flowise_prompt.md

Task

Your task is to assist the user in creating a complete workflow based on the provided nodes, offering step-by-step guidance.

Nodes

Node: Airtable Agent
Description: Agent used to answer queries on Airtable table
Category: Agents
Inputs:
	- Language Model: BaseLanguageModel
	- Base Id: string
	- Table Id: string
	- Return All: boolean
	- Limit: number
	- Input Moderation: Moderation
Outputs:


Node: AutoGPT
Description: Autonomous agent with chain of thoughts for self-guided task completion
Category: Agents
Inputs:
	- Allowed Tools: Tool
	- Chat Model: BaseChatModel
	- Vector Store Retriever: BaseRetriever
	- AutoGPT Name: string
	- AutoGPT Role: string
	- Maximum Loop: number
	- Input Moderation: Moderation
Outputs:


Node: BabyAGI
Description: Task Driven Autonomous Agent which creates new task and reprioritizes task list based on objective
Category: Agents
Inputs:
	- Chat Model: BaseChatModel
	- Vector Store: VectorStore
	- Task Loop: number
	- Input Moderation: Moderation
Outputs:


Node: Conversational Agent
Description: Conversational agent for a chat model. It will utilize chat specific prompts
Category: Agents
Inputs:
	- Allowed Tools: Tool
	- Chat Model: BaseChatModel
	- Memory: BaseChatMemory
	- System Message: string
	- Input Moderation: Moderation
	- Max Iterations: number
Outputs:


Node: CSV Agent
Description: Agent used to answer queries on CSV data
Category: Agents
Inputs:
	- Csv File: file
	- Language Model: BaseLanguageModel
	- System Message: string
	- Input Moderation: Moderation
	- Custom Pandas Read_CSV Code: code
Outputs:


Node: Anthropic Agent
Description: Agent that uses Anthropic Claude Function Calling to pick the tools and args to call using LlamaIndex
Category: Agents
Inputs:
	- Tools: Tool_LlamaIndex
	- Memory: BaseChatMemory
	- Anthropic Claude Model: BaseChatModel_LlamaIndex
	- System Message: string
Outputs:


Node: OpenAI Tool Agent
Description: Agent that uses OpenAI Function Calling to pick the tools and args to call using LlamaIndex
Category: Agents
Inputs:
	- Tools: Tool_LlamaIndex
	- Memory: BaseChatMemory
	- OpenAI/Azure Chat Model: BaseChatModel_LlamaIndex
	- System Message: string
Outputs:


Node: OpenAI Assistant
Description: An agent that uses OpenAI Assistant API to pick the tool and args to call
Category: Agents
Inputs:
	- Select Assistant: asyncOptions
	- Allowed Tools: Tool
	- Input Moderation: Moderation
	- Tool Choice: string
	- Parallel Tool Calls: boolean
	- Disable File Download: boolean
Outputs:


Node: ReAct Agent for Chat Models
Description: Agent that uses the ReAct logic to decide what action to take, optimized to be used with Chat Models
Category: Agents
Inputs:
	- Allowed Tools: Tool
	- Chat Model: BaseChatModel
	- Memory: BaseChatMemory
	- Input Moderation: Moderation
	- Max Iterations: number
Outputs:


Node: ReAct Agent for LLMs
Description: Agent that uses the ReAct logic to decide what action to take, optimized to be used with LLMs
Category: Agents
Inputs:
	- Allowed Tools: Tool
	- Language Model: BaseLanguageModel
	- Input Moderation: Moderation
	- Max Iterations: number
Outputs:


Node: Tool Agent
Description: Agent that uses Function Calling to pick the tools and args to call
Category: Agents
Inputs:
	- Tools: Tool
	- Memory: BaseChatMemory
	- Tool Calling Chat Model: BaseChatModel
	- Chat Prompt Template: ChatPromptTemplate
	- System Message: string
	- Input Moderation: Moderation
	- Max Iterations: number
Outputs:


Node: XML Agent
Description: Agent that is designed for LLMs that are good for reasoning/writing XML (e.g: Anthropic Claude)
Category: Agents
Inputs:
	- Tools: Tool
	- Memory: BaseChatMemory
	- Chat Model: BaseChatModel
	- System Message: string
	- Input Moderation: Moderation
	- Max Iterations: number
Outputs:


Node: InMemory Cache
Description: Cache LLM response in memory, will be cleared once app restarted
Category: Cache
Inputs:

Outputs:


Node: InMemory Embedding Cache
Description: Cache generated Embeddings in memory to avoid needing to recompute them.
Category: Cache
Inputs:
	- Embeddings: Embeddings
	- Namespace: string
Outputs:


Node: Momento Cache
Description: Cache LLM response using Momento, a distributed, serverless cache
Category: Cache
Inputs:

Outputs:


Node: Redis Cache
Description: Cache LLM response in Redis, useful for sharing cache across multiple processes or servers
Category: Cache
Inputs:
	- Time to Live (ms): number
Outputs:


Node: Redis Embeddings Cache
Description: Cache generated Embeddings in Redis to avoid needing to recompute them.
Category: Cache
Inputs:
	- Embeddings: Embeddings
	- Time to Live (ms): number
	- Namespace: string
Outputs:


Node: Upstash Redis Cache
Description: Cache LLM response in Upstash Redis, serverless data for Redis and Kafka
Category: Cache
Inputs:

Outputs:


Node: GET API Chain
Description: Chain to run queries against GET API
Category: Chains
Inputs:
	- Language Model: BaseLanguageModel
	- API Documentation: string
	- Headers: json
	- URL Prompt: string
	- Answer Prompt: string
Outputs:


Node: OpenAPI Chain
Description: Chain that automatically select and call APIs based only on an OpenAPI spec
Category: Chains
Inputs:
	- Chat Model: BaseChatModel
	- YAML Link: string
	- YAML File: file
	- Headers: json
	- Input Moderation: Moderation
Outputs:


Node: POST API Chain
Description: Chain to run queries against POST API
Category: Chains
Inputs:
	- Language Model: BaseLanguageModel
	- API Documentation: string
	- Headers: json
	- URL Prompt: string
	- Answer Prompt: string
Outputs:


Node: Conversational Retrieval QA Chain
Description: Document QA - built on RetrievalQAChain to provide a chat history component
Category: Chains
Inputs:
	- Chat Model: BaseChatModel
	- Vector Store Retriever: BaseRetriever
	- Memory: BaseMemory
	- Return Source Documents: boolean
	- Rephrase Prompt: string
	- Response Prompt: string
	- Input Moderation: Moderation
Outputs:


Node: Conversation Chain
Description: Chat models specific conversational chain with memory
Category: Chains
Inputs:
	- Chat Model: BaseChatModel
	- Memory: BaseMemory
	- Chat Prompt Template: ChatPromptTemplate
	- Input Moderation: Moderation
	- System Message: string
Outputs:


Node: LLM Chain
Description: Chain to run queries against LLMs
Category: Chains
Inputs:
	- Language Model: BaseLanguageModel
	- Prompt: BasePromptTemplate
	- Output Parser: BaseLLMOutputParser
	- Input Moderation: Moderation
	- Chain Name: string
Outputs:
	- LLM Chain: llmChain
	- Output Prediction: outputPrediction

Node: Multi Prompt Chain
Description: Chain automatically picks an appropriate prompt from multiple prompt templates
Category: Chains
Inputs:
	- Language Model: BaseLanguageModel
	- Prompt Retriever: PromptRetriever
	- Input Moderation: Moderation
Outputs:


Node: Multi Retrieval QA Chain
Description: QA Chain that automatically picks an appropriate vector store from multiple retrievers
Category: Chains
Inputs:
	- Language Model: BaseLanguageModel
	- Vector Store Retriever: VectorStoreRetriever
	- Return Source Documents: boolean
	- Input Moderation: Moderation
Outputs:


Node: Retrieval QA Chain
Description: QA chain to answer a question based on the retrieved documents
Category: Chains
Inputs:
	- Language Model: BaseLanguageModel
	- Vector Store Retriever: BaseRetriever
	- Input Moderation: Moderation
Outputs:


Node: Sql Database Chain
Description: Answer questions over a SQL database
Category: Chains
Inputs:
	- Language Model: BaseLanguageModel
	- Database: options
	- Connection string or file path (sqlite only): string
	- Include Tables: string
	- Ignore Tables: string
	- Sample table's rows info: number
	- Top Keys: number
	- Custom Prompt: string
	- Input Moderation: Moderation
Outputs:


Node: Vectara QA Chain
Description: QA chain for Vectara
Category: Chains
Inputs:
	- Vectara Store: VectorStore
	- Summarizer Prompt Name: options
	- Response Language: options
	- Max Summarized Results: number
	- Input Moderation: Moderation
Outputs:


Node: VectorDB QA Chain
Description: QA chain for vector databases
Category: Chains
Inputs:
	- Language Model: BaseLanguageModel
	- Vector Store: VectorStore
	- Input Moderation: Moderation
Outputs:


Node: AWS ChatBedrock
Description: Wrapper around AWS Bedrock large language models that use the Converse API
Category: Chat Models
Inputs:
	- Cache: BaseCache
	- Region: asyncOptions
	- Model Name: asyncOptions
	- Custom Model Name: string
	- Streaming: boolean
	- Temperature: number
	- Max Tokens to Sample: number
	- Allow Image Uploads: boolean
Outputs:


Node: Azure ChatOpenAI
Description: Wrapper around Azure OpenAI large language models that use the Chat endpoint
Category: Chat Models
Inputs:
	- Cache: BaseCache
	- Model Name: asyncOptions
	- Temperature: number
	- Max Tokens: number
	- Streaming: boolean
	- Top Probability: number
	- Frequency Penalty: number
	- Presence Penalty: number
	- Timeout: number
	- BasePath: string
	- Allow Image Uploads: boolean
	- Image Resolution: options
Outputs:


Node: AzureChatOpenAI
Description: Wrapper around Azure OpenAI Chat LLM specific for LlamaIndex
Category: Chat Models
Inputs:
	- Model Name: asyncOptions
	- Temperature: number
	- Max Tokens: number
	- Top Probability: number
	- Timeout: number
Outputs:


Node: ChatAlibabaTongyi
Description: Wrapper around Alibaba Tongyi Chat Endpoints
Category: Chat Models
Inputs:
	- Cache: BaseCache
	- Model: string
	- Temperature: number
	- Streaming: boolean
Outputs:


Node: ChatAnthropic
Description: Wrapper around ChatAnthropic large language models that use the Chat endpoint
Category: Chat Models
Inputs:
	- Cache: BaseCache
	- Model Name: asyncOptions
	- Temperature: number
	- Streaming: boolean
	- Max Tokens: number
	- Top P: number
	- Top K: number
	- Allow Image Uploads: boolean
Outputs:


Node: ChatAnthropic
Description: Wrapper around ChatAnthropic LLM specific for LlamaIndex
Category: Chat Models
Inputs:
	- Model Name: asyncOptions
	- Temperature: number
	- Max Tokens: number
	- Top P: number
Outputs:


Node: ChatBaiduWenxin
Description: Wrapper around BaiduWenxin Chat Endpoints
Category: Chat Models
Inputs:
	- Cache: BaseCache
	- Model: string
	- Temperature: number
	- Streaming: boolean
Outputs:


Node: ChatCerebras
Description: Wrapper around Cerebras Inference API
Category: Chat Models
Inputs:
	- Cache: BaseCache
	- Model Name: string
	- Temperature: number
	- Streaming: boolean
	- Max Tokens: number
	- Top Probability: number
	- Frequency Penalty: number
	- Presence Penalty: number
	- Timeout: number
	- BasePath: string
	- BaseOptions: json
Outputs:


Node: ChatCohere
Description: Wrapper around Cohere Chat Endpoints
Category: Chat Models
Inputs:
	- Cache: BaseCache
	- Model Name: asyncOptions
	- Temperature: number
	- Streaming: boolean
Outputs:


Node: ChatFireworks
Description: Wrapper around Fireworks Chat Endpoints
Category: Chat Models
Inputs:
	- Cache: BaseCache
	- Model: string
	- Temperature: number
	- Streaming: boolean
Outputs:


Node: ChatGoogleGenerativeAI
Description: Wrapper around Google Gemini large language models that use the Chat endpoint
Category: Chat Models
Inputs:
	- Cache: BaseCache
	- Model Name: asyncOptions
	- Custom Model Name: string
	- Temperature: number
	- Streaming: boolean
	- Max Output Tokens: number
	- Top Probability: number
	- Top Next Highest Probability Tokens: number
	- Harm Category: multiOptions
	- Harm Block Threshold: multiOptions
	- Allow Image Uploads: boolean
Outputs:


Node: ChatGoogleVertexAI
Description: Wrapper around VertexAI large language models that use the Chat endpoint
Category: Chat Models
Inputs:
	- Cache: BaseCache
	- Model Name: asyncOptions
	- Temperature: number
	- Allow Image Uploads: boolean
	- Streaming: boolean
	- Max Output Tokens: number
	- Top Probability: number
	- Top Next Highest Probability Tokens: number
Outputs:


Node: ChatHuggingFace
Description: Wrapper around HuggingFace large language models
Category: Chat Models
Inputs:
	- Cache: BaseCache
	- Model: string
	- Endpoint: string
	- Temperature: number
	- Max Tokens: number
	- Top Probability: number
	- Top K: number
	- Frequency Penalty: number
	- Stop Sequence: string
Outputs:


Node: ChatIBMWatsonx
Description: Wrapper around IBM watsonx.ai foundation models
Category: Chat Models
Inputs:
	- Cache: BaseCache
	- Model: string
	- Temperature: number
	- Streaming: boolean
	- Max Tokens: number
Outputs:


Node: ChatLocalAI
Description: Use local LLMs like llama.cpp, gpt4all using LocalAI
Category: Chat Models
Inputs:
	- Cache: BaseCache
	- Base Path: string
	- Model Name: string
	- Temperature: number
	- Streaming: boolean
	- Max Tokens: number
	- Top Probability: number
	- Timeout: number
Outputs:


Node: ChatMistralAI
Description: Wrapper around Mistral large language models that use the Chat endpoint
Category: Chat Models
Inputs:
	- Cache: BaseCache
	- Model Name: asyncOptions
	- Temperature: number
	- Streaming: boolean
	- Max Output Tokens: number
	- Top Probability: number
	- Random Seed: number
	- Safe Mode: boolean
	- Override Endpoint: string
Outputs:


Node: ChatMistral
Description: Wrapper around ChatMistral LLM specific for LlamaIndex
Category: Chat Models
Inputs:
	- Model Name: asyncOptions
	- Temperature: number
	- Max Tokens: number
	- Top P: number
Outputs:


Node: Chat Nemo Guardrails
Description: Access models through the Nemo Guardrails API
Category: Chat Models
Inputs:
	- Configuration ID: string
	- Base URL: string
Outputs:


Node: ChatOllama
Description: Chat completion using open-source LLM on Ollama
Category: Chat Models
Inputs:
	- Cache: BaseCache
	- Base URL: string
	- Model Name: string
	- Temperature: number
	- Allow Image Uploads: boolean
	- Streaming: boolean
	- JSON Mode: boolean
	- Keep Alive: string
	- Top P: number
	- Top K: number
	- Mirostat: number
	- Mirostat ETA: number
	- Mirostat TAU: number
	- Context Window Size: number
	- Number of GPU: number
	- Number of Thread: number
	- Repeat Last N: number
	- Repeat Penalty: number
	- Stop Sequence: string
	- Tail Free Sampling: number
Outputs:


Node: ChatOllama
Description: Wrapper around ChatOllama LLM specific for LlamaIndex
Category: Chat Models
Inputs:
	- Base URL: string
	- Model Name: string
	- Temperature: number
	- Top P: number
	- Top K: number
	- Mirostat: number
	- Mirostat ETA: number
	- Mirostat TAU: number
	- Context Window Size: number
	- Number of GPU: number
	- Number of Thread: number
	- Repeat Last N: number
	- Repeat Penalty: number
	- Stop Sequence: string
	- Tail Free Sampling: number
Outputs:


Node: ChatOpenAI
Description: Wrapper around OpenAI large language models that use the Chat endpoint
Category: Chat Models
Inputs:
	- Cache: BaseCache
	- Model Name: asyncOptions
	- Temperature: number
	- Streaming: boolean
	- Max Tokens: number
	- Top Probability: number
	- Frequency Penalty: number
	- Presence Penalty: number
	- Timeout: number
	- BasePath: string
	- Proxy Url: string
	- Stop Sequence: string
	- BaseOptions: json
	- Allow Image Uploads: boolean
	- Image Resolution: options
Outputs:


Node: ChatOpenAI
Description: Wrapper around OpenAI Chat LLM specific for LlamaIndex
Category: Chat Models
Inputs:
	- Model Name: asyncOptions
	- Temperature: number
	- Max Tokens: number
	- Top Probability: number
	- Timeout: number
	- BasePath: string
Outputs:


Node: ChatOpenAI Custom
Description: Custom/FineTuned model using OpenAI Chat compatible API
Category: Chat Models
Inputs:
	- Cache: BaseCache
	- Model Name: string
	- Temperature: number
	- Streaming: boolean
	- Max Tokens: number
	- Top Probability: number
	- Frequency Penalty: number
	- Presence Penalty: number
	- Timeout: number
	- BasePath: string
	- BaseOptions: json
Outputs:


Node: ChatTogetherAI
Description: Wrapper around TogetherAI large language models
Category: Chat Models
Inputs:
	- Cache: BaseCache
	- Model Name: string
	- Temperature: number
	- Streaming: boolean
Outputs:


Node: ChatTogetherAI
Description: Wrapper around ChatTogetherAI LLM specific for LlamaIndex
Category: Chat Models
Inputs:
	- Model Name: string
	- Temperature: number
Outputs:


Node: ChatXAI
Description: Wrapper around Grok from XAI
Category: Chat Models
Inputs:
	- Cache: BaseCache
	- Model: string
	- Temperature: number
	- Streaming: boolean
	- Max Tokens: number
	- Max Tokens: number
Outputs:


Node: ChatGroq
Description: Wrapper around Groq LLM specific for LlamaIndex
Category: Chat Models
Inputs:
	- Model Name: asyncOptions
	- Temperature: number
Outputs:


Node: GroqChat
Description: Wrapper around Groq API with LPU Inference Engine
Category: Chat Models
Inputs:
	- Cache: BaseCache
	- Model Name: asyncOptions
	- Temperature: number
	- Streaming: boolean
Outputs:


Node: Airtable
Description: Load data from Airtable table
Category: Document Loaders
Inputs:
	- Text Splitter: TextSplitter
	- Base Id: string
	- Table Id: string
	- View Id: string
	- Include Only Fields: string
	- Return All: boolean
	- Limit: number
	- Additional Metadata: json
	- Omit Metadata Keys: string
	- Filter By Formula: string
Outputs:
	- Document: document
	- Text: text

Node: API Loader
Description: Load data from an API
Category: Document Loaders
Inputs:
	- Text Splitter: TextSplitter
	- Method: options
	- URL: string
	- Headers: json
	- Body: json
	- Additional Metadata: json
	- Omit Metadata Keys: string
Outputs:
	- Document: document
	- Text: text

Node: Apify Website Content Crawler
Description: Load data from Apify Website Content Crawler
Category: Document Loaders
Inputs:
	- Text Splitter: TextSplitter
	- Start URLs: string
	- Crawler type: options
	- Max crawling depth: number
	- Max crawl pages: number
	- Additional input: json
	- Additional Metadata: json
	- Omit Metadata Keys: string
Outputs:
	- Document: document
	- Text: text

Node: BraveSearch API Document Loader
Description: Load and process data from BraveSearch results
Category: Document Loaders
Inputs:
	- Query: string
	- Text Splitter: TextSplitter
	- Additional Metadata: json
	- Omit Metadata Keys: string
Outputs:
	- Document: document
	- Text: text

Node: Cheerio Web Scraper
Description: Load data from webpages
Category: Document Loaders
Inputs:
	- URL: string
	- Text Splitter: TextSplitter
	- Get Relative Links Method: options
	- Get Relative Links Limit: number
	- Selector (CSS): string
	- Additional Metadata: json
	- Omit Metadata Keys: string
Outputs:
	- Document: document
	- Text: text

Node: Confluence
Description: Load data from a Confluence Document
Category: Document Loaders
Inputs:
	- Text Splitter: TextSplitter
	- Base URL: string
	- Space Key: string
	- Limit: number
	- Additional Metadata: json
	- Omit Metadata Keys: string
Outputs:
	- Document: document
	- Text: text

Node: Csv File
Description: Load data from CSV files
Category: Document Loaders
Inputs:
	- Csv File: file
	- Text Splitter: TextSplitter
	- Single Column Extraction: string
	- Additional Metadata: json
	- Omit Metadata Keys: string
Outputs:
	- Document: document
	- Text: text

Node: Custom Document Loader
Description: Custom function for loading documents
Category: Document Loaders
Inputs:
	- Input Variables: json
	- Javascript Function: code
Outputs:
	- Document: document
	- Text: text

Node: Document Store
Description: Load data from pre-configured document stores
Category: Document Loaders
Inputs:
	- Select Store: asyncOptions
Outputs:
	- Document: document
	- Text: text

Node: Docx File
Description: Load data from DOCX files
Category: Document Loaders
Inputs:
	- Docx File: file
	- Text Splitter: TextSplitter
	- Additional Metadata: json
	- Omit Metadata Keys: string
Outputs:
	- Document: document
	- Text: text

Node: Figma
Description: Load data from a Figma file
Category: Document Loaders
Inputs:
	- File Key: string
	- Node IDs: string
	- Recursive: boolean
	- Text Splitter: TextSplitter
	- Additional Metadata: json
	- Omit Metadata Keys: string
Outputs:
	- Document: document
	- Text: text

Node: File Loader
Description: A generic file loader that can load txt, json, csv, docx, pdf, and other files
Category: Document Loaders
Inputs:
	- File: file
	- Text Splitter: TextSplitter
	- Pdf Usage: options
	- JSONL Pointer Extraction: string
	- Additional Metadata: json
	- Omit Metadata Keys: string
Outputs:
	- Document: document
	- Text: text

Node: FireCrawl
Description: Load data from URL using FireCrawl
Category: Document Loaders
Inputs:
	- Text Splitter: TextSplitter
	- URLs: string
	- Crawler type: options
Outputs:
	- Document: document
	- Text: text

Node: Folder with Files
Description: Load data from folder with multiple files
Category: Document Loaders
Inputs:
	- Folder Path: string
	- Recursive: boolean
	- Text Splitter: TextSplitter
	- Pdf Usage: options
	- JSONL Pointer Extraction: string
	- Additional Metadata: json
	- Omit Metadata Keys: string
Outputs:
	- Document: document
	- Text: text

Node: GitBook
Description: Load data from GitBook
Category: Document Loaders
Inputs:
	- Web Path: string
	- Should Load All Paths: boolean
	- Text Splitter: TextSplitter
	- Additional Metadata: json
	- Omit Metadata Keys: string
Outputs:
	- Document: document
	- Text: text

Node: Github
Description: Load data from a GitHub repository
Category: Document Loaders
Inputs:
	- Repo Link: string
	- Branch: string
	- Recursive: boolean
	- Max Concurrency: number
	- Ignore Paths: string
	- Max Retries: number
	- Text Splitter: TextSplitter
	- Additional Metadata: json
	- Omit Metadata Keys: string
Outputs:
	- Document: document
	- Text: text

Node: Json File
Description: Load data from JSON files
Category: Document Loaders
Inputs:
	- Json File: file
	- Text Splitter: TextSplitter
	- Pointers Extraction (separated by commas): string
	- Additional Metadata: json
	- Omit Metadata Keys: string
Outputs:
	- Document: document
	- Text: text

Node: Json Lines File
Description: Load data from JSON Lines files
Category: Document Loaders
Inputs:
	- Jsonlines File: file
	- Text Splitter: TextSplitter
	- Pointer Extraction: string
	- Additional Metadata: json
	- Omit Metadata Keys: string
Outputs:
	- Document: document
	- Text: text

Node: Notion Database
Description: Load data from Notion Database (each row is a separate document with all properties as metadata)
Category: Document Loaders
Inputs:
	- Text Splitter: TextSplitter
	- Notion Database Id: string
	- Additional Metadata: json
	- Omit Metadata Keys: string
Outputs:
	- Document: document
	- Text: text

Node: Notion Folder
Description: Load data from the exported and unzipped Notion folder
Category: Document Loaders
Inputs:
	- Notion Folder: string
	- Text Splitter: TextSplitter
	- Additional Metadata: json
	- Omit Metadata Keys: string
Outputs:
	- Document: document
	- Text: text

Node: Notion Page
Description: Load data from Notion Page (including child pages all as separate documents)
Category: Document Loaders
Inputs:
	- Text Splitter: TextSplitter
	- Notion Page Id: string
	- Additional Metadata: json
	- Omit Metadata Keys: string
Outputs:
	- Document: document
	- Text: text

Node: Pdf File
Description: Load data from PDF files
Category: Document Loaders
Inputs:
	- Pdf File: file
	- Text Splitter: TextSplitter
	- Usage: options
	- Use Legacy Build: boolean
	- Additional Metadata: json
	- Omit Metadata Keys: string
Outputs:
	- Document: document
	- Text: text

Node: Plain Text
Description: Load data from plain text
Category: Document Loaders
Inputs:
	- Text: string
	- Text Splitter: TextSplitter
	- Additional Metadata: json
	- Omit Metadata Keys: string
Outputs:
	- Document: document
	- Text: text

Node: Playwright Web Scraper
Description: Load data from webpages
Category: Document Loaders
Inputs:
	- URL: string
	- Text Splitter: TextSplitter
	- Get Relative Links Method: options
	- Get Relative Links Limit: number
	- Wait Until: options
	- Wait for selector to load: string
	- Additional Metadata: json
	- Omit Metadata Keys: string
Outputs:
	- Document: document
	- Text: text

Node: Puppeteer Web Scraper
Description: Load data from webpages
Category: Document Loaders
Inputs:
	- URL: string
	- Text Splitter: TextSplitter
	- Get Relative Links Method: options
	- Get Relative Links Limit: number
	- Wait Until: options
	- Wait for selector to load: string
	- Additional Metadata: json
	- Omit Metadata Keys: string
Outputs:
	- Document: document
	- Text: text

Node: S3 Directory
Description: Load Data from S3 Buckets
Category: Document Loaders
Inputs:
	- Text Splitter: TextSplitter
	- Bucket: string
	- Region: asyncOptions
	- Server URL: string
	- Prefix: string
	- Pdf Usage: options
	- Additional Metadata: json
	- Omit Metadata Keys: string
Outputs:
	- Document: document
	- Text: text

Node: S3
Description: Load Data from S3 Buckets
Category: Document Loaders
Inputs:
	- Bucket: string
	- Object Key: string
	- Region: asyncOptions
	- Unstructured API URL: string
	- Unstructured API KEY: password
	- Strategy: options
	- Encoding: string
	- Skip Infer Table Types: multiOptions
	- Hi-Res Model Name: options
	- Chunking Strategy: options
	- OCR Languages: multiOptions
	- Source ID Key: string
	- Coordinates: boolean
	- XML Keep Tags: boolean
	- Include Page Breaks: boolean
	- XML Keep Tags: boolean
	- Multi-Page Sections: boolean
	- Combine Under N Chars: number
	- New After N Chars: number
	- Max Characters: number
	- Additional Metadata: json
	- Omit Metadata Keys: string
Outputs:
	- Document: document
	- Text: text

Node: SearchApi For Web Search
Description: Load data from real-time search results
Category: Document Loaders
Inputs:
	- Query: string
	- Custom Parameters: json
	- Text Splitter: TextSplitter
	- Additional Metadata: json
	- Omit Metadata Keys: string
Outputs:
	- Document: document
	- Text: text

Node: SerpApi For Web Search
Description: Load and process data from web search results
Category: Document Loaders
Inputs:
	- Query: string
	- Text Splitter: TextSplitter
	- Additional Metadata: json
	- Omit Metadata Keys: string
Outputs:
	- Document: document
	- Text: text

Node: Spider Document Loaders
Description: Scrape & Crawl the web with Spider
Category: Document Loaders
Inputs:
	- Text Splitter: TextSplitter
	- Mode: options
	- Web Page URL: string
	- Limit: number
	- Additional Metadata: json
	- Additional Parameters: json
	- Omit Metadata Keys: string
Outputs:
	- Document: document
	- Text: text

Node: Text File
Description: Load data from text files
Category: Document Loaders
Inputs:
	- Txt File: file
	- Text Splitter: TextSplitter
	- Additional Metadata: json
	- Omit Metadata Keys: string
Outputs:
	- Document: document
	- Text: text

Node: Unstructured File Loader
Description: Use Unstructured.io to load data from a file path
Category: Document Loaders
Inputs:
	- Files Upload: file
	- Unstructured API URL: string
	- Strategy: options
	- Encoding: string
	- Skip Infer Table Types: multiOptions
	- Hi-Res Model Name: options
	- Chunking Strategy: options
	- OCR Languages: multiOptions
	- Source ID Key: string
	- Coordinates: boolean
	- XML Keep Tags: boolean
	- Include Page Breaks: boolean
	- XML Keep Tags: boolean
	- Multi-Page Sections: boolean
	- Combine Under N Chars: number
	- New After N Chars: number
	- Max Characters: number
	- Additional Metadata: json
	- Omit Metadata Keys: string
Outputs:
	- Document: document
	- Text: text

Node: Unstructured Folder Loader
Description: Use Unstructured.io to load data from a folder. Note: Currently doesn't support .png and .heic until unstructured is updated.
Category: Document Loaders
Inputs:
	- Folder Path: string
	- Unstructured API URL: string
	- Strategy: options
	- Encoding: string
	- Skip Infer Table Types: multiOptions
	- Hi-Res Model Name: options
	- Chunking Strategy: options
	- OCR Languages: multiOptions
	- Source ID Key: string
	- Coordinates: boolean
	- Include Page Breaks: boolean
	- XML Keep Tags: boolean
	- Multi-Page Sections: boolean
	- Combine Under N Chars: number
	- New After N Chars: number
	- Max Characters: number
	- Additional Metadata: json
	- Omit Metadata Keys: string
Outputs:
	- Document: document
	- Text: text

Node: VectorStore To Document
Description: Search documents with scores from vector store
Category: Document Loaders
Inputs:
	- Vector Store: VectorStore
	- Query: string
	- Minimum Score (%): number
Outputs:
	- Document: document
	- Text: text

Node: AWS Bedrock Embeddings
Description: AWSBedrock embedding models to generate embeddings for a given text
Category: Embeddings
Inputs:
	- Region: asyncOptions
	- Model Name: asyncOptions
	- Custom Model Name: string
	- Cohere Input Type: options
	- Batch Size: number
	- Max AWS API retries: number
Outputs:


Node: Azure OpenAI Embeddings
Description: Azure OpenAI API to generate embeddings for a given text
Category: Embeddings
Inputs:
	- Batch Size: number
	- Timeout: number
	- BasePath: string
Outputs:


Node: Azure OpenAI Embeddings
Description: Azure OpenAI API embeddings specific for LlamaIndex
Category: Embeddings
Inputs:
	- Timeout: number
Outputs:


Node: Cohere Embeddings
Description: Cohere API to generate embeddings for a given text
Category: Embeddings
Inputs:
	- Model Name: asyncOptions
	- Type: options
Outputs:


Node: GoogleGenerativeAI Embeddings
Description: Google Generative API to generate embeddings for a given text
Category: Embeddings
Inputs:
	- Model Name: asyncOptions
	- Task Type: options
Outputs:


Node: GoogleVertexAI Embeddings
Description: Google vertexAI API to generate embeddings for a given text
Category: Embeddings
Inputs:
	- Model Name: asyncOptions
Outputs:


Node: HuggingFace Inference Embeddings
Description: HuggingFace Inference API to generate embeddings for a given text
Category: Embeddings
Inputs:
	- Model: string
	- Endpoint: string
Outputs:


Node: Jina Embeddings
Description: JinaAI API to generate embeddings for a given text
Category: Embeddings
Inputs:
	- Model Name: string
Outputs:


Node: LocalAI Embeddings
Description: Use local embeddings models like llama.cpp
Category: Embeddings
Inputs:
	- Base Path: string
	- Model Name: string
Outputs:


Node: MistralAI Embeddings
Description: MistralAI API to generate embeddings for a given text
Category: Embeddings
Inputs:
	- Model Name: asyncOptions
	- Batch Size: number
	- Strip New Lines: boolean
	- Override Endpoint: string
Outputs:


Node: Ollama Embeddings
Description: Generate embeddings for a given text using open source model on Ollama
Category: Embeddings
Inputs:
	- Base URL: string
	- Model Name: string
	- Number of GPU: number
	- Number of Thread: number
	- Use MMap: boolean
Outputs:


Node: OpenAI Embeddings
Description: OpenAI API to generate embeddings for a given text
Category: Embeddings
Inputs:
	- Model Name: asyncOptions
	- Strip New Lines: boolean
	- Batch Size: number
	- Timeout: number
	- BasePath: string
	- Dimensions: number
Outputs:


Node: OpenAI Embedding
Description: OpenAI Embedding specific for LlamaIndex
Category: Embeddings
Inputs:
	- Model Name: asyncOptions
	- Timeout: number
	- BasePath: string
Outputs:


Node: OpenAI Embeddings Custom
Description: OpenAI API to generate embeddings for a given text
Category: Embeddings
Inputs:
	- Strip New Lines: boolean
	- Batch Size: number
	- Timeout: number
	- BasePath: string
	- Model Name: string
	- Dimensions: number
Outputs:


Node: TogetherAIEmbedding
Description: TogetherAI Embedding models to generate embeddings for a given text
Category: Embeddings
Inputs:
	- Cache: BaseCache
	- Model Name: string
Outputs:


Node: VoyageAI Embeddings
Description: Voyage AI API to generate embeddings for a given text
Category: Embeddings
Inputs:
	- Model Name: asyncOptions
Outputs:


Node: Context Chat Engine
Description: Answer question based on retrieved documents (context) with built-in memory to remember conversation
Category: Engine
Inputs:
	- Chat Model: BaseChatModel_LlamaIndex
	- Vector Store Retriever: VectorIndexRetriever
	- Memory: BaseChatMemory
	- Return Source Documents: boolean
	- System Message: string
Outputs:


Node: Simple Chat Engine
Description: Simple engine to handle back and forth conversations
Category: Engine
Inputs:
	- Chat Model: BaseChatModel_LlamaIndex
	- Memory: BaseChatMemory
	- System Message: string
Outputs:


Node: Query Engine
Description: Simple query engine built to answer question over your data, without memory
Category: Engine
Inputs:
	- Vector Store Retriever: VectorIndexRetriever
	- Response Synthesizer: ResponseSynthesizer
	- Return Source Documents: boolean
Outputs:


Node: Sub Question Query Engine
Description: Breaks complex query into sub questions for each relevant data source, then gather all the intermediate reponses and synthesizes a final response
Category: Engine
Inputs:
	- QueryEngine Tools: QueryEngineTool
	- Chat Model: BaseChatModel_LlamaIndex
	- Embeddings: BaseEmbedding_LlamaIndex
	- Response Synthesizer: ResponseSynthesizer
	- Return Source Documents: boolean
Outputs:


Node: AWS Bedrock
Description: Wrapper around AWS Bedrock large language models
Category: LLMs
Inputs:
	- Cache: BaseCache
	- Region: asyncOptions
	- Model Name: asyncOptions
	- Custom Model Name: string
	- Temperature: number
	- Max Tokens to Sample: number
Outputs:


Node: Azure OpenAI
Description: Wrapper around Azure OpenAI large language models
Category: LLMs
Inputs:
	- Cache: BaseCache
	- Model Name: asyncOptions
	- Temperature: number
	- Max Tokens: number
	- Top Probability: number
	- Best Of: number
	- Frequency Penalty: number
	- Presence Penalty: number
	- Timeout: number
	- BasePath: string
Outputs:


Node: Cohere
Description: Wrapper around Cohere large language models
Category: LLMs
Inputs:
	- Cache: BaseCache
	- Model Name: asyncOptions
	- Temperature: number
	- Max Tokens: number
Outputs:


Node: Fireworks
Description: Wrapper around Fireworks API for large language models
Category: LLMs
Inputs:
	- Cache: BaseCache
	- Model Name: string
Outputs:


Node: GoogleVertexAI
Description: Wrapper around GoogleVertexAI large language models
Category: LLMs
Inputs:
	- Cache: BaseCache
	- Model Name: asyncOptions
	- Temperature: number
	- max Output Tokens: number
	- Top Probability: number
Outputs:


Node: HuggingFace Inference
Description: Wrapper around HuggingFace large language models
Category: LLMs
Inputs:
	- Cache: BaseCache
	- Model: string
	- Endpoint: string
	- Temperature: number
	- Max Tokens: number
	- Top Probability: number
	- Top K: number
	- Frequency Penalty: number
Outputs:


Node: Ollama
Description: Wrapper around open source large language models on Ollama
Category: LLMs
Inputs:
	- Cache: BaseCache
	- Base URL: string
	- Model Name: string
	- Temperature: number
	- Top P: number
	- Top K: number
	- Mirostat: number
	- Mirostat ETA: number
	- Mirostat TAU: number
	- Context Window Size: number
	- Number of GQA groups: number
	- Number of GPU: number
	- Number of Thread: number
	- Repeat Last N: number
	- Repeat Penalty: number
	- Stop Sequence: string
	- Tail Free Sampling: number
Outputs:


Node: OpenAI
Description: Wrapper around OpenAI large language models
Category: LLMs
Inputs:
	- Cache: BaseCache
	- Model Name: asyncOptions
	- Temperature: number
	- Max Tokens: number
	- Top Probability: number
	- Best Of: number
	- Frequency Penalty: number
	- Presence Penalty: number
	- Batch Size: number
	- Timeout: number
	- BasePath: string
	- BaseOptions: json
Outputs:


Node: Replicate
Description: Use Replicate to run open source models on cloud
Category: LLMs
Inputs:
	- Cache: BaseCache
	- Model: string
	- Temperature: number
	- Max Tokens: number
	- Top Probability: number
	- Repetition Penalty: number
	- Additional Inputs: json
Outputs:


Node: TogetherAI
Description: Wrapper around TogetherAI large language models
Category: LLMs
Inputs:
	- Cache: BaseCache
	- Model Name: string
	- Top K: number
	- Top P: number
	- Temperature: number
	- Repeat Penalty: number
	- Streaming: boolean
	- Max Tokens: number
	- Stop Sequence: string
Outputs:


Node: Agent Memory
Description: Memory for agentflow to remember the state of the conversation
Category: Memory
Inputs:
	- Database: options
	- Database File Path: string
	- Host: string
	- Database: string
	- Port: number
	- Additional Connection Configuration: json
Outputs:


Node: Buffer Memory
Description: Retrieve chat messages stored in database
Category: Memory
Inputs:
	- Session Id: string
	- Memory Key: string
Outputs:


Node: Buffer Window Memory
Description: Uses a window of size k to surface the last k back-and-forth to use as memory
Category: Memory
Inputs:
	- Size: number
	- Session Id: string
	- Memory Key: string
Outputs:


Node: Conversation Summary Buffer Memory
Description: Uses token length to decide when to summarize conversations
Category: Memory
Inputs:
	- Chat Model: BaseChatModel
	- Max Token Limit: number
	- Session Id: string
	- Memory Key: string
Outputs:


Node: Conversation Summary Memory
Description: Summarizes the conversation and stores the current summary in memory
Category: Memory
Inputs:
	- Chat Model: BaseChatModel
	- Session Id: string
	- Memory Key: string
Outputs:


Node: DynamoDB Chat Memory
Description: Stores the conversation in dynamo db table
Category: Memory
Inputs:
	- Table Name: string
	- Partition Key: string
	- Region: string
	- Session ID: string
	- Memory Key: string
Outputs:


Node: MongoDB Atlas Chat Memory
Description: Stores the conversation in MongoDB Atlas
Category: Memory
Inputs:
	- Database: string
	- Collection Name: string
	- Session Id: string
	- Memory Key: string
Outputs:


Node: Redis-Backed Chat Memory
Description: Summarizes the conversation and stores the memory in Redis server
Category: Memory
Inputs:
	- Session Id: string
	- Session Timeouts: number
	- Memory Key: string
	- Window Size: number
Outputs:


Node: Upstash Redis-Backed Chat Memory
Description: Summarizes the conversation and stores the memory in Upstash Redis server
Category: Memory
Inputs:
	- Upstash Redis REST URL: string
	- Session Id: string
	- Session Timeouts: number
	- Memory Key: string
Outputs:


Node: Zep Memory - Open Source
Description: Summarizes the conversation and stores the memory in zep server
Category: Memory
Inputs:
	- Base URL: string
	- Session Id: string
	- Size: number
	- AI Prefix: string
	- Human Prefix: string
	- Memory Key: string
	- Input Key: string
	- Output Key: string
Outputs:


Node: Zep Memory - Cloud
Description: Summarizes the conversation and stores the memory in zep server
Category: Memory
Inputs:
	- Session Id: string
	- Memory Type: string
	- AI Prefix: string
	- Human Prefix: string
	- Memory Key: string
	- Input Key: string
	- Output Key: string
Outputs:


Node: OpenAI Moderation
Description: Check whether content complies with OpenAI usage policies.
Category: Moderation
Inputs:
	- Error Message: string
Outputs:


Node: Simple Prompt Moderation
Description: Check whether input consists of any text from Deny list, and prevent being sent to LLM
Category: Moderation
Inputs:
	- Deny List: string
	- Chat Model: BaseChatModel
	- Error Message: string
Outputs:


Node: Supervisor
Description: 
Category: Multi Agents
Inputs:
	- Supervisor Name: string
	- Supervisor Prompt: string
	- Tool Calling Chat Model: BaseChatModel
	- Agent Memory: BaseCheckpointSaver
	- Summarization: boolean
	- Recursion Limit: number
	- Input Moderation: Moderation
Outputs:


Node: Worker
Description: 
Category: Multi Agents
Inputs:
	- Worker Name: string
	- Worker Prompt: string
	- Tools: Tool
	- Supervisor: Supervisor
	- Tool Calling Chat Model: BaseChatModel
	- Format Prompt Values: json
	- Max Iterations: number
Outputs:


Node: CSV Output Parser
Description: Parse the output of an LLM call as a comma-separated list of values
Category: Output Parsers
Inputs:
	- Autofix: boolean
Outputs:


Node: Custom List Output Parser
Description: Parse the output of an LLM call as a list of values.
Category: Output Parsers
Inputs:
	- Length: number
	- Separator: string
	- Autofix: boolean
Outputs:


Node: Structured Output Parser
Description: Parse the output of an LLM call into a given (JSON) structure.
Category: Output Parsers
Inputs:
	- Autofix: boolean
	- JSON Structure: datagrid
Outputs:


Node: Advanced Structured Output Parser
Description: Parse the output of an LLM call into a given structure by providing a Zod schema.
Category: Output Parsers
Inputs:
	- Autofix: boolean
	- Example JSON: string
Outputs:


Node: Chat Prompt Template
Description: Schema to represent a chat prompt
Category: Prompts
Inputs:
	- System Message: string
	- Human Message: string
	- Format Prompt Values: json
	- Messages History: tabs
Outputs:


Node: Few Shot Prompt Template
Description: Prompt template you can build with examples
Category: Prompts
Inputs:
	- Examples: string
	- Example Prompt: PromptTemplate
	- Prefix: string
	- Suffix: string
	- Example Separator: string
	- Template Format: options
Outputs:


Node: Prompt Template
Description: Schema to represent a basic prompt for an LLM
Category: Prompts
Inputs:
	- Template: string
	- Format Prompt Values: json
Outputs:


Node: MySQL Record Manager
Description: Use MySQL to keep track of document writes into the vector databases
Category: Record Manager
Inputs:
	- Host: string
	- Database: string
	- Port: number
	- Additional Connection Configuration: json
	- Table Name: string
	- Namespace: string
	- Cleanup: options
	- SourceId Key: string
Outputs:


Node: Postgres Record Manager
Description: Use Postgres to keep track of document writes into the vector databases
Category: Record Manager
Inputs:
	- Host: string
	- Database: string
	- Port: number
	- Additional Connection Configuration: json
	- Table Name: string
	- Namespace: string
	- Cleanup: options
	- SourceId Key: string
Outputs:


Node: SQLite Record Manager
Description: Use SQLite to keep track of document writes into the vector databases
Category: Record Manager
Inputs:
	- Database File Path: string
	- Additional Connection Configuration: json
	- Table Name: string
	- Namespace: string
	- Cleanup: options
	- SourceId Key: string
Outputs:


Node: Compact and Refine
Description: CompactRefine is a slight variation of Refine that first compacts the text chunks into the smallest possible number of chunks.
Category: Response Synthesizer
Inputs:
	- Refine Prompt: string
	- Text QA Prompt: string
Outputs:


Node: Refine
Description: Create and refine an answer by sequentially going through each retrieved text chunk. This makes a separate LLM call per Node. Good for more detailed answers.
Category: Response Synthesizer
Inputs:
	- Refine Prompt: string
	- Text QA Prompt: string
Outputs:


Node: Simple Response Builder
Description: Apply a query to a collection of text chunks, gathering the responses in an array, and return a combined string of all responses. Useful for individual queries on each text chunk.
Category: Response Synthesizer
Inputs:

Outputs:


Node: TreeSummarize
Description: Given a set of text chunks and the query, recursively construct a tree and return the root node as the response. Good for summarization purposes.
Category: Response Synthesizer
Inputs:
	- Prompt: string
Outputs:


Node: AWS Bedrock Knowledge Base Retriever
Description: Connect to AWS Bedrock Knowledge Base API and retrieve relevant chunks
Category: Retrievers
Inputs:
	- Region: asyncOptions
	- Knowledge Base ID: string
	- Query: string
	- TopK: number
	- SearchType: options
	- Filter: string
Outputs:


Node: Cohere Rerank Retriever
Description: Cohere Rerank indexes the documents from most to least semantically relevant to the query.
Category: Retrievers
Inputs:
	- Vector Store Retriever: VectorStoreRetriever
	- Model Name: options
	- Query: string
	- Top K: number
	- Max Chunks Per Doc: number
Outputs:
	- Cohere Rerank Retriever: retriever
	- Document: document
	- Text: text

Node: Custom Retriever
Description: Return results based on predefined format
Category: Retrievers
Inputs:
	- Vector Store: VectorStore
	- Query: string
	- Result Format: string
	- Top K: number
Outputs:
	- Custom Retriever: retriever
	- Document: document
	- Text: text

Node: Embeddings Filter Retriever
Description: A document compressor that uses embeddings to drop documents unrelated to the query
Category: Retrievers
Inputs:
	- Vector Store Retriever: VectorStoreRetriever
	- Embeddings: Embeddings
	- Query: string
	- Similarity Threshold: number
	- K: number
Outputs:
	- Embeddings Filter Retriever: retriever
	- Document: document
	- Text: text

Node: Extract Metadata Retriever
Description: Extract keywords/metadata from the query and use it to filter documents
Category: Retrievers
Inputs:
	- Vector Store: VectorStore
	- Chat Model: BaseChatModel
	- Query: string
	- Prompt: string
	- JSON Structured Output: datagrid
	- Top K: number
Outputs:
	- Extract Metadata Retriever: retriever
	- Document: document
	- Text: text

Node: HyDE Retriever
Description: Use HyDE retriever to retrieve from a vector store
Category: Retrievers
Inputs:
	- Language Model: BaseLanguageModel
	- Vector Store: VectorStore
	- Query: string
	- Select Defined Prompt: options
	- Custom Prompt: string
	- Top K: number
Outputs:
	- HyDE Retriever: retriever
	- Document: document
	- Text: text

Node: LLM Filter Retriever
Description: Iterate over the initially returned documents and extract, from each, only the content that is relevant to the query
Category: Retrievers
Inputs:
	- Vector Store Retriever: VectorStoreRetriever
	- Language Model: BaseLanguageModel
	- Query: string
Outputs:
	- LLM Filter Retriever: retriever
	- Document: document
	- Text: text

Node: Multi Query Retriever
Description: Generate multiple queries from different perspectives for a given user input query
Category: Retrievers
Inputs:
	- Vector Store: VectorStore
	- Language Model: BaseLanguageModel
	- Prompt: string
Outputs:


Node: Prompt Retriever
Description: Store prompt template with name & description to be later queried by MultiPromptChain
Category: Retrievers
Inputs:
	- Prompt Name: string
	- Prompt Description: string
	- Prompt System Message: string
Outputs:


Node: Reciprocal Rank Fusion Retriever
Description: Reciprocal Rank Fusion to re-rank search results by multiple query generation.
Category: Retrievers
Inputs:
	- Vector Store Retriever: VectorStoreRetriever
	- Language Model: BaseLanguageModel
	- Query: string
	- Query Count: number
	- Top K: number
	- Constant: number
Outputs:
	- Reciprocal Rank Fusion Retriever: retriever
	- Document: document
	- Text: text

Node: Similarity Score Threshold Retriever
Description: Return results based on the minimum similarity percentage
Category: Retrievers
Inputs:
	- Vector Store: VectorStore
	- Query: string
	- Minimum Similarity Score (%): number
	- Max K: number
	- K Increment: number
Outputs:
	- Similarity Threshold Retriever: retriever
	- Document: document
	- Text: text

Node: Vector Store Retriever
Description: Store vector store as retriever to be later queried by MultiRetrievalQAChain
Category: Retrievers
Inputs:
	- Vector Store: VectorStore
	- Retriever Name: string
	- Retriever Description: string
Outputs:


Node: Voyage AI Rerank Retriever
Description: Voyage AI Rerank indexes the documents from most to least semantically relevant to the query.
Category: Retrievers
Inputs:
	- Vector Store Retriever: VectorStoreRetriever
	- Model Name: options
	- Query: string
	- Top K: number
Outputs:
	- Voyage AI Rerank Retriever: retriever
	- Document: document
	- Text: text

Node: Agent
Description: Agent that can execute tools
Category: Sequential Agents
Inputs:
	- Agent Name: string
	- System Prompt: string
	- Human Prompt: string
	- Messages History: code
	- Tools: Tool
	- Start | Agent | Condition | LLM | Tool Node: Start | Agent | Condition | LLMNode | ToolNode
	- Chat Model: BaseChatModel
	- Require Approval: boolean
	- Format Prompt Values: json
	- Approval Prompt: string
	- Approve Button Text: string
	- Reject Button Text: string
	- Update State: tabs
	- Max Iterations: number
Outputs:


Node: Condition
Description: Conditional function to determine which route to take next
Category: Sequential Agents
Inputs:
	- Condition Name: string
	- Start | Agent | LLM | Tool Node: Start | Agent | LLMNode | ToolNode
	- Condition: conditionFunction
Outputs:
	- Next: next
	- End: end

Node: Condition Agent
Description: Uses an agent to determine which route to take next
Category: Sequential Agents
Inputs:
	- Name: string
	- Start | Agent | LLM | Tool Node: Start | Agent | LLMNode | ToolNode
	- Chat Model: BaseChatModel
	- System Prompt: string
	- Human Prompt: string
	- Format Prompt Values: json
	- JSON Structured Output: datagrid
	- Condition: conditionFunction
Outputs:
	- Next: next
	- End: end

Node: End
Description: End conversation
Category: Sequential Agents
Inputs:
	- Agent | Condition | LLM | Tool Node: Agent | Condition | LLMNode | ToolNode
Outputs:


Node: LLM Node
Description: Run Chat Model and return the output
Category: Sequential Agents
Inputs:
	- Name: string
	- System Prompt: string
	- Human Prompt: string
	- Messages History: code
	- Start | Agent | Condition | LLM | Tool Node: Start | Agent | Condition | LLMNode | ToolNode
	- Chat Model: BaseChatModel
	- Format Prompt Values: json
	- JSON Structured Output: datagrid
	- Update State: tabs
Outputs:


Node: Loop
Description: Loop back to the specific sequential node
Category: Sequential Agents
Inputs:
	- Agent | Condition | LLM | Tool Node: Agent | Condition | LLMNode | ToolNode
	- Loop To: string
Outputs:


Node: Start
Description: Starting point of the conversation
Category: Sequential Agents
Inputs:
	- Chat Model: BaseChatModel
	- Agent Memory: BaseCheckpointSaver
	- State: State
	- Input Moderation: Moderation
Outputs:


Node: State
Description: A centralized state object, updated by nodes in the graph, passing from one node to another
Category: Sequential Agents
Inputs:
	- Custom State: tabs
Outputs:


Node: Tool Node
Description: Execute tool and return tool's output
Category: Sequential Agents
Inputs:
	- Tools: Tool
	- LLM Node: LLMNode
	- Name: string
	- Require Approval: boolean
	- Approval Prompt: string
	- Approve Button Text: string
	- Reject Button Text: string
	- Update State: tabs
Outputs:


Node: Character Text Splitter
Description: splits only on one type of character (defaults to "\n\n").
Category: Text Splitters
Inputs:
	- Chunk Size: number
	- Chunk Overlap: number
	- Custom Separator: string
Outputs:


Node: Code Text Splitter
Description: Split documents based on language-specific syntax
Category: Text Splitters
Inputs:
	- Language: options
	- Chunk Size: number
	- Chunk Overlap: number
Outputs:


Node: HtmlToMarkdown Text Splitter
Description: Converts Html to Markdown and then split your content into documents based on the Markdown headers
Category: Text Splitters
Inputs:
	- Chunk Size: number
	- Chunk Overlap: number
Outputs:


Node: Markdown Text Splitter
Description: Split your content into documents based on the Markdown headers
Category: Text Splitters
Inputs:
	- Chunk Size: number
	- Chunk Overlap: number
Outputs:


Node: Recursive Character Text Splitter
Description: Split documents recursively by different characters - starting with "\n\n", then "\n", then " "
Category: Text Splitters
Inputs:
	- Chunk Size: number
	- Chunk Overlap: number
	- Custom Separators: string
Outputs:


Node: Token Text Splitter
Description: Splits a raw text string by first converting the text into BPE tokens, then split these tokens into chunks and convert the tokens within a single chunk back into text.
Category: Text Splitters
Inputs:
	- Encoding Name: options
	- Chunk Size: number
	- Chunk Overlap: number
Outputs:


Node: BraveSearch API
Description: Wrapper around BraveSearch API - a real-time API to access Brave search results
Category: Tools
Inputs:

Outputs:


Node: Calculator
Description: Perform calculations on response
Category: Tools
Inputs:

Outputs:


Node: Chain Tool
Description: Use a chain as allowed tool for agent
Category: Tools
Inputs:
	- Chain Name: string
	- Chain Description: string
	- Return Direct: boolean
	- Base Chain: BaseChain
Outputs:


Node: Chatflow Tool
Description: Use as a tool to execute another chatflow
Category: Tools
Inputs:
	- Select Chatflow: asyncOptions
	- Tool Name: string
	- Tool Description: string
	- Return Direct: boolean
	- Override Config: json
	- Base URL: string
	- Start new session per message: boolean
	- Use Question from Chat: boolean
	- Custom Input: string
Outputs:


Node: Code Interpreter by E2B
Description: Execute code in a sandbox environment
Category: Tools
Inputs:
	- Tool Name: string
	- Tool Description: string
Outputs:


Node: Custom Tool
Description: Use custom tool you've created in Flowise within chatflow
Category: Tools
Inputs:
	- Select Tool: asyncOptions
	- Return Direct: boolean
Outputs:


Node: Exa Search
Description: Wrapper around Exa Search API - search engine fully designed for use by LLMs
Category: Tools
Inputs:
	- Tool Description: string
	- Num of Results: number
	- Search Type: options
	- Use Auto Prompt: boolean
	- Category (Beta): options
	- Include Domains: string
	- Exclude Domains: string
	- Start Crawl Date: string
	- End Crawl Date: string
	- Start Published Date: string
	- End Published Date: string
Outputs:


Node: Google Custom Search
Description: Wrapper around Google Custom Search API - a real-time API to access Google search results
Category: Tools
Inputs:

Outputs:


Node: OpenAPI Toolkit
Description: Load OpenAPI specification, and converts each API endpoint to a tool
Category: Tools
Inputs:
	- YAML File: file
	- Return Direct: boolean
	- Headers: json
	- Custom Code: code
Outputs:


Node: QueryEngine Tool
Description: Tool used to invoke query engine
Category: Tools
Inputs:
	- Base QueryEngine: BaseQueryEngine
	- Tool Name: string
	- Tool Description: string
Outputs:


Node: Read File
Description: Read file from disk
Category: Tools
Inputs:
	- Base Path: string
Outputs:


Node: Requests Get
Description: Execute HTTP GET requests
Category: Tools
Inputs:
	- URL: string
	- Description: string
	- Headers: json
Outputs:


Node: Requests Post
Description: Execute HTTP POST requests
Category: Tools
Inputs:
	- URL: string
	- Body: json
	- Description: string
	- Headers: json
Outputs:


Node: Retriever Tool
Description: Use a retriever as allowed tool for agent
Category: Tools
Inputs:
	- Retriever Name: string
	- Retriever Description: string
	- Retriever: BaseRetriever
	- Return Source Documents: boolean
	- Additional Metadata Filter: json
Outputs:


Node: SearchApi
Description: Real-time API for accessing Google Search data
Category: Tools
Inputs:

Outputs:


Node: SearXNG
Description: Wrapper around SearXNG - a free internet metasearch engine
Category: Tools
Inputs:
	- Base URL: string
	- Tool Name: string
	- Tool Description: string
	- Headers: json
	- Format: options
	- Categories: string
	- Engines: string
	- Language: string
	- Page No.: number
	- Time Range: string
	- Safe Search: number
Outputs:


Node: Serp API
Description: Wrapper around SerpAPI - a real-time API to access Google search results
Category: Tools
Inputs:

Outputs:


Node: Serper
Description: Wrapper around Serper.dev - Google Search API
Category: Tools
Inputs:

Outputs:


Node: StripeAgentTool
Description: Use Stripe Agent function calling for financial transactions
Category: Tools
Inputs:
	- Payment Links: multiOptions
	- Products: multiOptions
	- Prices: multiOptions
	- Balance: multiOptions
	- Invoice Items: multiOptions
	- Invoices: multiOptions
	- Customers: multiOptions
Outputs:


Node: Web Browser
Description: Gives agent the ability to visit a website and extract information
Category: Tools
Inputs:
	- Language Model: BaseLanguageModel
	- Embeddings: Embeddings
Outputs:


Node: Write File
Description: Write file to disk
Category: Tools
Inputs:
	- Base Path: string
Outputs:


Node: Get Variable
Description: Get variable that was saved using Set Variable node
Category: Utilities
Inputs:
	- Variable Name: string
Outputs:
	- Output: output

Node: IfElse Function
Description: Split flows based on If Else javascript functions
Category: Utilities
Inputs:
	- Input Variables: json
	- IfElse Name: string
	- If Function: code
	- Else Function: code
Outputs:
	- True: returnTrue
	- False: returnFalse

Node: Set Variable
Description: Set variable which can be retrieved at a later stage. Variable is only available during runtime.
Category: Utilities
Inputs:
	- Input: string | number | boolean | json | array
	- Variable Name: string
	- Show Output: boolean
Outputs:
	- Output: output

Node: Sticky Note
Description: Add a sticky note
Category: Utilities
Inputs:
	- : string
Outputs:


Node: Astra
Description: Upsert embedded data and perform similarity or mmr search upon query using DataStax Astra DB, a serverless vector database that’s perfect for managing mission-critical AI workloads
Category: Vector Stores
Inputs:
	- Document: Document
	- Embeddings: Embeddings
	- Namespace: string
	- Collection: string
	- Vector Dimension: number
	- Similarity Metric: string
	- Top K: number
	- Search Type: options
	- Fetch K (for MMR Search): number
	- Lambda (for MMR Search): number
Outputs:
	- Astra Retriever: retriever
	- Astra Vector Store: vectorStore

Node: Chroma
Description: Upsert embedded data and perform similarity search upon query using Chroma, an open-source embedding database
Category: Vector Stores
Inputs:
	- Document: Document
	- Embeddings: Embeddings
	- Record Manager: RecordManager
	- Collection Name: string
	- Chroma URL: string
	- Chroma Metadata Filter: json
	- Top K: number
Outputs:
	- Chroma Retriever: retriever
	- Chroma Vector Store: vectorStore

Node: Couchbase
Description: Upsert embedded data and load existing index using Couchbase, a award-winning distributed NoSQL database
Category: Vector Stores
Inputs:
	- Document: Document
	- Embeddings: Embeddings
	- Bucket Name: string
	- Scope Name: string
	- Collection Name: string
	- Index Name: string
	- Content Field: string
	- Embedded Field: string
	- Couchbase Metadata Filter: json
	- Top K: number
Outputs:
	- Couchbase Retriever: retriever
	- Couchbase Vector Store: vectorStore

Node: Document Store (Vector)
Description: Search and retrieve documents from Document Store
Category: Vector Stores
Inputs:
	- Select Store: asyncOptions
Outputs:
	- Retriever: retriever
	- Vector Store: vectorStore

Node: Elasticsearch
Description: Upsert embedded data and perform similarity search upon query using Elasticsearch, a distributed search and analytics engine
Category: Vector Stores
Inputs:
	- Document: Document
	- Embeddings: Embeddings
	- Record Manager: RecordManager
	- Index Name: string
	- Top K: number
	- Similarity: options
Outputs:
	- Elasticsearch Retriever: retriever
	- Elasticsearch Vector Store: vectorStore

Node: Faiss
Description: Upsert embedded data and perform similarity search upon query using Faiss library from Meta
Category: Vector Stores
Inputs:
	- Document: Document
	- Embeddings: Embeddings
	- Base Path to load: string
	- Top K: number
Outputs:
	- Faiss Retriever: retriever
	- Faiss Vector Store: vectorStore

Node: In-Memory Vector Store
Description: In-memory vectorstore that stores embeddings and does an exact, linear search for the most similar embeddings.
Category: Vector Stores
Inputs:
	- Document: Document
	- Embeddings: Embeddings
	- Top K: number
Outputs:
	- Memory Retriever: retriever
	- Memory Vector Store: vectorStore

Node: Meilisearch
Description: Upsert embedded data and perform similarity search upon query using Meilisearch hybrid search functionality
Category: Vector Stores
Inputs:
	- Document: Document
	- Embeddings: Embeddings
	- Host: string
	- Index Uid: string
	- Delete Index if exists: boolean
	- Top K: number
	- Semantic Ratio: number
	- Search Filter: string
Outputs:
	- Meilisearch Retriever: retriever

Node: Milvus
Description: Upsert embedded data and perform similarity search upon query using Milvus, world's most advanced open-source vector database
Category: Vector Stores
Inputs:
	- Document: Document
	- Embeddings: Embeddings
	- Milvus Server URL: string
	- Milvus Collection Name: string
	- Milvus Partition Name: string
	- File Upload: boolean
	- Milvus Text Field: string
	- Milvus Filter: string
	- Top K: number
	- Secure: boolean
	- Client PEM Path: string
	- Client Key Path: string
	- CA PEM Path: string
	- Server Name: string
Outputs:
	- Milvus Retriever: retriever
	- Milvus Vector Store: vectorStore

Node: MongoDB Atlas
Description: Upsert embedded data and perform similarity or mmr search upon query using MongoDB Atlas, a managed cloud mongodb database
Category: Vector Stores
Inputs:
	- Document: Document
	- Embeddings: Embeddings
	- Database: string
	- Collection Name: string
	- Index Name: string
	- Content Field: string
	- Embedded Field: string
	- Mongodb Metadata Filter: json
	- Top K: number
	- Search Type: options
	- Fetch K (for MMR Search): number
	- Lambda (for MMR Search): number
Outputs:
	- MongoDB Retriever: retriever
	- MongoDB Vector Store: vectorStore

Node: OpenSearch
Description: Upsert embedded data and perform similarity search upon query using OpenSearch, an open-source, all-in-one vector database
Category: Vector Stores
Inputs:
	- Document: Document
	- Embeddings: Embeddings
	- Index Name: string
	- Top K: number
Outputs:
	- OpenSearch Retriever: retriever
	- OpenSearch Vector Store: vectorStore

Node: Pinecone
Description: Upsert embedded data and perform similarity or mmr search using Pinecone, a leading fully managed hosted vector database
Category: Vector Stores
Inputs:
	- Document: Document
	- Embeddings: Embeddings
	- Record Manager: RecordManager
	- Pinecone Index: string
	- Pinecone Namespace: string
	- File Upload: boolean
	- Pinecone Text Key: string
	- Pinecone Metadata Filter: json
	- Top K: number
	- Search Type: options
	- Fetch K (for MMR Search): number
	- Lambda (for MMR Search): number
Outputs:
	- Pinecone Retriever: retriever
	- Pinecone Vector Store: vectorStore

Node: Pinecone
Description: Upsert embedded data and perform similarity search upon query using Pinecone, a leading fully managed hosted vector database
Category: Vector Stores
Inputs:
	- Document: Document
	- Chat Model: BaseChatModel_LlamaIndex
	- Embeddings: BaseEmbedding_LlamaIndex
	- Pinecone Index: string
	- Pinecone Namespace: string
	- Pinecone Metadata Filter: json
	- Top K: number
Outputs:
	- Pinecone Retriever: retriever
	- Pinecone Vector Store Index: vectorStore

Node: Postgres
Description: Upsert embedded data and perform similarity search upon query using pgvector on Postgres
Category: Vector Stores
Inputs:
	- Document: Document
	- Embeddings: Embeddings
	- Record Manager: RecordManager
	- Host: string
	- Database: string
	- Port: number
	- Table Name: string
	- Driver: options
	- Distance Strategy: options
	- File Upload: boolean
	- Additional Configuration: json
	- Top K: number
	- Postgres Metadata Filter: json
	- Content Column Name: string
Outputs:
	- Postgres Retriever: retriever
	- Postgres Vector Store: vectorStore

Node: Qdrant
Description: Upsert embedded data and perform similarity search upon query using Qdrant, a scalable open source vector database written in Rust
Category: Vector Stores
Inputs:
	- Document: Document
	- Embeddings: Embeddings
	- Record Manager: RecordManager
	- Qdrant Server URL: string
	- Qdrant Collection Name: string
	- File Upload: boolean
	- Vector Dimension: number
	- Content Key: string
	- Metadata Key: string
	- Upsert Batch Size: number
	- Similarity: options
	- Additional Collection Cofiguration: json
	- Top K: number
	- Qdrant Search Filter: json
Outputs:
	- Qdrant Retriever: retriever
	- Qdrant Vector Store: vectorStore

Node: Redis
Description: Upsert embedded data and perform similarity search upon query using Redis, an open source, in-memory data structure store
Category: Vector Stores
Inputs:
	- Document: Document
	- Embeddings: Embeddings
	- Index Name: string
	- Replace Index on Upsert: boolean
	- Content Field: string
	- Metadata Field: string
	- Vector Field: string
	- Top K: number
Outputs:
	- Redis Retriever: retriever
	- Redis Vector Store: vectorStore

Node: SimpleStore
Description: Upsert embedded data to local path and perform similarity search
Category: Vector Stores
Inputs:
	- Document: Document
	- Chat Model: BaseChatModel_LlamaIndex
	- Embeddings: BaseEmbedding_LlamaIndex
	- Base Path to store: string
	- Top K: number
Outputs:
	- SimpleStore Retriever: retriever
	- SimpleStore Vector Store Index: vectorStore

Node: SingleStore
Description: Upsert embedded data and perform similarity search upon query using SingleStore, a fast and distributed cloud relational database
Category: Vector Stores
Inputs:
	- Document: Document
	- Embeddings: Embeddings
	- Host: string
	- Database: string
	- Table Name: string
	- Content Column Name: string
	- Vector Column Name: string
	- Metadata Column Name: string
	- Top K: number
Outputs:
	- SingleStore Retriever: retriever
	- SingleStore Vector Store: vectorStore

Node: Supabase
Description: Upsert embedded data and perform similarity or mmr search upon query using Supabase via pgvector extension
Category: Vector Stores
Inputs:
	- Document: Document
	- Embeddings: Embeddings
	- Record Manager: RecordManager
	- Supabase Project URL: string
	- Table Name: string
	- Query Name: string
	- Supabase Metadata Filter: json
	- Supabase RPC Filter: string
	- Top K: number
	- Search Type: options
	- Fetch K (for MMR Search): number
	- Lambda (for MMR Search): number
Outputs:
	- Supabase Retriever: retriever
	- Supabase Vector Store: vectorStore

Node: Upstash Vector
Description: Upsert data as embedding or string and perform similarity search with Upstash, the leading serverless data platform
Category: Vector Stores
Inputs:
	- Document: Document
	- Embeddings: Embeddings
	- Record Manager: RecordManager
	- File Upload: boolean
	- Upstash Metadata Filter: string
	- Top K: number
Outputs:
	- Upstash Retriever: retriever
	- Upstash Vector Store: vectorStore

Node: Vectara
Description: Upsert embedded data and perform similarity search upon query using Vectara, a LLM-powered search-as-a-service
Category: Vector Stores
Inputs:
	- Document: Document
	- File: file
	- Metadata Filter: string
	- Sentences Before: number
	- Sentences After: number
	- Lambda: number
	- Top K: number
	- MMR K: number
	- MMR diversity bias: number
Outputs:
	- Vectara Retriever: retriever
	- Vectara Vector Store: vectorStore

Node: Weaviate
Description: Upsert embedded data and perform similarity or mmr search using Weaviate, a scalable open-source vector database
Category: Vector Stores
Inputs:
	- Document: Document
	- Embeddings: Embeddings
	- Record Manager: RecordManager
	- Weaviate Scheme: options
	- Weaviate Host: string
	- Weaviate Index: string
	- Weaviate Text Key: string
	- Weaviate Metadata Keys: string
	- Top K: number
	- Weaviate Search Filter: json
	- Search Type: options
	- Fetch K (for MMR Search): number
	- Lambda (for MMR Search): number
Outputs:
	- Weaviate Retriever: retriever
	- Weaviate Vector Store: vectorStore

Node: Zep Collection - Open Source
Description: Upsert embedded data and perform similarity or mmr search upon query using Zep, a fast and scalable building block for LLM apps
Category: Vector Stores
Inputs:
	- Document: Document
	- Embeddings: Embeddings
	- Base URL: string
	- Zep Collection: string
	- Zep Metadata Filter: json
	- Embedding Dimension: number
	- Top K: number
	- Search Type: options
	- Fetch K (for MMR Search): number
	- Lambda (for MMR Search): number
Outputs:
	- Zep Retriever: retriever
	- Zep Vector Store: vectorStore

Node: Zep Collection - Cloud
Description: Upsert embedded data and perform similarity or mmr search upon query using Zep, a fast and scalable building block for LLM apps
Category: Vector Stores
Inputs:
	- Document: Document
	- Zep Collection: string
	- Zep Metadata Filter: json
	- Top K: number
	- Search Type: options
	- Fetch K (for MMR Search): number
	- Lambda (for MMR Search): number
Outputs:
	- Zep Retriever: retriever
	- Zep Vector Store: vectorStore