From 9daf07b72d653acd3a4217558ef4c5f9135fa877 Mon Sep 17 00:00:00 2001
From: Artur Mukhamadiev <muhamadiev1@gmail.com>
Date: Mon, 16 Mar 2026 13:40:46 +0300
Subject: [PATCH] Update Ollama prompt and crawler sources

- crawlers.yml appended with more google scholar topics, removed habr AI
- in LLM prompt removed C++ trends relation and changed web rendering to
  web engine
---
 src/crawlers.yml                 | 23 ++++++++++++++++-------
 src/processor/ollama_provider.py |  4 ++--
 2 files changed, 18 insertions(+), 9 deletions(-)

diff --git a/src/crawlers.yml b/src/crawlers.yml
index 6bcadbc..c0d8ee0 100644
--- a/src/crawlers.yml
+++ b/src/crawlers.yml
@@ -1,7 +1,4 @@
 crawlers:
-  - type: rss
-    url: "https://habr.com/ru/rss/hubs/artificial_intelligence/articles/?fl=ru"
-    source: "Habr AI"
   - type: rss
     url: "https://www.nature.com/nature.rss"
     source: "Nature"
@@ -102,9 +99,21 @@ crawlers:
     source: "SciRate"
   - type: scholar
     url: "https://scholar.google.com/"
-    source: "Google Scholar"
-    query: "WebGPU machine learning"
+    source: "Google Scholar WebGPU"
+    query: "WebGPU"
   - type: scholar
     url: "https://scholar.google.com/"
-    source: "Google Scholar"
-    query: "NPU acceleration"
\ No newline at end of file
+    source: "Google Scholar NPU"
+    query: "NPU acceleration"
+  - type: scholar
+    url: "https://scholar.google.com/"
+    source: "Google Scholar Browsers"
+    query: "Browsers | Lightweight Web Engine"
+  - type: scholar
+    url: "https://scholar.google.com/"
+    source: "Google Scholar Performance"
+    query: "Software Optimization"
+  - type: scholar
+    url: "https://scholar.google.com/"
+    source: "Google Scholar BMI"
+    query: "Brain-machine interface (IoT|Webengine|Linux)"
\ No newline at end of file
diff --git a/src/processor/ollama_provider.py b/src/processor/ollama_provider.py
index 7ffbda4..08a2427 100644
--- a/src/processor/ollama_provider.py
+++ b/src/processor/ollama_provider.py
@@ -32,11 +32,11 @@ class OllamaProvider(ILLMProvider):
             "1. 'relevance_score' (integer 0-10): Score the potential impact on our R&D targets.\n"
             "2. 'summary_ru' (string): A concise technical summary in Russian (2-3 sentences). Explain methodology, core innovation, and practical relevance.\n"
             "3. 'anomalies_detected' (list of strings): Identify state-of-the-art (SOTA) breakthroughs, strategic disruptions, new standards, or unexpected results. Return [] if none.\n"
-            "4. 'category' (string): Must be exactly one of: 'WebEngines/Browsers', 'System Tools (SWE)', 'Middleware Platforms', 'Cross-Platform', 'SmartTV/IoT', 'Samsung New Technologies', 'C++ Trends', 'Competitors', 'Academic/SOTA', 'Other'.\n\n"
+            "4. 'category' (string): Must be exactly one of: 'WebEngines/Browsers', 'System Tools (SWE)', 'Middleware Platforms', 'Cross-Platform', 'SmartTV/IoT', 'Samsung New Technologies', 'Competitors', 'Academic/SOTA', 'Other'.\n\n"
             
             "SCORING GUIDELINES ('relevance_score'):\n"
             "Start with a base score:\n"
-            "- 9-10 (Core R&D): Breakthroughs in web rendering engines, cross-platform frameworks, modern C++ paradigms relevant to system tools, or SOTA research in web/middleware.\n"
+            "- 9-10 (Core R&D): Breakthroughs in web engines, cross-platform frameworks, system tools, or SOTA research in web engines/middleware.\n"
             "- 7-8 (Ecosystem): Solid improvements applicable to Automotive Content Platforms, IoT ecosystems, SmartTV OS, or major SWE tool improvements.\n"
             "- 4-6 (Peripheral): Theoretical work, general programming news, or technologies with distant industrial application.\n"
             "- 0-3 (Out of Scope): Pure medicine, social sciences, consumer electronics reviews, pure audio/acoustics.\n\n"