rowboat/apps/rowboat_agents/tests/sample_requests/tmp4.json
2025-05-09 09:39:09 +05:30

200 lines
No EOL
8.7 KiB
JSON
Raw Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"messages": [
{
"role": "system",
"content": ""
},
{
"version": "v1",
"chatId": "",
"createdAt": "2025-05-08T07:06:48.280Z",
"role": "assistant",
"content": "How can I help you today?",
"agenticSender": "Example Agent",
"agenticResponseType": "external"
},
{
"role": "user",
"content": "Tell me about article 1",
"version": "v1",
"chatId": "",
"createdAt": "2025-05-08T07:06:53.518Z"
},
{
"version": "v1",
"chatId": "",
"createdAt": "2025-05-08T07:06:55.690Z",
"role": "assistant",
"tool_calls": [
{
"id": "call_uzRd4Y1CeBioJ9h26XeGhCvH",
"function": {
"name": "rag_search",
"arguments": "{\"query\":\"article 1\"}"
},
"type": "function"
}
],
"agenticSender": "Example Agent",
"agenticResponseType": "internal"
},
{
"version": "v1",
"chatId": "",
"createdAt": "2025-05-08T07:06:55.690Z",
"role": "tool",
"content": "{\n \"Information\": [\n {\n \"title\": \"text\",\n \"name\": \"text\",\n \"content\": \"This is article 1.\",\n \"docId\": \"681c50f17e7a18621c7215cd\",\n \"sourceId\": \"681c50f17e7a18621c7215cc\"\n },\n {\n \"title\": \"text\",\n \"name\": \"text\",\n \"content\": \"This is article 2.\",\n \"docId\": \"681c51067e7a18621c7215cf\",\n \"sourceId\": \"681c51067e7a18621c7215ce\"\n },\n {\n \"title\": \"text\",\n \"name\": \"text\",\n \"content\": \"This is article 3.\",\n \"docId\": \"681c51137e7a18621c7215d1\",\n \"sourceId\": \"681c51137e7a18621c7215d0\"\n }\n ]\n}",
"tool_call_id": "call_uzRd4Y1CeBioJ9h26XeGhCvH",
"tool_name": ""
},
{
"version": "v1",
"chatId": "",
"createdAt": "2025-05-08T07:06:57.096Z",
"role": "assistant",
"content": "Article 1 states: \"This is article 1.\"\n\nIf you need more details or information about another article, please let me know!",
"agenticSender": "Example Agent",
"agenticResponseType": "external"
}
],
"lastRequest": {
"projectId": "8e59c4b6-91d2-42e9-8990-41583f4105f1",
"messages": [
{
"content": "",
"role": "system",
"sender": null,
"tool_calls": null,
"tool_call_id": null,
"tool_name": null
},
{
"content": "How can I help you today?",
"role": "assistant",
"sender": "Example Agent",
"tool_calls": null,
"tool_call_id": null,
"tool_name": null,
"response_type": "external"
},
{
"content": "Tell me about article 1",
"role": "user",
"sender": null,
"tool_calls": null,
"tool_call_id": null,
"tool_name": null
}
],
"state": {
"last_agent_name": "Example Agent",
"tokens": {
"total": 0,
"prompt": 0,
"completion": 0
}
},
"agents": [
{
"name": "Example Agent",
"type": "conversation",
"description": "An example agent that uses the rag_search tool to fetch information for customer support queries.",
"instructions": "## 🧑‍💼 Role:\nYou are a helpful customer support assistant who fetches information using the rag_search tool.\n\n---\n## ⚙️ Steps to Follow:\n1. Ask the user what they would like help with.\n2. If the user's query requires information or an answer, use the [@tool:rag_search] tool with the user's question as the query.\n3. Provide the user with an answer based on the information retrieved from the tool.\n4. If the user's issue is about follow-up or requires human support, ask for their email address and let them know someone will contact them soon.\n5. If a question is out of scope, politely inform the user and avoid providing an answer.\n\n---\n## 🎯 Scope:\n✅ In Scope:\n- Answering customer support questions using information from articles.\n- Asking the user their issue and getting their email if needed.\n\n❌ Out of Scope:\n- Questions unrelated to customer support.\n- Providing answers without using the rag_search tool when information is needed.\n\n---\n## 📋 Guidelines:\n✔ Dos:\n- Use [@tool:rag_search](#mention) to fetch accurate information for user queries.\n- Provide clear and concise answers based on the tool's results.\n- Ask for the user's email if the issue requires follow-up.\n\n🚫 Don'ts:\n- Do not provide answers without fetching information when required.\n- Do not ask for details other than the user's email.\n\n# Examples\n- **User** : What is your refund policy?\n - **Agent actions**: Call [@tool:rag_search](#mention)\n - **Agent response**: Our refund policy is as follows: <summary from rag_search results>\n\n- **User** : How can I change my password?\n - **Agent actions**: Call [@tool:rag_search](#mention)\n - **Agent response**: To change your password, follow these steps: <steps from rag_search results>\n\n- **User** : I need help with my order.\n - **Agent actions**: Call [@tool:rag_search](#mention)\n - **Agent response**: Can you please provide more details about your order issue? <additional info from rag_search results if relevant>\n\n- **User** : I want someone to contact me about a billing issue.\n - **Agent response**: Sure, could you please provide your email address so someone from our team can contact you soon?\n\n- **User** : Can you tell me about your subscription plans?\n - **Agent actions**: Call [@tool:rag_search](#mention)\n - **Agent response**: Here are our subscription plans: <details from rag_search results>",
"model": "gpt-4.1",
"controlType": "retain",
"ragDataSources": [
"681c50f17e7a18621c7215cc",
"681c51067e7a18621c7215ce",
"681c51137e7a18621c7215d0"
],
"ragK": 1,
"ragReturnType": "chunks",
"tools": [
"rag_search"
],
"prompts": [],
"connectedAgents": []
}
],
"tools": [
{
"name": "web_search",
"description": "Fetch information from the web based on chat context",
"parameters": {
"type": "object",
"properties": {}
},
"isLibrary": true
},
{
"name": "rag_search",
"description": "Fetch articles with knowledge relevant to the query",
"parameters": {
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "The query to retrieve articles for"
}
},
"required": [
"query"
]
},
"isLibrary": true
}
],
"prompts": [],
"startAgent": "Example Agent",
"mcpServers": [],
"toolWebhookUrl": ""
},
"lastResponse": {
"state": {
"last_agent_name": "Example Agent",
"tokens": {
"total": 1581,
"prompt": 1533,
"completion": 48
}
},
"messages": [
{
"version": "v1",
"chatId": "",
"createdAt": "2025-05-08T07:06:55.690Z",
"role": "assistant",
"tool_calls": [
{
"id": "call_uzRd4Y1CeBioJ9h26XeGhCvH",
"function": {
"name": "rag_search",
"arguments": "{\"query\":\"article 1\"}"
},
"type": "function"
}
],
"agenticSender": "Example Agent",
"agenticResponseType": "internal"
},
{
"version": "v1",
"chatId": "",
"createdAt": "2025-05-08T07:06:55.690Z",
"role": "tool",
"content": "{\n \"Information\": [\n {\n \"title\": \"text\",\n \"name\": \"text\",\n \"content\": \"This is article 1.\",\n \"docId\": \"681c50f17e7a18621c7215cd\",\n \"sourceId\": \"681c50f17e7a18621c7215cc\"\n },\n {\n \"title\": \"text\",\n \"name\": \"text\",\n \"content\": \"This is article 2.\",\n \"docId\": \"681c51067e7a18621c7215cf\",\n \"sourceId\": \"681c51067e7a18621c7215ce\"\n },\n {\n \"title\": \"text\",\n \"name\": \"text\",\n \"content\": \"This is article 3.\",\n \"docId\": \"681c51137e7a18621c7215d1\",\n \"sourceId\": \"681c51137e7a18621c7215d0\"\n }\n ]\n}",
"tool_call_id": "call_uzRd4Y1CeBioJ9h26XeGhCvH",
"tool_name": ""
},
{
"version": "v1",
"chatId": "",
"createdAt": "2025-05-08T07:06:57.096Z",
"role": "assistant",
"content": "Article 1 states: \"This is article 1.\"\n\nIf you need more details or information about another article, please let me know!",
"agenticSender": "Example Agent",
"agenticResponseType": "external"
}
]
}
}