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 →
{
"name": "LLM Testing",
"nodes": [
{
"parameters": {
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"typeVersion": 1.1,
"position": [
-380,
540
],
"id": "5792dafb-f847-492f-869a-d2228f816bd6",
"name": "When chat message received"
},
{
"parameters": {
"name": "nvidia",
"description": "retrieves data about nvidia earnings report"
},
"type": "@n8n/n8n-nodes-langchain.toolVectorStore",
"typeVersion": 1,
"position": [
560,
180
],
"id": "6960ff1b-218f-4ce7-b26f-f1ea2cddb8fb",
"name": "nvidia"
},
{
"parameters": {
"pineconeIndex": {
"__rl": true,
"value": "sample",
"mode": "list",
"cachedResultName": "sample"
},
"options": {
"pineconeNamespace": "nvidia"
}
},
"type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
"typeVersion": 1,
"position": [
860,
180
],
"id": "2c0b680b-6f42-44d5-b07a-f27ee7c0d04e",
"name": "Pinecone Vector Store",
"credentials": {
"pineconeApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"name": "nvidia",
"description": "retrieves data about nvidia earnings report"
},
"type": "@n8n/n8n-nodes-langchain.toolVectorStore",
"typeVersion": 1,
"position": [
560,
520
],
"id": "7e6879d3-de58-45d1-baba-28789fe1b262",
"name": "nvidia1"
},
{
"parameters": {
"pineconeIndex": {
"__rl": true,
"value": "sample",
"mode": "list",
"cachedResultName": "sample"
},
"options": {
"pineconeNamespace": "nvidia"
}
},
"type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
"typeVersion": 1,
"position": [
860,
520
],
"id": "d34166ae-c985-422d-994b-bca22c0b416c",
"name": "Pinecone Vector Store1",
"credentials": {
"pineconeApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"typeVersion": 1.2,
"position": [
880,
680
],
"id": "87303ce2-7cd0-4568-a395-9b6add58ce33",
"name": "Embeddings OpenAI1",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"model": "gpt-4o",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1.1,
"position": [
200,
700
],
"id": "7d338a2b-c8d5-401c-a094-81ed74e5e014",
"name": "GPT-4o",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"typeVersion": 1.2,
"position": [
880,
360
],
"id": "4c174591-543c-4a72-9f5f-9c6cb1565344",
"name": "Embeddings OpenAI",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatAnthropic",
"typeVersion": 1.2,
"position": [
180,
360
],
"id": "33ad68d1-790f-467e-82be-d15cfebff7e9",
"name": "Claude 3.5 Sonnet",
"credentials": {
"anthropicApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"options": {
"systemMessage": "=# Overview \nYou are an AI agent responsible for retrieving and summarizing NVIDIA's financial and earnings information. \n\n## Context \n- The agent uses the \"nvidia\" tool to access up-to-date data on NVIDIA's financials, including revenue, earnings, and market performance. \n- Responses should be concise, accurate, and focused on the requested metrics or insights. \n\n## Instructions \n1. Identify the specific financial metric or information requested by the user. \n2. Query the \"nvidia\" tool for the relevant data. \n3. Summarize the findings in a clear and professional manner. \n\n## Tools \n- NVIDIA financials and earnings tool (\"nvidia\"). \n\n## Examples \n- Input: \"Provide NVIDIA's Q4 earnings report summary.\" \n- Output: \"NVIDIA's Q4 earnings were $2.5 billion, with a 12% year-over-year growth. Revenue was $8.3 billion.\" \n\n- Input: \"What was NVIDIA's revenue in the last fiscal year?\" \n- Output: \"NVIDIA's revenue for the last fiscal year was $33 billion, marking a 20% increase from the previous year.\" \n\n## SOP (Standard Operating Procedure) \n1. Parse the user's query to determine the specific financial details required. \n2. Use the \"nvidia\" tool to retrieve the latest data. \n3. Cross-check and verify the data for accuracy. \n4. Provide a concise summary in response to the user's query. \n\n## Final Notes \n- Always ensure the data is current and relevant to the query. \n- Avoid speculation; report only factual information retrieved from the \"nvidia\" tool. \n"
}
},
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 1.7,
"position": [
180,
500
],
"id": "b4328a17-373c-462d-bca3-fb9314598177",
"name": "GPT-4o Agent"
},
{
"parameters": {
"options": {
"systemMessage": "=# Overview \nYou are an AI agent responsible for retrieving and summarizing NVIDIA's financial and earnings information. \n\n## Context \n- The agent uses the \"nvidia\" tool to access up-to-date data on NVIDIA's financials, including revenue, earnings, and market performance. \n- Responses should be concise, accurate, and focused on the requested metrics or insights. \n\n## Instructions \n1. Identify the specific financial metric or information requested by the user. \n2. Query the \"nvidia\" tool for the relevant data. \n3. Summarize the findings in a clear and professional manner. \n\n## Tools \n- NVIDIA financials and earnings tool (\"nvidia\"). \n\n## Examples \n- Input: \"Provide NVIDIA's Q4 earnings report summary.\" \n- Output: \"NVIDIA's Q4 earnings were $2.5 billion, with a 12% year-over-year growth. Revenue was $8.3 billion.\" \n\n- Input: \"What was NVIDIA's revenue in the last fiscal year?\" \n- Output: \"NVIDIA's revenue for the last fiscal year was $33 billion, marking a 20% increase from the previous year.\" \n\n## SOP (Standard Operating Procedure) \n1. Parse the user's query to determine the specific financial details required. \n2. Use the \"nvidia\" tool to retrieve the latest data. \n3. Cross-check and verify the data for accuracy. \n4. Provide a concise summary in response to the user's query. \n\n## Final Notes \n- Always ensure the data is current and relevant to the query. \n- Avoid speculation; report only factual information retrieved from the \"nvidia\" tool. \n"
}
},
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 1.7,
"position": [
180,
160
],
"id": "0ecbf39d-1212-4ee2-857a-bd2da1cab29b",
"name": "Claude 3.5 Sonnet Agent"
},
{
"parameters": {
"name": "nvidia",
"description": "retrieves data about nvidia earnings report"
},
"type": "@n8n/n8n-nodes-langchain.toolVectorStore",
"typeVersion": 1,
"position": [
560,
860
],
"id": "a533d282-f346-4830-8da4-f323c9659f61",
"name": "nvidia2"
},
{
"parameters": {
"pineconeIndex": {
"__rl": true,
"value": "sample",
"mode": "list",
"cachedResultName": "sample"
},
"options": {
"pineconeNamespace": "nvidia"
}
},
"type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
"typeVersion": 1,
"position": [
860,
860
],
"id": "2717272f-77af-44b2-9bd8-16acf5994227",
"name": "Pinecone Vector Store2",
"credentials": {
"pineconeApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"typeVersion": 1.2,
"position": [
880,
1020
],
"id": "738be7f8-3fc5-4603-bd32-e0281b0629d9",
"name": "Embeddings OpenAI2",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"options": {
"systemMessage": "=# Overview \nYou are an AI agent responsible for retrieving and summarizing NVIDIA's financial and earnings information. \n\n## Context \n- The agent uses the \"nvidia\" tool to access up-to-date data on NVIDIA's financials, including revenue, earnings, and market performance. \n- Responses should be concise, accurate, and focused on the requested metrics or insights. \n\n## Instructions \n1. Identify the specific financial metric or information requested by the user. \n2. Query the \"nvidia\" tool for the relevant data. \n3. Summarize the findings in a clear and professional manner. \n\n## Tools \n- NVIDIA financials and earnings tool (\"nvidia\"). \n\n## Examples \n- Input: \"Provide NVIDIA's Q4 earnings report summary.\" \n- Output: \"NVIDIA's Q4 earnings were $2.5 billion, with a 12% year-over-year growth. Revenue was $8.3 billion.\" \n\n- Input: \"What was NVIDIA's revenue in the last fiscal year?\" \n- Output: \"NVIDIA's revenue for the last fiscal year was $33 billion, marking a 20% increase from the previous year.\" \n\n## SOP (Standard Operating Procedure) \n1. Parse the user's query to determine the specific financial details required. \n2. Use the \"nvidia\" tool to retrieve the latest data. \n3. Cross-check and verify the data for accuracy. \n4. Provide a concise summary in response to the user's query. \n\n## Final Notes \n- Always ensure the data is current and relevant to the query. \n- Avoid speculation; report only factual information retrieved from the \"nvidia\" tool. \n"
}
},
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 1.7,
"position": [
160,
840
],
"id": "1db0a232-fb95-4c1a-a900-2f44767ae90a",
"name": "GPT-4o Agent1"
},
{
"parameters": {
"modelName": "models/gemini-2.0-flash-exp",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"typeVersion": 1,
"position": [
160,
1040
],
"id": "9f08f95b-0a10-4754-9d1d-60b807680dc9",
"name": "Gemini Flash 2.0",
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"modelName": "models/gemini-2.0-flash-exp",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"typeVersion": 1,
"position": [
620,
1040
],
"id": "fabe7920-1c92-4ce5-80b1-8cf869d576eb",
"name": "Gemini Flash 2.0_",
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"model": "gpt-4o",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1.1,
"position": [
580,
700
],
"id": "d2e13319-85c0-48c6-b252-c476965410d7",
"name": "GPT-4o_",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatAnthropic",
"typeVersion": 1.2,
"position": [
620,
340
],
"id": "bc54a0df-8baa-4db3-9473-52c3e64f9fbf",
"name": "Claude 3.5 Sonnet_",
"credentials": {
"anthropicApi": {
"name": "<your credential>"
}
}
}
],
"connections": {
"When chat message received": {
"main": [
[]
]
},
"nvidia": {
"ai_tool": [
[
{
"node": "Claude 3.5 Sonnet Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Pinecone Vector Store": {
"ai_vectorStore": [
[
{
"node": "nvidia",
"type": "ai_vectorStore",
"index": 0
}
]
]
},
"nvidia1": {
"ai_tool": [
[
{
"node": "GPT-4o Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Pinecone Vector Store1": {
"ai_vectorStore": [
[
{
"node": "nvidia1",
"type": "ai_vectorStore",
"index": 0
}
]
]
},
"Embeddings OpenAI1": {
"ai_embedding": [
[
{
"node": "Pinecone Vector Store1",
"type": "ai_embedding",
"index": 0
}
]
]
},
"GPT-4o": {
"ai_languageModel": [
[
{
"node": "GPT-4o Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Embeddings OpenAI": {
"ai_embedding": [
[
{
"node": "Pinecone Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Claude 3.5 Sonnet": {
"ai_languageModel": [
[
{
"node": "Claude 3.5 Sonnet Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"nvidia2": {
"ai_tool": [
[
{
"node": "GPT-4o Agent1",
"type": "ai_tool",
"index": 0
}
]
]
},
"Pinecone Vector Store2": {
"ai_vectorStore": [
[
{
"node": "nvidia2",
"type": "ai_vectorStore",
"index": 0
}
]
]
},
"Embeddings OpenAI2": {
"ai_embedding": [
[
{
"node": "Pinecone Vector Store2",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Gemini Flash 2.0": {
"ai_languageModel": [
[
{
"node": "GPT-4o Agent1",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Gemini Flash 2.0_": {
"ai_languageModel": [
[
{
"node": "nvidia2",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"GPT-4o_": {
"ai_languageModel": [
[
{
"node": "nvidia1",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Claude 3.5 Sonnet_": {
"ai_languageModel": [
[
{
"node": "nvidia",
"type": "ai_languageModel",
"index": 0
}
]
]
}
},
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "ab0ea85a-10b3-46ed-a263-c388de8b5998",
"meta": {
"templateCredsSetupCompleted": true
},
"id": "CgLalQnT5EZXMaMb",
"tags": []
}
Credentials you'll need
Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.
anthropicApigooglePalmApiopenAiApipineconeApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
How this works
This workflow enables developers and AI enthusiasts to rigorously test large language models by simulating interactive conversations and evaluating responses against a knowledge base stored in Pinecone. It delivers immediate value through structured feedback on model accuracy, coherence, and relevance, helping refine prompts or identify biases without manual oversight. The core step involves the chat trigger capturing inputs, followed by OpenAI embeddings and the lmChatOpenAi node generating and scoring outputs in a 19-node chain that integrates vector stores for efficient retrieval.
Use this workflow when prototyping LLM applications that require real-time testing, such as chatbots or Q&A systems, especially if you need to benchmark multiple models like GPT-4o and Anthropic's offerings. Avoid it for production environments lacking Pinecone setup or when simple one-off queries suffice, as the full chain demands configuration. Common variations include swapping embeddings for custom models or adding nodes for logging test results to a spreadsheet.
About this workflow
LLM Testing. Uses chatTrigger, toolVectorStore, vectorStorePinecone, embeddingsOpenAi. Chat trigger; 19 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.
Advanced Ai Demo Presented At Ai Developers 14 Meetup. Uses slack, stickyNote, textSplitterRecursiveCharacterTextSplitter, embeddingsOpenAi. Chat trigger; 39 nodes.
Slack, Text Splitter Recursive Character Text Splitter, OpenAI Embeddings +14
Advanced Ai Demo (Presented At Ai Developers #14 Meetup). Uses slack, stickyNote, textSplitterRecursiveCharacterTextSplitter, embeddingsOpenAi. Chat trigger; 39 nodes.
Slack, Text Splitter Recursive Character Text Splitter, OpenAI Embeddings +14
Workflow 2358. Uses slack, textSplitterRecursiveCharacterTextSplitter, embeddingsOpenAi, documentDefaultDataLoader. Chat trigger; 39 nodes.
Slack, Text Splitter Recursive Character Text Splitter, OpenAI Embeddings +14
2358. Uses slack, textSplitterRecursiveCharacterTextSplitter, embeddingsOpenAi, documentDefaultDataLoader. Chat trigger; 39 nodes.
Slack, Text Splitter Recursive Character Text Splitter, OpenAI Embeddings +14
This workflow was presented at the AI Developers meet up in San Fransico on 24 July, 2024. Categorize incoming Gmail emails and assign custom Gmail labels. This example uses the Text Classifier node,
Slack, Text Splitter Recursive Character Text Splitter, OpenAI Embeddings +14