Document analysis & chatbot creation with Llama Parser, Gemini LLM & Pinecone DB
Needs changesWhat this workflow does
This AI workflow has 33 nodes and runs when someone submits an n8n form (“form which gets multiple files”) (plus 1 other trigger). Along the way it connects Google Gemini Chat Model, Gmail, Pinecone Vector Store and Embeddings Mistral Cloud. It also calls api.cloud.llamaindex.ai over HTTP.
How it runs
Trigger: When someone submits an n8n form (“form which gets multiple files”) (plus 1 other trigger).
- split the binary item (Code): runs custom JavaScript code
- Question and Answer Chain: answers questions over your documents (RAG), with model: Google Gemini Chat Model; retriever: Vector Store Retriever
- Loop Over Items (Loop Over Items (Split in Batches)): loops over the items in batches
- AI Agent: runs an AI agent, with model: Google Gemini Chat Model
- Aggregate: combines items into one
- Parsing the document (HTTP Request): calls api.cloud.llamaindex.ai (POST)
- Translator Agent (AI Agent): runs an AI agent, with model: Google Gemini Chat Model
- Check the parsing status (HTTP Request): calls an HTTP API
- Analyzer Agent (AI Agent): runs an AI agent, with model: Google Gemini Chat Model
- Convert to File: converts data to a file (to text)
…plus 9 more steps. See the full node list below.
Services it uses
HTTP calls to: api.cloud.llamaindex.ai
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in AI Agent (v1.8), AI Agent1 (v1.8), Translator Agent (v1.8)…: replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) AI Agent (v1.8), AI Agent1 (v1.8), Translator Agent (v1.8), Analyzer Agent (v1.8) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (19)
- n8n Form Trigger
n8n-nodes-base.formTrigger - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - If
n8n-nodes-base.if - Aggregate
n8n-nodes-base.aggregate - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - Code
n8n-nodes-base.code - HTTP Request
n8n-nodes-base.httpRequest - Markdown
n8n-nodes-base.markdown - Gmail
n8n-nodes-base.gmail - Convert to File
n8n-nodes-base.convertToFile - AI Agent
@n8n/n8n-nodes-langchain.agent - Information Extractor
@n8n/n8n-nodes-langchain.informationExtractor - Pinecone Vector Store
@n8n/n8n-nodes-langchain.vectorStorePinecone - Embeddings Mistral Cloud
@n8n/n8n-nodes-langchain.embeddingsMistralCloud - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Recursive Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter - Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - Question and Answer Chain
@n8n/n8n-nodes-langchain.chainRetrievalQa - Vector Store Retriever
@n8n/n8n-nodes-langchain.retrieverVectorStore
From the author
📄Description This automation workflow enables users to upload files via an N8N form, automatically analyzes the content using Google Gemini agents, and delivers the analyzed results via email along with a chatbot link. The system leverages Llama Cloud API,…