CI: Smaller embedding model for Ollama test

.github/workflows/test_ollama.yml

@@ -7,13 +7,8 @@ jobs:
 
   run_ollama_test:
 
-    # needs 16 Gb RAM for phi4
+    
     runs-on: buildjet-4vcpu-ubuntu-2204
-#    services:
-#      ollama:
-#        image: ollama/ollama
-#        ports:
-#          - 11434:11434
 
     steps:
       - name: Checkout repository
@@ -28,14 +23,6 @@ jobs:
         run: |
           uv add torch
 
-#      - name: Install ollama
-#        run: curl -fsSL https://ollama.com/install.sh | sh
-#      - name: Run ollama
-#        run: |
-#          ollama serve --openai &
-#          ollama pull llama3.2 &
-#          ollama pull avr/sfr-embedding-mistral:latest
-
       - name: Start Ollama container
         run: |
           docker run -d --name ollama -p 11434:11434 ollama/ollama
@@ -60,15 +47,15 @@ jobs:
 
       - name: Pull required Ollama models
         run: |
-          curl -X POST http://localhost:11434/api/pull -d '{"name": "phi4"}'
-          curl -X POST http://localhost:11434/api/pull -d '{"name": "avr/sfr-embedding-mistral:latest"}'
+          curl -X POST http://localhost:11434/api/pull -d '{"name": "phi3:mini"}'
+          curl -X POST http://localhost:11434/api/pull -d '{"name": "nomic-embed-text"}'
 
       - name: Call ollama API
         run: |
           curl -X POST http://localhost:11434/v1/chat/completions \
             -H "Content-Type: application/json" \
             -d '{
-              "model": "phi4",
+              "model": "phi3:mini",
               "stream": false,
               "messages": [
                 { "role": "system", "content": "You are a helpful assistant." },
@@ -78,7 +65,7 @@ jobs:
           curl -X POST http://127.0.0.1:11434/api/embed \
             -H "Content-Type: application/json" \
              -d '{
-              "model": "avr/sfr-embedding-mistral:latest",
+              "model": "nomic-embed-text",
             "input": "This is a test sentence to generate an embedding."
             }'
 
@@ -95,10 +82,10 @@ jobs:
           LLM_PROVIDER: "ollama"
           LLM_API_KEY: "ollama"
           LLM_ENDPOINT: "http://localhost:11434/v1/"
-          LLM_MODEL: "phi4"
+          LLM_MODEL: "phi3:mini"
           EMBEDDING_PROVIDER: "ollama"
-          EMBEDDING_MODEL: "avr/sfr-embedding-mistral:latest"
+          EMBEDDING_MODEL: "nomic-embed-text"
           EMBEDDING_ENDPOINT: "http://localhost:11434/api/embed"
-          EMBEDDING_DIMENSIONS: "4096"
-          HUGGINGFACE_TOKENIZER: "Salesforce/SFR-Embedding-Mistral"
+          EMBEDDING_DIMENSIONS: "768"
+          HUGGINGFACE_TOKENIZER: "nomic-ai/nomic-embed-text-v1"
         run: uv run python ./examples/python/simple_example.py