Configure max allowed iterations in research mode via env var

.github/workflows/run_evals.yml

@@ -45,6 +45,11 @@ on:
         required: false
         default: 'gemini-2.0-flash'
         type: string
+      max_research_iterations:
+        description: 'Maximum number of iterations in research mode'
+        required: false
+        default: 5
+        type: number
 
 jobs:
   eval:
@@ -110,6 +115,7 @@ jobs:
           KHOJ_URL: "http://localhost:42110"
           KHOJ_DEFAULT_CHAT_MODEL: ${{ github.event_name == 'workflow_dispatch' && inputs.chat_model || 'gemini-2.0-flash' }}
           KHOJ_LLM_SEED: "42"
+          KHOJ_RESEARCH_ITERATIONS: ${{ github.event_name == 'workflow_dispatch' && inputs.max_research_iterations || 5 }}
           GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}
           SERPER_DEV_API_KEY: ${{ matrix.dataset != 'math500' && secrets.SERPER_DEV_API_KEY }}
           OLOSTEP_API_KEY: ${{ matrix.dataset != 'math500' && secrets.OLOSTEP_API_KEY }}

src/khoj/routers/research.py

@@ -1,4 +1,5 @@
 import logging
+import os
 from datetime import datetime
 from typing import Callable, Dict, List, Optional
 
@@ -160,7 +161,7 @@ async def execute_information_collection(
     query_files: str = None,
 ):
     current_iteration = 0
-    MAX_ITERATIONS = 5
+    MAX_ITERATIONS = int(os.getenv("KHOJ_RESEARCH_ITERATIONS", 5))
     previous_iterations: List[InformationCollectionIteration] = []
     while current_iteration < MAX_ITERATIONS:
         online_results: Dict = dict()