/docs/use_cases/code/twitter-the-algorithm-analysis-deeplake |
b4eb12d0b901-0 | Page Not Found | 🦜�🔗 Langchain
Skip to main content🦜�🔗 LangChainDocsUse casesIntegrationsAPILangSmithJS/TS DocsCTRLKPage Not FoundWe could not find what you were looking for.Please contact the owner of the site that linked you to the original URL and let them know their link is broken.CommunityDisc... | https://python.langchain.com/docs/use_cases/code/twitter-the-algorithm-analysis-deeplake.html |
4fc703b077e5-0 | Use LangChain, GPT and Activeloop's Deep Lake to work with code base | 🦜�🔗 Langchain | https://python.langchain.com/docs/use_cases/code/code-analysis-deeplake |
4fc703b077e5-1 | Skip to main content🦜�🔗 LangChainDocsUse casesIntegrationsAPILangSmithJS/TS DocsCTRLKUse casesQA and Chat over DocumentsAnalyzing structured dataExtractionInteracting with APIsChatbotsSummarizationCode UnderstandingUse LangChain, GPT and Activeloop's Deep Lake to work with code baseAnalysis of Twitter the-algor... | https://python.langchain.com/docs/use_cases/code/code-analysis-deeplake |
4fc703b077e5-2 | osfrom getpass import getpassos.environ["OPENAI_API_KEY"] = getpass()# Please manually enter OpenAI KeyAuthenticate into Deep Lake if you want to create your own dataset and publish it. You can get an API key from the platform at app.activeloop.aiactiveloop_token = getpass("Activeloop Token:")os.environ["ACTIVELOOP_TOK... | https://python.langchain.com/docs/use_cases/code/code-analysis-deeplake |
4fc703b077e5-3 | take several minutes. from langchain.embeddings.openai import OpenAIEmbeddingsembeddings = OpenAIEmbeddings()embeddingsfrom langchain.vectorstores import DeepLakedb = DeepLake.from_documents( texts, embeddings, dataset_path=f"hub://{<org_id>}/langchain-code")dbOptional: You can also use Deep Lake's Managed Tensor Da... | https://python.langchain.com/docs/use_cases/code/code-analysis-deeplake |
4fc703b077e5-4 | filter(x): # filter based on source code if "something" in x["text"].data()["value"]: return False # filter based on path e.g. extension metadata = x["metadata"].data()["value"] return "only_this" in metadata["source"] or "also_that" in metadata["source"]### turn on below for custom filtering# ret... | https://python.langchain.com/docs/use_cases/code/code-analysis-deeplake |
End of preview. Expand in Data Studio
README.md exists but content is empty.
- Downloads last month
- 11