Describe the problem/error/question
Gemini Chat Model sometimes works, and other times it doesn’t.
What is the error message (if any)?
I get a trim error using 2.5 Pro. I get ‘The service is receiving too many requests from you’ when I use an exp model, or a flash model. It randomly works, but at the moment, it’s continously failing to work.
Please share your workflow
{
“nodes”: [
{
“parameters”: {
“schemaType”: “manual”,
“inputSchema”: “{\n “priority_words”: “array”,\n “all_keywords”: “array”,\n “industry”: “array”\n}”
},
“type”: “@n8n/n8n-nodes-langchain.outputParserStructured”,
“typeVersion”: 1.3,
“position”: [
-400,
336
],
“id”: “621bec56-bf1d-4fcd-821f-322d87b098ea”,
“name”: “Structured Output Parser”
},
{
“parameters”: {
“modelName”: “models/gemini-2.0-pro-exp”,
“options”: {
“temperature”: 0.1
}
},
“type”: “@n8n/n8n-nodes-langchain.lmChatGoogleGemini”,
“typeVersion”: 1,
“position”: [
-624,
336
],
“id”: “ecfdb3ae-766a-4e88-bd87-d17e5828afed”,
“name”: “Google Gemini Chat Model”,
“credentials”: {
“googlePalmApi”: {
“id”: “B9wRfzpRPcTa1dZ9”,
“name”: “Google Gemini(PaLM) Api account”
}
}
},
{
“parameters”: {
“promptType”: “define”,
“text”: “=abc,
“hasOutputParser”: true,
“options”: {}
},
“type”: “@n8n/n8n-nodes-langchain.agent”,
“typeVersion”: 2.1,
“position”: [
-608,
160
],
“id”: “4ecb0781-109e-4345-ad72-0d27380a7784”,
“name”: “Get Keywords”,
“executeOnce”: true,
“retryOnFail”: false
}
],
“connections”: {
“Structured Output Parser”: {
“ai_outputParser”: [
[
{
“node”: “Get Keywords”,
“type”: “ai_outputParser”,
“index”: 0
}
]
]
},
“Google Gemini Chat Model”: {
“ai_languageModel”: [
[
{
“node”: “Get Keywords”,
“type”: “ai_languageModel”,
“index”: 0
}
]
]
},
“Get Keywords”: {
“main”: [
]
}
},
“pinData”: {},
“meta”: {
“templateCredsSetupCompleted”: true,
“instanceId”: “10b25450b35b5ded2d77feae47bf68bccc734781d23ae371a81ff821307daeda”
}
}
Share the output returned by the last node
System: IMPORTANT: For your response to user, you MUST use the `format_final_json_response` tool with your complete answer formatted according to the required schema. Do not attempt to format the JSON manually - always use this tool. Your response will be rejected if it is not properly formatted through this tool. Only use this tool once you are ready to provide your final answer.\nHuman: Step 1: Analyze the ‘INFORMATION’ thoroughly to extract ALL keywords. Strictly adhere to ALL RULES provided.\nStep 2: Prioritize the keywords alphabetically and count the total number of unique keywords.\nStep 3: Create a category called PRIORITY WORDS that includes:\n- Industry from the job description.\n- Separate any combined industry terms (e.g., ‘auto insurance’) into distinct categories (e.g., ‘Automotive,’ ‘Insurance’).\n\nINFORMATION TO ANALYZE:\n\n\nName this output ‘JD Keywords.’\n\n\nRULES for ALL steps:\n1. Include:\n- Core responsibilities and skills without qualifiers (e.g., ‘Process Improvement’ instead of ‘Process Improvement Expert’).\n- Both required and preferred skills (e.g., ‘Project Management,’ ‘Agile’).\n- Industry-specific terminology (e.g., ‘FDA Regulations’).\n- Technical skills and certifications (e.g., ‘Salesforce,’ ‘PMP’).\n- Job titles without hierarchical terms (e.g., ‘Marketing’ instead of ‘Marketing Manager’).\n- Soft skills only if explicitly mentioned (e.g., ‘Leadership,’ ‘Communication’).\n- Cross-functional collaboration terms (e.g., ‘Cross-functional’).\n- Project-specific terms or deliverables in their simplest form (e.g., ‘Business Case’).\n- Tools, software, or platforms (e.g., ‘Tableau,’ ‘SQL’).\n- Performance metrics or deliverables in their simplest form (e.g., ‘Efficiency’).\n2. Exclude:\n- Pre-screening qualifications (e.g., ‘5+ years of experience’).\n- Generic, filler terms (e.g., ‘Passionate,’ ‘Motivated’).\n- Locations, durations, and dates.\n- Terms like ‘Full-Time’ or ‘Part-Time’.\n- Headings and sub-headings (e.g., ‘Accountabilities’, ‘Key Responsibilities’).\n3. Split paired keywords into separate, individual terms (e.g., ‘Strategy,’ ‘Organizational Design’).\n4. Break down overly long or complex phrases into simpler components.\n5. Adhere strictly to the INFORMATION provided without assumptions.\n6. Double-check each keyword against the INFORMATION, instructions, and rules before including.\n7. Conduct two passes for each step to ensure completeness.\n9. Do not include any terms not explicitly mentioned in the INFORMATION provided.\n\nAnalyze the job description and extract keywords according to the rules. Return the results in the required JSON format called ‘JD Keywords’.\n\nCRITICAL: Return your analysis as a JSON object with this structure:\n{\n “priority_words”: [“array of priority terms”],\n “all_keywords”: [“alphabetical array of all keywords”], \n “industry”: [“array of industry terms”],\n}
Information on your n8n setup
n8n version: 1.106.3
Database (default: SQLite): SQLite
n8n EXECUTIONS_PROCESS setting (default: own, main): default
Running n8n via (Docker, npm, n8n cloud, desktop app): npm
Operating system: Windows