refactor: model name in various comments, strings etc.

Author: Felipe Campos Penha

initiatives/genai_red_team_handbook/sandboxes/RAG_local/Makefile

@@ -21,7 +21,7 @@ help:
 	@echo "  make format        - Run black and isort formatters"
 	@echo "  make mypy          - Run mypy static type checker"
 	@echo ""
-	@echo "  make ollama-pull   - Pull llama3 model for Ollama"
+	@echo "  make ollama-pull   - Pull gpt-oss:20b model for Ollama"
 	@echo "  make ollama-serve  - Start Ollama server"
 	@echo "  make ingest        - Ingest all PDFs from data/documents/"
 	@echo "  make upload PATH=x - Upload a file to data/documents/ (requires PATH argument)"
@@ -67,7 +67,7 @@ clean:
 	@echo "✅ Cleanup complete!"
 
 ollama-pull:
-	ollama pull llama3
+	ollama pull gpt-oss:20b
 	ollama pull nomic-embed-text
 
 ollama-serve:

initiatives/genai_red_team_handbook/sandboxes/RAG_local/README.md

@@ -75,7 +75,7 @@ graph LR
     
     subgraph "External Services (Local Host)"
         Ollama[Ollama Server<br/>:11434]
-        Model[llama3 Model<br/>config/model.toml]
+        Model[gpt-oss:20b Model<br/>config/model.toml]
         FileStorage[File Storage<br/>data/documents]
     end
     
@@ -182,7 +182,7 @@ To use a different model, simply pull it with `ollama pull <model_name>` and upd
 Controls which LLM model to use:
 ```toml
 [default]
-model = "llama3"  # Change to switch models
+model = "gpt-oss:20b"  # Change to switch models
 
 [ollama]
 base_url = "http://host.containers.internal:11434/v1"
@@ -273,7 +273,7 @@ Run `make help` to see all commands:
 - `make mypy` - Run mypy type checker
 
 **Ollama:**
-- `make ollama-pull` - Pull llama3 model
+- `make ollama-pull` - Pull gpt-oss:20b model
 - `make ollama-serve` - Start Ollama (checks if already running)
 
 ## Testing the Mock API
@@ -290,7 +290,7 @@ curl -X POST http://localhost:8000/v1/chat/completions \
 -H "Content-Type: application/json" \
 -H "Authorization: Bearer sk-mock-key" \
 -d '{
-  "model": "llama3",
+  "model": "gpt-oss:20b",
   "messages": [{"role": "user", "content": "Hello!"}]
 }'
 ```

initiatives/genai_red_team_handbook/sandboxes/RAG_local/app/mocks/openai.py

@@ -49,7 +49,7 @@ class ChatCompletionRequest(BaseModel):
     """Request model for chat completions endpoint.
 
     Attributes:
-        model: Name of the model to use (e.g., "llama3").
+        model: Name of the model to use (e.g., "gpt-oss:20b").
         messages: List of message dictionaries with 'role' and 'content' keys.
         temperature: Sampling temperature between 0 and 2. Defaults to 0.7.
         max_tokens: Maximum number of tokens to generate. Defaults to None.

initiatives/genai_red_team_handbook/sandboxes/RAG_local/config/model.toml

@@ -3,7 +3,7 @@
 # To change which model is used, edit the [default] section below.
 
 [default]
-# CHANGE THIS to switch models (e.g., "llama3", "llama2", "mistral")
+# CHANGE THIS to switch models (e.g., "gpt-oss:20b", "llama2", "mistral")
 model = "gpt-oss:20b"
 
 [ollama]

initiatives/genai_red_team_handbook/sandboxes/llm_local/Makefile

@@ -21,7 +21,7 @@ help:
 	@echo "  make format        - Run black and isort formatters"
 	@echo "  make mypy          - Run mypy static type checker"
 	@echo ""
-	@echo "  make ollama-pull   - Pull llama3 model for Ollama"
+	@echo "  make ollama-pull   - Pull gpt-oss:20b model for Ollama"
 	@echo "  make ollama-serve  - Start Ollama server"
 	@echo ""
 	@echo "Environment:"
@@ -65,7 +65,7 @@ clean:
 	@echo "✅ Cleanup complete!"
 
 ollama-pull:
-	ollama pull llama3
+	ollama pull gpt-oss:20b
 
 ollama-serve:
 	@echo "🔍 Checking if Ollama is running..."

initiatives/genai_red_team_handbook/sandboxes/llm_local/app/mocks/openai.py

@@ -47,7 +47,7 @@ class ChatCompletionRequest(BaseModel):
     """Request model for chat completions endpoint.
 
     Attributes:
-        model: Name of the model to use (e.g., "llama3").
+        model: Name of the model to use (e.g., "gpt-oss:20b").
         messages: List of message dictionaries with 'role' and 'content' keys.
         temperature: Sampling temperature between 0 and 2. Defaults to 0.7.
         max_tokens: Maximum number of tokens to generate. Defaults to None.

initiatives/genai_red_team_handbook/sandboxes/llm_local/config/model.toml

@@ -3,7 +3,7 @@
 # To change which model is used, edit the [default] section below.
 
 [default]
-# CHANGE THIS to switch models (e.g., "llama3", "llama2", "mistral")
+# CHANGE THIS to switch models (e.g., "gpt-oss:20b", "llama2", "mistral")
 model = "gpt-oss:20b"
 
 [ollama]