refactor2

config.template

@@ -80,14 +80,17 @@ ollama = False
 # ollamaModel = gemma2:2b
 # server instance to use (defaults to local machine install)
 ollamaHostName = http://localhost:11434
+
 # Produce LLM replies to messages that aren't commands?
 # If False, the LLM only replies to the "ask:" and "askai" commands.
 llmReplyToNonCommands = True
-# if True, the input is sent raw to the LLM, if False uses legacy template query
+# if True, the input is sent raw to the LLM, if False uses SYSTEM prompt
 rawLLMQuery = True
+
 # Enable Wikipedia/Kiwix integration with LLM for RAG (Retrieval Augmented Generation)
 # When enabled, LLM will automatically search Wikipedia/Kiwix and include context in responses
 llmUseWikiContext = False
+
 # Use OpenWebUI instead of direct Ollama API (enables advanced RAG features)
 useOpenWebUI = False
 # OpenWebUI server URL (e.g., http://localhost:3000)

modules/llm.md

@@ -0,0 +1,45 @@
+# How do I use this thing?
+This is not a full turnkey setup for Docker yet?
+
+
+# Ollama local
+```bash
+# bash
+curl -fsSL https://ollama.com/install.sh | sh
+# docker
+docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -e OLLAMA_API_BASE_URL=http://host.docker.internal:11434 open-webui/open-webui
+```
+
+```ini
+#service file addition
+# https://github.com/ollama/ollama/issues/703
+[Service]
+Environment="OLLAMA_HOST=0.0.0.0:11434"
+```
+## validation
+http://IP::11434
+`Ollama is running`
+
+# OpenWebUI (docker)
+```bash
+## ollama in docker
+docker run -d -p 3000:8080 --gpus all -v open-webui:/app/backend/data --name open-webui ghcr.io/open-webui/open-webui:cuda
+
+## external ollama
+docker run -d -p 3000:8080 -e OLLAMA_BASE_URL=https://IP:11434 -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main
+```
+wait for engine to build, update the config.ini for the bot
+
+```ini
+# Use OpenWebUI instead of direct Ollama API (enables advanced RAG features)
+useOpenWebUI = True
+# OpenWebUI server URL (e.g., http://localhost:3000)
+openWebUIURL = http://IP:3000
+```
+
+## validation
+http://IP:3000
+make a new admin user.
+validate you have models imported or that the system is working for query.
+set api endpoint [OpenWebUI API](https://docs.openwebui.com/getting-started/api-endpoints)
+to quickly get started, go to admin ->settings ->connections ->Manage OpenAI API Connections ->Auth Type None

modules/llm.py

@@ -201,7 +201,7 @@ def send_openwebui_query(prompt, model=None, max_tokens=450, context=''):
     }
     
     try:
-        result = requests.post(openWebUIChatAPI, headers=headers, json=data, timeout=10)
+        result = requests.post(openWebUIChatAPI, headers=headers, json=data, timeout=urlTimeoutSeconds * 4)
         if result.status_code == 200:
             result_json = result.json()
             # OpenWebUI returns OpenAI-compatible format
@@ -274,15 +274,14 @@ def llm_query(input, nodeID=0, location_name=None, init=False):
         # classic model for gemma2, deepseek-r1, etc
         logger.debug(f"System: Using SYSTEM model framework, ideally for gemma2, deepseek-r1, etc")
 
-
-    # Remove command bang if present
-    if cmdBang:
-        input = input[1:].strip()
-
     if not location_name:
         location_name = "no location provided "
+
+    # Remove command bang if present
+    if cmdBang and input.startswith('!'):
+        input = input.strip('!').strip()
     
-    # remove askai: and ask: from the input
+    # Remove any trap words from the start of the input
     for trap in trap_list_llm:
         if input.lower().startswith(trap):
             input = input[len(trap):].strip()