This workflow follows the Agent → Chat Trigger recipe pattern — see all workflows that pair these two integrations.
The workflow JSON
Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →
{
"id": "cGNK44mkCzIh4113",
"name": "My workflow 3",
"tags": [],
"nodes": [
{
"id": "4db348cf-bd5a-408e-b212-d75b792460b4",
"name": "On form submission4",
"type": "n8n-nodes-base.formTrigger",
"position": [
-1720,
20
],
"parameters": {
"options": {},
"formTitle": "form which gets multiple files",
"formFields": {
"values": [
{
"fieldType": "file",
"fieldLabel": "file1",
"requiredField": true
},
{
"fieldType": "file",
"fieldLabel": "file2"
},
{
"fieldLabel": "provide your mail Id",
"requiredField": true
}
]
}
},
"typeVersion": 2.2
},
{
"id": "6a1f197f-310e-4eb1-926f-60cfbae60a49",
"name": "Loop Over Items1",
"type": "n8n-nodes-base.splitInBatches",
"position": [
-380,
20
],
"parameters": {
"options": {}
},
"typeVersion": 3,
"alwaysOutputData": false
},
{
"id": "7eb210e4-687c-4e9d-b2e7-50d0b85da8dc",
"name": "If2",
"type": "n8n-nodes-base.if",
"position": [
700,
100
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "1edbcd59-130d-4053-9db3-cb8dec068fe0",
"operator": {
"name": "filter.operator.equals",
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.status }}",
"rightValue": "SUCCESS"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "e76b9523-3f87-4ad3-87df-1e4e93ead090",
"name": "Aggregate1",
"type": "n8n-nodes-base.aggregate",
"position": [
0,
0
],
"parameters": {
"options": {},
"fieldsToAggregate": {
"fieldToAggregate": [
{
"fieldToAggregate": "markdown"
}
]
}
},
"typeVersion": 1
},
{
"id": "21234dcf-52dc-4ae0-975e-36a1a18ed456",
"name": "Google Gemini Chat Model5",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
1060,
180
],
"parameters": {
"options": {},
"modelName": "models/gemini-1.5-flash"
},
"typeVersion": 1
},
{
"id": "52fcaca7-c49d-4004-96a3-0094ed0e510f",
"name": "split the binary item",
"type": "n8n-nodes-base.code",
"position": [
-1000,
20
],
"parameters": {
"jsCode": "// Get the input data\nconst items = $input.all()\n\n// Initialize an array to hold the split items\nconst splitItems = [];\n\n// Iterate over each item\nitems.forEach(item => {\n // Check if the item has binary data\n if (item.binary) {\n // Iterate over each binary field\n for (const [key, value] of Object.entries(item.binary)) {\n // Create a new item for each binary file\n splitItems.push({\n json: {},\n binary: {\n data: value\n }\n });\n }\n }\n});\n\n// Return the split items\nreturn splitItems;"
},
"typeVersion": 2,
"alwaysOutputData": true
},
{
"id": "4660eef4-de62-4b13-9f51-05000b1afa33",
"name": "Parsing the document",
"type": "n8n-nodes-base.httpRequest",
"position": [
260,
100
],
"parameters": {
"url": "https://api.cloud.llamaindex.ai/api/parsing/upload",
"method": "POST",
"options": {
"redirect": {
"redirect": {}
}
},
"sendBody": true,
"contentType": "multipart-form-data",
"sendHeaders": true,
"bodyParameters": {
"parameters": [
{
"name": "=file",
"parameterType": "formBinaryData",
"inputDataFieldName": "=data"
}
]
},
"headerParameters": {
"parameters": [
{
"name": "accept",
"value": "application/json"
},
{
"name": "Authorization",
"value": "Bearer $secret token"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "07e76215-b9d4-4adb-b8f3-f8c8615abb56",
"name": "Check the parsing status",
"type": "n8n-nodes-base.httpRequest",
"position": [
480,
100
],
"parameters": {
"url": "=https://api.cloud.llamaindex.ai/api/parsing/job/{{ $json.id }}",
"options": {},
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "accept",
"value": "application/json"
},
{
"name": "Authorization",
"value": "Bearer $secret token"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "3909a632-7002-4d60-a53b-3f73e4958c27",
"name": "Provide the markdown",
"type": "n8n-nodes-base.httpRequest",
"position": [
1180,
400
],
"parameters": {
"url": "=https://api.cloud.llamaindex.ai/api/parsing/job/{{ $json.id }}/result/markdown",
"options": {},
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "accept",
"value": "application/json"
},
{
"name": "Authorization",
"value": "Bearer $secret token"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "89c25b95-8bc6-4bb5-82d2-1f870416c4af",
"name": "Google Gemini Chat Model6",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
1600,
300
],
"parameters": {
"options": {},
"modelName": "models/gemini-1.5-flash"
},
"typeVersion": 1
},
{
"id": "8ddf6e94-6da0-4ef9-a6dc-0db8967914a6",
"name": "Markdown",
"type": "n8n-nodes-base.markdown",
"position": [
2140,
0
],
"parameters": {
"mode": "markdownToHtml",
"options": {},
"markdown": "={{ $json.output }}",
"destinationKey": "html"
},
"typeVersion": 1
},
{
"id": "59c33f95-6f8f-4992-8421-dc3a0b668861",
"name": "Gmail",
"type": "n8n-nodes-base.gmail",
"position": [
4540,
0
],
"parameters": {
"sendTo": "={{ $('On form submission4').item.json['provide your mail Id'] }}",
"message": "=Hi user,\nThe below document contains the detailed analysis of the provided document.\n\nYou can also use the below link to interact with the assistant regarding your doubts on the analysis\nhttps://pavithranvh28.app.n8n.cloud/webhook/8c5c9e83-f595-4e4b-b45c-544a9a0840c4/chat\n\n\n",
"options": {
"attachmentsUi": {
"attachmentsBinary": [
{}
]
}
},
"subject": "Analysis of the documents provided",
"emailType": "text"
},
"typeVersion": 2.1
},
{
"id": "b9bb8338-d52e-4f5b-bd2f-d517851b6014",
"name": "Code",
"type": "n8n-nodes-base.code",
"position": [
3200,
0
],
"parameters": {
"jsCode": "const items = $input.first().json.html;\n\n// Ensure items is an array\nconst htmlArray = Array.isArray(items) ? items : [items];\n\nfunction htmlToFormattedText(html) {\n // Replace heading tags (h1-h6) with bold text\n html = html.replace(/<h[1-6]>(.*?)<\\/h[1-6]>/gi, \"\\n**$1**\\n\");\n\n // Replace paragraph tags with spacing\n html = html.replace(/<p>(.*?)<\\/p>/gi, \"\\n$1\\n\");\n\n // Replace line breaks with newline characters\n html = html.replace(/<br\\s*\\/?>/gi, \"\\n\");\n\n // Remove all other HTML tags\n html = html.replace(/<[^>]+>/g, \"\").trim();\n\n // Remove extra newlines\n return html.replace(/\\n{2,}/g, \"\\n\").trim();\n}\n\nconst updatedItems = htmlArray.map((item) => {\n const htmlContent = item?.json?.html || item;\n const textContent = htmlToFormattedText(htmlContent);\n return { textContent };\n});\n\nreturn updatedItems;\n"
},
"typeVersion": 2
},
{
"id": "e8176d99-3625-47a5-8989-80fdce053ba7",
"name": "Convert to File",
"type": "n8n-nodes-base.convertToFile",
"position": [
3840,
0
],
"parameters": {
"options": {},
"operation": "toText",
"sourceProperty": "textContent"
},
"typeVersion": 1.1
},
{
"id": "9fb1a6a0-c49f-48f5-93bc-f0c6e9b8a138",
"name": "AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
2600,
460
],
"parameters": {
"text": "={{ $json.output }}",
"options": {
"systemMessage": "You are a helpful assistant.\nObjective:\nThe agent must process the input content to enhance readability, apply structured formatting, and bold necessary text elements while preserving the original meaning.\n\nProcessing Rules:\nApply Text Formatting:\n\nConvert any text enclosed with * (asterisks) into bold.\nStructurize the Content:\n\nOrganize the content using clear section headers.\nSeparate sections with line breaks for readability.\nEnsure proper indentation and bullet point usage for clarity.\nMaintain Clarity & Coherence:\n\nReformat the text without changing the core meaning.\nRemove redundancy while ensuring key details remain intact.\nText File Compatibility:\n\nResponse NEEDS TO BE A TEXT FILE"
},
"promptType": "define"
},
"typeVersion": 1.8
},
{
"id": "9995921a-ca41-40c5-9159-350908ca8213",
"name": "Google Gemini Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
2780,
740
],
"parameters": {
"options": {},
"modelName": "models/gemini-1.5-flash"
},
"typeVersion": 1
},
{
"id": "bd281ef9-bc33-4b3a-9d3f-41d00521b14e",
"name": "Information Extractor",
"type": "@n8n/n8n-nodes-langchain.informationExtractor",
"position": [
2820,
880
],
"parameters": {
"text": "={{ $json.output }}",
"options": {
"systemPromptTemplate": "You are an expert extraction algorithm.\nOnly extract relevant information from the text.\nIf you do not know the value of an attribute asked to extract, you may omit the attribute's value."
},
"attributes": {
"attributes": [
{
"name": "Project Overview",
"description": "overview of the content extracted"
},
{
"name": "System and prerequisites",
"description": "=which contains the information about the system and the prerequisites needed"
}
]
}
},
"typeVersion": 1
},
{
"id": "2f1c4efb-6885-48c9-b2a6-a13d2e9b4f66",
"name": "Google Gemini Chat Model1",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
3140,
1100
],
"parameters": {
"options": {},
"modelName": "models/gemini-1.5-flash"
},
"typeVersion": 1
},
{
"id": "b7a0276a-d253-43a8-a7f3-fb3b83599d7f",
"name": "Convert to File4",
"type": "n8n-nodes-base.convertToFile",
"position": [
1840,
740
],
"parameters": {
"options": {},
"operation": "toText",
"sourceProperty": "output"
},
"typeVersion": 1.1
},
{
"id": "7441e1ff-1966-4535-abaa-ee565db787de",
"name": "Pinecone Vector Store",
"type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
"position": [
2080,
980
],
"parameters": {
"mode": "insert",
"options": {},
"pineconeIndex": {
"__rl": true,
"mode": "list",
"value": "samuraichamploo",
"cachedResultName": "samuraichamploo"
}
},
"typeVersion": 1.1
},
{
"id": "82d9d9fb-6f8c-4c86-9287-d5e7e73f58a7",
"name": "Embeddings Mistral Cloud",
"type": "@n8n/n8n-nodes-langchain.embeddingsMistralCloud",
"position": [
2140,
1200
],
"parameters": {
"options": {}
},
"typeVersion": 1
},
{
"id": "3a3332f7-3fda-4898-999e-c5020c0ea02e",
"name": "Default Data Loader",
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"position": [
2240,
1280
],
"parameters": {
"options": {},
"dataType": "binary"
},
"typeVersion": 1
},
{
"id": "4a625913-5c98-4075-9022-058e863af326",
"name": "Recursive Character Text Splitter",
"type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
"position": [
2320,
1460
],
"parameters": {
"options": {}
},
"typeVersion": 1
},
{
"id": "5e38e72b-390f-433f-a638-522537bf1369",
"name": "When chat message received",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
-1820,
660
],
"parameters": {
"public": true,
"options": {}
},
"typeVersion": 1.1
},
{
"id": "77ea1fd6-73a9-42f6-835f-b945ce7fd294",
"name": "Question and Answer Chain",
"type": "@n8n/n8n-nodes-langchain.chainRetrievalQa",
"position": [
-1400,
680
],
"parameters": {
"options": {
"systemPromptTemplate": "You are an assistant for question-answering tasks. Use the following pieces of retrieved context to answer the question.\nIf you don't know the answer, just say that you don't know, don't try to make up an answer.\n----------------\nContext: {context}"
}
},
"typeVersion": 1.5
},
{
"id": "d71b0efe-7e27-44f8-beb4-370c02ef1d5f",
"name": "Google Gemini Chat Model2",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
-1380,
1020
],
"parameters": {
"options": {},
"modelName": "models/gemini-1.5-flash"
},
"typeVersion": 1
},
{
"id": "eb967c9d-415f-4992-bacd-517b7dddd6bf",
"name": "Vector Store Retriever",
"type": "@n8n/n8n-nodes-langchain.retrieverVectorStore",
"position": [
-1220,
900
],
"parameters": {},
"typeVersion": 1
},
{
"id": "690eacb5-1d47-430b-8914-4c474833be0b",
"name": "Pinecone Vector Store1",
"type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
"position": [
-900,
1060
],
"parameters": {
"options": {},
"pineconeIndex": {
"__rl": true,
"mode": "list",
"value": "samuraichamploo",
"cachedResultName": "samuraichamploo"
}
},
"typeVersion": 1.1
},
{
"id": "6d289625-ca46-49d7-8ee2-5996dc645ebe",
"name": "Embeddings Mistral Cloud1",
"type": "@n8n/n8n-nodes-langchain.embeddingsMistralCloud",
"position": [
-780,
1460
],
"parameters": {
"options": {}
},
"typeVersion": 1
},
{
"id": "dcc8bb20-e5f3-428e-93be-dc4081e1463c",
"name": "AI Agent1",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
-460,
680
],
"parameters": {
"text": "={{ $json.response }}",
"options": {
"systemMessage": "You are a helpful assistant.rephrase the prompt provided and Provide ONLY the response in a text format"
},
"promptType": "define"
},
"typeVersion": 1.8
},
{
"id": "777b4e63-7a0a-42fa-9069-83ab006e19a9",
"name": "Google Gemini Chat Model3",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
-400,
980
],
"parameters": {
"options": {},
"modelName": "models/gemini-1.5-flash"
},
"typeVersion": 1
},
{
"id": "f5d69ecd-9cdc-4bef-a8ae-7477dfc3f7c7",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1900,
440
],
"parameters": {
"width": 360,
"content": "## I'm a note \nThe below workflow is a chatbot workflow which will be triggered when a user types his/her prompt related to document the user provided for analysis on the chatbot link which was ent to the user via mail."
},
"typeVersion": 1
},
{
"id": "7140d564-a636-4937-b2c6-811b48dde851",
"name": "Translator Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
1060,
0
],
"parameters": {
"text": "={{ $('Aggregate1').item.json.markdown }}",
"options": {
"systemMessage": "You are a helpful assistant. Kindly check the prompt fed and find the language of the prompt you receive and if the prompt is in other language except english translate it and provide that as a response and also ATTACH THE REMAINING PROMPT WHICH IS IN ENGLISH WITH THE RESPONSE"
},
"promptType": "define"
},
"typeVersion": 1.8
},
{
"id": "496d49f1-5b7f-48ab-b759-2facd8fade8d",
"name": "Analyzer Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
1420,
0
],
"parameters": {
"text": "={{ $json.output }}",
"options": {
"systemMessage": "=You are a helpful assistant. \n1\ufe0f\u20e3 Comprehensive Prompt Analysis\n\nCarefully examine the entire prompt provided by the user.\nEnsure all details are considered before formulating a response.\n2\ufe0f\u20e3 Interactive and Clear Breakdown\n\nStructure the response in a well-organized manner with clear topic separation.\nPresent insights in a way that enhances understanding and usability.\n3\ufe0f\u20e3 Duplicate Check and Handling\n\nIdentify and highlight any repeated information within the prompt.\nIf duplicates exist, consolidate the relevant details to avoid redundancy.\n4\ufe0f\u20e3 Reliable and Actionable Resolutions\n\nProvide resolutions that are dependable and practical.\nEnsure the solutions align with the context and user\u2019s intent.\nWhere applicable, offer alternative approaches for flexibility.\nAlso make sure not to add too much of star or hash to indicate the difference"
},
"promptType": "define"
},
"typeVersion": 1.8
},
{
"id": "4218f320-c580-41ae-91ca-134bd2cc8128",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
2880,
640
],
"parameters": {
"content": "## I'm a note \nThese two subflows are for trial purpose"
},
"typeVersion": 1
},
{
"id": "bc0a3e52-1259-4651-bbe4-9ba727d8e46a",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
1420,
700
],
"parameters": {
"content": "## I'm a note \nThis subflow is responsible for storing the translated as well as the analyzed contents into the vector database to feed as a knowledge to the chatbot"
},
"typeVersion": 1
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "7c6e0b7c-dfbb-45e5-bc16-038ff6175cdc",
"connections": {
"If2": {
"main": [
[
{
"node": "Provide the markdown",
"type": "main",
"index": 0
}
],
[
{
"node": "Check the parsing status",
"type": "main",
"index": 0
}
]
]
},
"Code": {
"main": [
[
{
"node": "Convert to File",
"type": "main",
"index": 0
}
]
]
},
"AI Agent": {
"main": [
[]
]
},
"Markdown": {
"main": [
[
{
"node": "Code",
"type": "main",
"index": 0
}
]
]
},
"Aggregate1": {
"main": [
[
{
"node": "Translator Agent",
"type": "main",
"index": 0
}
]
]
},
"Analyzer Agent": {
"main": [
[
{
"node": "Markdown",
"type": "main",
"index": 0
},
{
"node": "AI Agent",
"type": "main",
"index": 0
},
{
"node": "Information Extractor",
"type": "main",
"index": 0
},
{
"node": "Convert to File4",
"type": "main",
"index": 0
}
]
]
},
"Convert to File": {
"main": [
[
{
"node": "Gmail",
"type": "main",
"index": 0
}
]
]
},
"Convert to File4": {
"main": [
[
{
"node": "Pinecone Vector Store",
"type": "main",
"index": 0
}
]
]
},
"Loop Over Items1": {
"main": [
[
{
"node": "Aggregate1",
"type": "main",
"index": 0
}
],
[
{
"node": "Parsing the document",
"type": "main",
"index": 0
}
]
]
},
"Translator Agent": {
"main": [
[
{
"node": "Analyzer Agent",
"type": "main",
"index": 0
},
{
"node": "Convert to File4",
"type": "main",
"index": 0
}
]
]
},
"Default Data Loader": {
"ai_document": [
[
{
"node": "Pinecone Vector Store",
"type": "ai_document",
"index": 0
}
]
]
},
"On form submission4": {
"main": [
[
{
"node": "split the binary item",
"type": "main",
"index": 0
}
]
]
},
"Parsing the document": {
"main": [
[
{
"node": "Check the parsing status",
"type": "main",
"index": 0
}
]
]
},
"Provide the markdown": {
"main": [
[
{
"node": "Loop Over Items1",
"type": "main",
"index": 0
}
]
]
},
"split the binary item": {
"main": [
[
{
"node": "Loop Over Items1",
"type": "main",
"index": 0
}
]
]
},
"Pinecone Vector Store1": {
"ai_vectorStore": [
[
{
"node": "Vector Store Retriever",
"type": "ai_vectorStore",
"index": 0
}
]
]
},
"Vector Store Retriever": {
"ai_retriever": [
[
{
"node": "Question and Answer Chain",
"type": "ai_retriever",
"index": 0
}
]
]
},
"Check the parsing status": {
"main": [
[
{
"node": "If2",
"type": "main",
"index": 0
}
]
]
},
"Embeddings Mistral Cloud": {
"ai_embedding": [
[
{
"node": "Pinecone Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Google Gemini Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Embeddings Mistral Cloud1": {
"ai_embedding": [
[
{
"node": "Pinecone Vector Store1",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Google Gemini Chat Model1": {
"ai_languageModel": [
[
{
"node": "Information Extractor",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Google Gemini Chat Model2": {
"ai_languageModel": [
[
{
"node": "Question and Answer Chain",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Google Gemini Chat Model3": {
"ai_languageModel": [
[
{
"node": "AI Agent1",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Google Gemini Chat Model5": {
"ai_languageModel": [
[
{
"node": "Translator Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Google Gemini Chat Model6": {
"ai_languageModel": [
[
{
"node": "Analyzer Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Question and Answer Chain": {
"main": [
[
{
"node": "AI Agent1",
"type": "main",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "Question and Answer Chain",
"type": "main",
"index": 0
}
]
]
},
"Recursive Character Text Splitter": {
"ai_textSplitter": [
[
{
"node": "Default Data Loader",
"type": "ai_textSplitter",
"index": 0
}
]
]
}
}
}
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
How this works
Streamline your document processing by automating the extraction of key information from submitted forms, saving hours of manual review and reducing errors in data handling. This workflow suits teams managing high volumes of incoming documents, such as legal firms or customer support departments, by intelligently analysing content with Google Gemini's AI capabilities. Upon form submission, it triggers a batch loop to process items, aggregates results, and uses HTTP requests to parse and verify documents before integrating with Gmail for notifications.
Use this workflow when dealing with repetitive form-based document intake that requires AI-driven summarisation or extraction, particularly for unstructured data like PDFs or scans. Avoid it for simple data entry without AI needs, or when real-time processing isn't essential due to its batch-oriented design. Common variations include swapping Google Gemini for another LLM model or adding custom email templates in Gmail for varied output formats.
About this workflow
My workflow 3. Uses formTrigger, splitInBatches, lmChatGoogleGemini, httpRequest. Event-driven trigger; 36 nodes.
Source: https://github.com/Zie619/n8n-workflows — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
This comprehensive workflow bundle is designed as a powerful starter kit, enabling you to build a multi-functional AI assistant on Telegram. It seamlessly integrates AI-powered voice interactions, an
Telegram Trigger, Telegram, OpenAI +19
This intelligent chatbot leverages cutting-edge financial APIs and AI-driven analysis to deliver comprehensive stock research reports. Get instant access to professional-grade investment analysis that
Tool Think, Supabase Vector Store, OpenAI Embeddings +15
This n8n template automatically classifies incoming emails (Sales, Support, Internal, Finance, Promotions) and routes them to a dedicated OpenAI LLM Agent for processing. Depending on the category, th
OpenAI, Gmail, Text Classifier +16
This simple philosophy changes the way we think about automated sales agents. Context changes everything. In this 4-part workflow, we start by creating a knowledge base that will act as context across
Pinecone Vector Store, Document Default Data Loader, Text Splitter Recursive Character Text Splitter +12
Code Extractfromfile. Uses manualTrigger, sort, httpRequest, compression. Event-driven trigger; 50 nodes.
HTTP Request, Compression, Edit Image +15