"noAccess":"Due to insufficient permissions, this answer has excluded content that you are not authorized to view",
"source":"Reference Source",
"file":"File",
"filePrsing":"File is currently being parsed",
"sourceTooltip":"Source Paragraph",
"filterLabel":"Filter Labels",
"tooltipText":"The system generates key information tags automatically based on the answers, and you can also manually add or delete labels. The system calculates the relevance of various files and paragraphs based on these tags.",
"customLabel":"Custom",
"addCustomLabel":"+ Custom",
"sourceDocumentsLabel":"Source Documents",
"downloadPDFTooltip":"Download Dual-Layered PDF",
"downloadOriginalTooltip":"Download Original File",
"editPythonCodeDescription":"Edit your Python code here. This code snippet accepts module imports and a function definition. Make sure your function returns a string.",
"editCode":"Edit Code",
"codeReadyToRun":"Code ready to run",
"functionError":"There is an error in your function",
"importsError":"There is an error in your imports",
"exportCodeDialogTip":"Generate code to integrate the workflow into an external application (please make sure to build the skill before opening this page).",
"customSampleSizeTooltip1":"This is an optional item:",
"customSampleSizeTooltip2":"If this option is not selected, all samples of the selected personal data set and the pre-set data set will participate in training;",
"customSampleSizeTooltip3":"If this option is selected, the user can freely specify the number of samples used for training in different data sets. If the input box is empty or the number entered is greater than the total number of samples in the data set, all samples in the data set will be used for training.",
"presetDatasets":"Preset Datasets",
"download":"Download",
"sampleSize":"Sample Size",
"userDatasets":"Personal Dataset",
"gpuDesc":"The number of the graphics card used for training, and multiple cards are separated by commas, such as 0, 1, 2, and 3",
"valRatioDesc":"Verification set ratio: if the value is greater than 0, loss will be calculated on the validation set after each epoch",
"batchSizeDesc":"Batch size indicates the number of samples used in each training iteration. A larger batch size can accelerate training, but may lead to excessive memory usage;",
"learningRateDesc":"A learning rate (learning rate) is a hyperparameter used to update weights during the process of gradient descent; if it is too high, the model will be difficult to converge, while if it is too low, the model will converge slowly.",
"numEpochsDesc":"The number of iterations (epochs) controls the number of iterations in the training process; you can judge whether the model is converged according to the loss curve, if the loss is still decreasing without being stable, you can increase the epoch.",
"maxSeqLenDesc":"Specify the maximum sequence length. The default value is 8192, i.e. the input and output lengths cannot exceed 8192 or they will be truncated;",
"cpuLoadDesc":"Whether to load some parameters and optimizers into the CPU (the default is not enabled) can be turned on after opening it will occupy memory detailed data can refer to resource consumption related documentation",
"selectRTService":"Please select RT service",
"selectBaseModel":"Please select the base model",
"enterModelName":"The model name contains at least one letter and is composed of numbers, letters, and underscores.",
"rtServiceTooltip":"Select the RT service where the target benchmark model is located; Finetune will also be deployed in the same RT service after training completes.",
"finetuneModelName":"The name of the Finetune model",
"parameterConfigurationTooltip":"Parameter configuration suggestions and experimental reference data are available in the product document.",
"parameter":"Parameter",
"quantity":"Quantity",
"description":"Description",
"gpuResourceUsage":"GPU resource usage"
},
"confirmButton":"Confirm",
"add":"Add",
"back":"Back",
"create":"Create",
"delete":"Delete",
"createTime":"Creation Time",
"updateTime":"Update Time",
"success":"Saved",
"edit":"Edit",
"enable":"Enable",
"disable":"Disable",
"close":"Close",
"cancel":"Cancel",
"save":"Save",
"submit":"Submit",
"operations":"Operations",
"previousPage":"Previous Page",
"nextPage":"Next Page",
"formatError":"Format Error",
"agents":{
"AgentInitializer":{
"display_name":"AgentInitializer",
"description":"Construct a zero shot agent from an LLM and tools.",
"description_url":"",
"template":{
"input_node":{
"display_name":"Preset Question"
},
"llm":{
"display_name":"LLM"
},
"memory":{
"display_name":"memory"
},
"tools":{
"display_name":"tools"
},
"agent":{
"display_name":"agent",
"options":[
"zero-shot-react-description",
"react-docstore",
"self-ask-with-search",
"conversational-react-description",
"openai-functions",
"openai-multi-functions"
]
}
}
},
"CSVAgent":{
"display_name":"CSVAgent",
"description_url":"",
"template":{
"input_node":{
"display_name":"Preset Question"
},
"llm":{
"display_name":"LLM"
},
"path":{
"display_name":"path"
},
"format_instructions":{
"display_name":"format_instructions",
"value":"Use the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input to the action Observation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question"
},
"input_variables":{
"display_name":"input_variables",
"value":[
"df_head",
"input",
"agent_scratchpad"
]
},
"prefix":{
"display_name":"prefix",
"value":"\nYou are working with a pandas dataframe in Python. The name of the dataframe is `df`.\nYou should use the tools below to answer the question posed of you:"
},
"suffix":{
"display_name":"suffix",
"value":"\nThis is the result of `print(df.head())`:\n{df_head}\n\nBegin!\nQuestion: {input}\n{agent_scratchpad}"
}
}
},
"ChatglmFunctionsAgent":{
"display_name":"ChatglmFunctionsAgent",
"description":"Construct an agent from an LLM and tools.",
"description_url":"",
"template":{
"input_node":{
"display_name":"Preset Question"
},
"llm":{
"display_name":"LLM"
},
"tools":{
"display_name":"tools"
}
}
},
"JsonAgent":{
"display_name":"JsonAgent",
"description":"Construct a json agent from an LLM and tools.",
"description_url":"",
"template":{
"input_node":{
"display_name":"Preset Question"
},
"llm":{
"display_name":"LLM"
},
"toolkit":{
"display_name":"toolkit"
}
}
},
"LLMFunctionsAgent":{
"display_name":"LLMFunctionsAgent",
"description":"Construct an agent from an LLM and tools.",
"description_url":"",
"template":{
"input_node":{
"display_name":"Preset Question"
},
"llm":{
"display_name":"LLM"
},
"tools":{
"display_name":"tools"
}
}
},
"SQLAgent":{
"display_name":"SQLAgent",
"description":"Construct an SQL agent from an LLM and tools.",
"description_url":"",
"template":{
"input_node":{
"display_name":"Preset Question"
},
"llm":{
"display_name":"LLM"
},
"database_uri":{
"display_name":"database_uri"
},
"format_instructions":{
"display_name":"format_instructions",
"value":"Use the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question"
},
"input_variables":{
"display_name":"input_variables",
"value":[
"input",
"agent_scratchpad"
]
},
"prefix":{
"display_name":"prefix",
"value":"You are an agent designed to interact with a SQL database.\nGiven an input question, create a syntactically correct {dialect} query to run, then look at the results of the query and return the answer.\nUnless the user specifies a specific number of examples they wish to obtain, always limit your query to at most {top_k} results.\nYou can order the results by a relevant column to return the most interesting examples in the database.\nNever query for all the columns from a specific table, only ask for the relevant columns given the question.\nYou have access to tools for interacting with the database.\nOnly use the below tools. Only use the information returned by the below tools to construct your final answer.\nYou MUST double check your query before executing it. If you get an error while executing a query, rewrite the query and try again.\n\nDO NOT make any DML statements (INSERT, UPDATE, DELETE, DROP etc.) to the database.\n\nIf the question does not seem related to the database, just return 'I don't know' as the answer."
},
"suffix":{
"display_name":"suffix",
"value":"Begin!\n\nQuestion: {input}\nThought: I should look at the tables in the database to see what I can query. Then I should query the schema of the most relevant tables.\n{agent_scratchpad}"
}
}
},
"VectorStoreAgent":{
"display_name":"VectorStoreAgent",
"description":"Construct an agent from a Vector Store.",
"description_url":"",
"template":{
"input_node":{
"display_name":"Preset Question"
},
"llm":{
"display_name":"LLM"
},
"vectorstoreinfo":{
"display_name":"Vector Store Info"
}
}
},
"VectorStoreRouterAgent":{
"display_name":"VectorStoreRouterAgent",
"description":"Construct an agent from a Vector Store Router.",
"description_url":"",
"template":{
"input_node":{
"display_name":"Preset Question"
},
"llm":{
"display_name":"LLM"
},
"vectorstoreroutertoolkit":{
"display_name":"Vector Store Router Toolkit"
}
}
},
"ZeroShotAgent":{
"display_name":"ZeroShotAgent",
"description":"Construct an agent from an LLM and tools.",
"description_url":"",
"template":{
"input_node":{
"display_name":"Preset Question"
},
"llm":{
"display_name":"LLM"
},
"tools":{
"display_name":"tools"
},
"format_instructions":{
"display_name":"format_instructions",
"value":"Use the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question"
},
"input_variables":{
"display_name":"input_variables"
},
"prefix":{
"display_name":"prefix",
"value":"Answer the following questions as best you can. You have access to the following tools:"
"description":"Knowledge graph memory for storing conversation memory.",
"description_url":"",
"template":{
"chat_memory":{
"display_name":"chat_memory"
},
"llm":{
"display_name":"llm"
},
"input_key":{
"display_name":"input_key"
},
"k":{
"display_name":"Memory Size"
},
"memory_key":{
"display_name":"memory_key"
},
"output_key":{
"display_name":"output_key"
},
"return_messages":{
"display_name":"return_messages"
}
}
},
"ConversationSummaryMemory":{
"display_name":"ConversationSummaryMemory",
"description":"Conversation summarizer to memory.",
"description_url":"",
"template":{
"chat_memory":{
"display_name":"chat_memory"
},
"llm":{
"display_name":"llm"
},
"input_key":{
"display_name":"input_key"
},
"memory_key":{
"display_name":"memory_key"
},
"output_key":{
"display_name":"output_key"
},
"return_messages":{
"display_name":"return_messages"
}
}
},
"MongoDBChatMessageHistory":{
"display_name":"MongoDBChatMessageHistory",
"description":"Memory store with MongoDB",
"description_url":"",
"template":{
"collection_name":{
"display_name":"collection_name"
},
"connection_string":{
"display_name":"connection_string"
},
"database_name":{
"display_name":"database_name"
},
"session_id":{
"display_name":"session_id"
}
}
},
"PostgresChatMessageHistory":{
"display_name":"PostgresChatMessageHistory",
"description":"Memory store with Postgres",
"description_url":"",
"template":{
"connection_string":{
"display_name":"connection_string"
},
"session_id":{
"display_name":"session_id"
},
"table_name":{
"display_name":"table_name"
}
}
},
"VectorStoreRetrieverMemory":{
"display_name":"VectorStoreRetrieverMemory",
"description":"Class for a VectorStore-backed memory object.",
"description_url":"",
"template":{
"retriever":{
"display_name":"retriever"
},
"input_key":{
"display_name":"input_key"
},
"memory_key":{
"display_name":"memory_key"
},
"return_messages":{
"display_name":"return_messages"
}
}
}
},
"output_parsers":{
"ResponseSchema":{
"display_name":"ResponseSchema",
"description_url":"",
"template":{
"description":{
"display_name":"description"
},
"name":{
"display_name":"name"
},
"type":{
"display_name":"type"
}
}
},
"StructuredOutputParser":{
"display_name":"StructuredOutputParser",
"template":{
"response_schemas":{
"display_name":"response_schemas"
}
}
}
},
"prompts":{
"ChatMessagePromptTemplate":{
"display_name":"ChatMessagePromptTemplate",
"description_url":"",
"template":{
"prompt":{
"display_name":"prompt"
},
"role":{
"display_name":"role"
}
}
},
"ChatPromptTemplate":{
"display_name":"ChatPromptTemplate",
"description_url":"",
"template":{
"messages":{
"display_name":"messages"
},
"output_parser":{
"display_name":"output_parser"
}
}
},
"HumanMessagePromptTemplate":{
"display_name":"HumanMessagePromptTemplate",
"description_url":"",
"template":{
"prompt":{
"display_name":"prompt"
}
}
},
"PromptTemplate":{
"display_name":"PromptTemplate",
"description":"Schema to represent a prompt for an LLM.",
"description_url":"",
"template":{
"output_parser":{
"display_name":"output_parser"
},
"template":{
"display_name":"template"
}
}
},
"SystemMessagePromptTemplate":{
"display_name":"SystemMessagePromptTemplate",
"description_url":"",
"template":{
"prompt":{
"display_name":"prompt"
}
}
}
},
"retrievers":{
"MixEsVectorRetriever":{
"display_name":"MixEsVectorRetriever",
"description":"This class ensemble the results of es retriever and vector retriever.",
"description_url":"",
"template":{
"keyword_retriever":{
"display_name":"keyword_retriever"
},
"vector_retriever":{
"display_name":"vector_retriever"
},
"combine_strategy":{
"display_name":"combine_strategy",
"options":[
"keyword_front",
"vector_front",
"mix"
]
}
},
"output_types":[
"MixEsVectorRetriever"
]
},
"MultiQueryRetriever":{
"display_name":"MultiQueryRetriever",
"description":"Initialize from llm using default template.",
"description_url":"",
"template":{
"llm":{
"display_name":"llm"
},
"prompt":{
"display_name":"prompt"
},
"retriever":{
"display_name":"retriever"
}
},
"output_types":[
"MultiQueryRetriever"
]
}
},
"textsplitters":{
"CharacterTextSplitter":{
"display_name":"CharacterTextSplitter",
"description":"Implementation of splitting text that looks at characters.",
"description_url":"",
"template":{
"documents":{
"display_name":"documents"
},
"chunk_overlap":{
"display_name":"Chunk Overlap"
},
"chunk_size":{
"display_name":"Chunk Size"
},
"separator":{
"display_name":"separator"
}
},
"output_types":[
"Document"
]
},
"RecursiveCharacterTextSplitter":{
"display_name":"RecursiveCharacterTextSplitter",
"description":"Implementation of splitting text that looks at characters.",
"description_url":"",
"template":{
"documents":{
"display_name":"documents"
},
"chunk_overlap":{
"display_name":"Chunk Overlap"
},
"chunk_size":{
"display_name":"Chunk Size"
},
"separator_type":{
"display_name":"Separator Type"
},
"separators":{
"display_name":"Separator"
}
},
"output_types":[
"Document"
]
}
},
"toolkits":{
"JsonToolkit":{
"display_name":"JsonToolkit",
"description":"Toolkit for interacting with a JSON spec.",
"description_url":"",
"template":{
"spec":{
"display_name":"spec"
}
}
},
"OpenAPIToolkit":{
"display_name":"OpenAPIToolkit",
"description":"Toolkit for interacting with an OpenAPI API.",
"description_url":"",
"template":{
"json_agent":{
"display_name":"json_agent"
},
"requests_wrapper":{
"display_name":"requests_wrapper"
}
}
},
"VectorStoreInfo":{
"display_name":"VectorStoreInfo",
"description":"Information about a vectorstore.",
"description_url":"",
"template":{
"vectorstore":{
"display_name":"vectorstore"
},
"description":{
"display_name":"description"
},
"name":{
"display_name":"name"
}
}
},
"VectorStoreRouterToolkit":{
"display_name":"VectorStoreRouterToolkit",
"description":"Toolkit for routing between vector stores.",
"description_url":"",
"template":{
"vectorstores":{
"display_name":"vectorstores"
}
}
},
"VectorStoreToolkit":{
"display_name":"VectorStoreToolkit",
"description":"Toolkit for interacting with a vector store.",
"description_url":"",
"template":{
"vectorstore_info":{
"display_name":"vectorstore_info"
}
}
}
},
"tools":{
"BingSearchRun":{
"display_name":"BingSearchRun",
"description":"A wrapper around Bing Search. Useful for when you need to answer questions about current events. Input should be a search query.",
"description_url":"",
"template":{
"api_wrapper":{
"display_name":"api_wrapper"
},
"args_schema":{
"display_name":"args_schema"
}
}
},
"Calculator":{
"display_name":"Calculator",
"description":"Useful for when you need to answer questions about math.",
"description_url":"",
"template":{
"llm":{
"display_name":"llm"
},
"args_schema":{
"display_name":"args_schema"
}
}
},
"ComfyUIRun":{
"display_name":"ComfyUIRun",
"description_url":"",
"template":{
"api_wrapper":{
"display_name":"api_wrapper"
},
"args_schema":{
"display_name":"args_schema"
}
}
},
"GoogleSearchResults":{
"display_name":"GoogleSearchResults",
"description":"A wrapper around Google Search. Useful for when you need to answer questions about current events. Input should be a search query. Output is a JSON array of the query results",
"description_url":"",
"template":{
"api_wrapper":{
"display_name":"api_wrapper"
},
"args_schema":{
"display_name":"args_schema"
}
}
},
"GoogleSearchRun":{
"display_name":"GoogleSearchRun",
"description":"A wrapper around Google Search. Useful for when you need to answer questions about current events. Input should be a search query.",
"description_url":"",
"template":{
"api_wrapper":{
"display_name":"api_wrapper"
},
"args_schema":{
"display_name":"args_schema"
}
}
},
"GoogleSerperRun":{
"display_name":"GoogleSerperRun",
"description_url":"",
"template":{
"api_wrapper":{
"display_name":"api_wrapper"
},
"args_schema":{
"display_name":"args_schema"
}
}
},
"InfoSQLDatabaseTool":{
"display_name":"InfoSQLDatabaseTool",
"description":"\nInput to this tool is a comma-separated list of tables, output is the schema and sample rows for those tables.\n\n Example Input: 'table1, table2, table3'",
"description_url":"",
"template":{
"db":{
"display_name":"db"
},
"args_schema":{
"display_name":"args_schema"
}
}
},
"JsonGetValueTool":{
"display_name":"JsonGetValueTool",
"description":"\n Can be used to see value in string format at a given path.\n Before calling this you should be SURE that the path to this exists.\n The input is a text representation of the path to the dict in Python syntax (e.g. data[\"key1\"][0][\"key2\"]).\n ",
"description_url":"",
"template":{
"spec":{
"display_name":"spec"
},
"args_schema":{
"display_name":"args_schema"
}
}
},
"JsonListKeysTool":{
"display_name":"JsonListKeysTool",
"description":"\n Can be used to see value in string format at a given path.\n Before calling this you should be SURE that the path to this exists.\n The input is a text representation of the path to the dict in Python syntax (e.g. data[\"key1\"][0][\"key2\"]).\n ",
"description_url":"",
"template":{
"spec":{
"display_name":"spec"
},
"args_schema":{
"display_name":"args_schema"
}
}
},
"JsonSpec":{
"display_name":"JsonSpec",
"description_url":"",
"template":{
"path":{
"display_name":"path"
},
"args_schema":{
"display_name":"args_schema"
},
"max_value_length":{
"display_name":"max_value_length"
}
}
},
"ListSQLDatabaseTool":{
"display_name":"ListSQLDatabaseTool",
"description":"Input is an empty string, output is a comma separated list of tables in the database.",
"description_url":"",
"template":{
"db":{
"display_name":"db"
},
"args_schema":{
"display_name":"args_schema"
}
}
},
"News API":{
"display_name":"News API",
"description":"Use this when you want to get information about the top headlines of current news stories. The input should be a question in natural language that this API can answer.",
"description_url":"",
"template":{
"llm":{
"display_name":"llm"
},
"args_schema":{
"display_name":"args_schema"
},
"news_api_key":{
"display_name":"news_api_key"
}
}
},
"PAL-MATH":{
"display_name":"PAL-MATH",
"description":"A language model that is really good at solving complex word math problems. Input should be a fully worded hard word math problem.",
"description_url":"",
"template":{
"llm":{
"display_name":"llm"
},
"args_schema":{
"display_name":"args_schema"
}
}
},
"Podcast API":{
"display_name":"Podcast API",
"description":"Use the Listen Notes Podcast API to search all podcasts or episodes. The input should be a question in natural language that this API can answer.",
"description_url":"",
"template":{
"llm":{
"display_name":"llm"
},
"args_schema":{
"display_name":"args_schema"
},
"listen_api_key":{
"display_name":"listen_api_key"
}
}
},
"PythonAstREPLTool":{
"display_name":"PythonAstREPLTool",
"description":"A Python shell. Use this to execute python commands. Input should be a valid python command. When using this tool, sometimes output is abbreviated - make sure it does not look abbreviated before using it in your answer.",
"description_url":"",
"template":{
"args_schema":{
"display_name":"args_schema"
}
}
},
"PythonFunction":{
"display_name":"PythonFunction",
"description":"Python function to be executed.",
"description_url":"",
"template":{
"code":{
"display_name":"code"
}
}
},
"PythonFunctionTool":{
"display_name":"PythonAstREPLTool",
"description":"Python function to be executed.",
"description_url":"",
"template":{
"code":{
"display_name":"code"
},
"description":{
"display_name":"description"
},
"name":{
"display_name":"name"
},
"return_direct":{
"display_name":"return_direct"
}
}
},
"PythonREPLTool":{
"display_name":"PythonREPLTool",
"description":"A Python shell. Use this to execute python commands. Input should be a valid python command. If you want to see the output of a value, you should print it out with `print(...)`.",
"description_url":"",
"template":{
"args_schema":{
"display_name":"args_schema"
}
}
},
"QuerySQLDataBaseTool":{
"display_name":"PythonREPLTool",
"description":"\n Input to this tool is a detailed and correct SQL query, output is a result from the database.\n If the query is not correct, an error message will be returned.\n If an error is returned, rewrite the query, check the query, and try again.\n ",
"description_url":"",
"template":{
"db":{
"display_name":"db"
},
"args_schema":{
"display_name":"args_schema"
}
}
},
"RequestsDeleteTool":{
"display_name":"RequestsDeleteTool",
"description":"A portal to the internet. Use this when you need to make a DELETE request to a URL. Input should be a specific url, and the output will be the text response of the DELETE request.",
"description_url":"",
"template":{
"requests_wrapper":{
"display_name":"requests_wrapper"
},
"args_schema":{
"display_name":"args_schema"
}
}
},
"RequestsGetTool":{
"display_name":"RequestsGetTool",
"description":"A portal to the internet. Use this when you need to get specific content from a website. Input should be a url (i.e. https://www.google.com). The output will be the text response of the GET request.",
"description_url":"",
"template":{
"requests_wrapper":{
"display_name":"requests_wrapper"
},
"args_schema":{
"display_name":"args_schema"
}
}
},
"RequestsPatchTool":{
"display_name":"RequestsPatchTool",
"description":"Use this when you want to PATCH to a website.\n Input should be a json string with two keys: \"url\" and \"data\".\n The value of \"url\" should be a string, and the value of \"data\" should be a dictionary of \n key-value pairs you want to PATCH to the url.\n Be careful to always use double quotes for strings in the json string\n The output will be the text response of the PATCH request.\n ",
"description_url":"",
"template":{
"requests_wrapper":{
"display_name":"requests_wrapper"
},
"args_schema":{
"display_name":"args_schema"
}
}
},
"RequestsPostTool":{
"display_name":"RequestsPostTool",
"description":"Use this when you want to POST to a website.\n Input should be a json string with two keys: \"url\" and \"data\".\n The value of \"url\" should be a string, and the value of \"data\" should be a dictionary of \n key-value pairs you want to POST to the url.\n Be careful to always use double quotes for strings in the json string\n The output will be the text response of the POST request.\n ",
"description_url":"",
"template":{
"requests_wrapper":{
"display_name":"requests_wrapper"
},
"args_schema":{
"display_name":"args_schema"
}
}
},
"RequestsPutTool":{
"display_name":"RequestsPutTool",
"description":"Use this when you want to PUT to a website.\n Input should be a json string with two keys: \"url\" and \"data\".\n The value of \"url\" should be a string, and the value of \"data\" should be a dictionary of \n key-value pairs you want to PUT to the url.\n Be careful to always use double quotes for strings in the json string.\n The output will be the text response of the PUT request.\n ",
"description_url":"",
"template":{
"requests_wrapper":{
"display_name":"requests_wrapper"
},
"args_schema":{
"display_name":"args_schema"
}
}
},
"Search":{
"display_name":"Search",
"description":"A search engine. Useful for when you need to answer questions about current events. Input should be a search query.",
"description_url":"",
"template":{
"args_schema":{
"display_name":"args_schema"
},
"serpapi_api_key":{
"display_name":"serpapi_api_key"
}
}
},
"TMDB API":{
"display_name":"TMDB API",
"description":"Useful for when you want to get information from The Movie Database. The input should be a question in natural language that this API can answer.",
"description_url":"",
"template":{
"llm":{
"display_name":"llm"
},
"args_schema":{
"display_name":"args_schema"
},
"tmdb_bearer_token":{
"display_name":"tmdb_bearer_token"
}
}
},
"Tool":{
"display_name":"Tool",
"description":"Converts a chain, agent or function into a tool.",
"description_url":"",
"template":{
"func":{
"display_name":"func"
},
"args_schema":{
"display_name":"args_schema"
},
"description":{
"display_name":"description"
},
"name":{
"display_name":"name"
},
"return_direct":{
"display_name":"return_direct"
}
}
},
"WikipediaQueryRun":{
"display_name":"WikipediaQueryRun",
"description":"A wrapper around Wikipedia. Useful for when you need to answer general questions about people, places, companies, facts, historical events, or other subjects. Input should be a search query.",
"description_url":"",
"template":{
"api_wrapper":{
"display_name":"api_wrapper"
},
"args_schema":{
"display_name":"args_schema"
}
}
},
"WolframAlphaQueryRun":{
"display_name":"WolframAlphaQueryRun",
"description":"A wrapper around Wolfram Alpha. Useful for when you need to answer questions about Math, Science, Technology, Culture, Society and Everyday Life. Input should be a search query.",
"description_url":"",
"template":{
"api_wrapper":{
"display_name":"api_wrapper"
},
"args_schema":{
"display_name":"args_schema"
}
}
}
},
"utilities":{
"BingSearchAPIWrapper":{
"display_name":"BingSearchAPIWrapper",
"description":"Wrapper for Bing Search API.",
"description_url":"",
"template":{
"bing_search_url":{
"display_name":"bing_search_url"
},
"bing_subscription_key":{
"display_name":"bing_subscription_key"
}
}
},
"ComfyUITxt2ImgAPIWrapper":{
"display_name":"ComfyUITxt2ImgAPIWrapper",
"description":"Wrapper for Comfy UI API.",
"description_url":"",
"template":{
"comfy_ui_workflow":{
"display_name":"comfy_ui_workflow"
},
"comfy_ui_api_url":{
"display_name":"comfy_ui_api_url"
},
"comfy_ui_ws_url":{
"display_name":"comfy_ui_ws_url"
}
}
},
"GoogleSearchAPIWrapper":{
"display_name":"GoogleSearchAPIWrapper",
"description":"Wrapper for Google Search API.",
"description_url":"",
"template":{
"google_api_key":{
"display_name":"google_api_key"
}
}
},
"GoogleSerperAPIWrapper":{
"display_name":"GoogleSerperAPIWrapper",
"description":"Wrapper around the Serper.dev Google Search API.",
"description_url":"",
"template":{
"result_key_for_type":{
"display_name":"result_key_for_type"
},
"serper_api_key":{
"display_name":"serper_api_key"
}
}
},
"SearxSearchWrapper":{
"display_name":"SearxSearchWrapper",
"description":"Wrapper for Searx API.",
"description_url":"",
"template":{
"headers":{
"display_name":"headers"
}
}
},
"SerpAPIWrapper":{
"display_name":"SerpAPIWrapper",
"description":"Wrapper around SerpAPI.",
"description_url":"",
"template":{
"serpapi_api_key":{
"display_name":"serpapi_api_key"
}
}
},
"WikipediaAPIWrapper":{
"display_name":"WikipediaAPIWrapper",
"description":"Wrapper around WikipediaAPI.",
"description_url":""
},
"WolframAlphaAPIWrapper":{
"display_name":"WolframAlphaAPIWrapper",
"description":"Wrapper for Wolfram Alpha.",
"description_url":""
}
},
"vectorstores":{
"Chroma":{
"display_name":"Chroma",
"description":"Create a Chroma vectorstore from a raw documents.",
"description_url":"",
"template":{
"documents":{
"display_name":"Documents"
},
"embedding":{
"display_name":"Embedding"
},
"collection_name":{
"display_name":"collection_name"
},
"persist":{
"display_name":"Persist"
},
"persist_directory":{
"display_name":"persist_directory"
}
}
},
"ElasticKeywordsSearch":{
"display_name":"ElasticKeywordsSearch",
"description":"Construct ElasticKeywordsSearch wrapper from raw documents.",
"description_url":"",
"template":{
"documents":{
"display_name":"Documents"
},
"llm":{
"display_name":"LLM"
},
"prompt":{
"display_name":"prompt"
},
"elasticsearch_url":{
"display_name":"ES_connection_url"
},
"index_name":{
"display_name":"index_name"
},
"ssl_verify":{
"display_name":"ssl_verify"
}
}
},
"FAISS":{
"display_name":"FAISS",
"description":"Construct FAISS wrapper from raw documents.",
"description_url":"",
"template":{
"documents":{
"display_name":"Documents"
},
"embedding":{
"display_name":"Embedding"
},
"folder_path":{
"display_name":"Local Path"
},
"index_name":{
"display_name":"Index Name"
}
}
},
"Milvus":{
"display_name":"Milvus",
"description":"Create a Milvus collection, indexes it with HNSW, and insert data.",
"description_url":"",
"template":{
"documents":{
"display_name":"Documents"
},
"embedding":{
"display_name":"Embedding"
},
"collection_name":{
"display_name":"collection_name"
},
"connection_args":{
"display_name":"connection_args"
}
},
"output_types":[
"Milvus"
]
},
"MongoDBAtlasVectorSearch":{
"display_name":"MongoDB Atlas",
"description":"Create a Milvus collection, indexes it with HNSW, and insert data.",
"description_url":"",
"template":{
"documents":{
"display_name":"Documents"
},
"embedding":{
"display_name":"Embedding"
},
"collection_name":{
"display_name":"Collection Name"
},
"db_name":{
"display_name":"Database Name"
},
"index_name":{
"display_name":"Index Name"
},
"mongodb_atlas_cluster_uri":{
"display_name":"MongoDB Atlas Cluster URI"
}
},
"output_types":[
"MongoDB Atlas"
]
},
"Pinecone":{
"display_name":"Pinecone",
"description":"Construct Pinecone wrapper from raw documents.",
"description_url":"",
"template":{
"documents":{
"display_name":"Documents"
},
"embedding":{
"display_name":"Embedding"
},
"index_name":{
"display_name":"Index Name"
},
"namespace":{
"display_name":"namespace"
}
},
"output_types":[
"Pinecone"
]
},
"Qdrant":{
"display_name":"Qdrant",
"description":"Construct Qdrant wrapper from a list of texts.",
"description_url":"",
"template":{
"documents":{
"display_name":"Documents"
},
"embedding":{
"display_name":"Embedding"
},
"api_key":{
"display_name":"API Key"
},
"collection_name":{
"display_name":"collection_name"
},
"location":{
"display_name":"location"
}
}
},
"SupabaseVectorStore":{
"display_name":"Supabase",
"description":"Return VectorStore initialized from texts and embeddings.",
"description_url":"",
"template":{
"documents":{
"display_name":"Documents"
},
"embedding":{
"display_name":"Embedding"
},
"query_name":{
"display_name":"query_name"
},
"supabase_service_key":{
"display_name":"supabase_service_key"
},
"supabase_url":{
"display_name":"supabase_url"
},
"table_name":{
"display_name":"table_name"
}
}
},
"Weaviate":{
"display_name":"Weaviate",
"description":"Construct Weaviate wrapper from raw documents.",
"description_url":"",
"template":{
"documents":{
"display_name":"Documents"
},
"embedding":{
"display_name":"Embedding"
},
"weaviate_url":{
"display_name":"weaviate_url"
}
}
}
},
"wrappers":{
"SQLDatabase":{
"display_name":"SQLDatabase",
"description":"Construct a SQLAlchemy engine from URI.",
"description_url":"",
"template":{
"database_uri":{
"display_name":"database_uri"
}
}
},
"TextRequestsWrapper":{
"display_name":"TextRequestsWrapper",
"description":"Lightweight wrapper around requests library.",
