Merge branch 'main' into 6-audio-generation-component

.github/workflows/docs.yaml

@@ -20,7 +20,7 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: '3.10'
-
+          cache: "pip"
       - name: Configure git
         run: |
           git config user.name 'github-actions[bot]'

.github/workflows/lint.yaml

@@ -12,23 +12,21 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/checkout@v4
+      - name: Check out the repository
+        uses: actions/checkout@v4
 
-      - name: Install uv
-        uses: astral-sh/setup-uv@v3
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
 
-      - name: Set up venv
-        run: |
-          uv venv
-          source .venv/bin/activate
-          uv pip install pre-commit
+      - name: Install pre-commit
+        run: pip install pre-commit
 
       - uses: actions/cache@v4
         with:
           path: ~/.cache/pre-commit/
           key: pre-commit-4|${{ env.pythonLocation }}|${{ hashFiles('.pre-commit-config.yaml') }}
 
       - name: pre-commit
-        run: |
-          source .venv/bin/activate
-          pre-commit run --all-files
+        run: pre-commit run --all-files

.github/workflows/tests.yaml

@@ -0,0 +1,28 @@
+name: Tests
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+  workflow_dispatch:
+
+jobs:
+  run-linter:
+    timeout-minutes: 30
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Check out the repository
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+          cache: "pip"
+
+      - name: Install
+        run: pip install -e '.[tests]'
+
+      - name: Run tests
+        run: pytest -v tests

demo/app.py

@@ -16,13 +16,20 @@
 )
 
 PODCAST_PROMPT = """
-You are a helpful podcast writer.
-You will take the input text and generate a conversation between 2 speakers.
-Example of response:
+You are a podcast scriptwriter generating engaging and natural-sounding conversations in JSON format. The script features two speakers:
+Speaker 1: Laura, the main host. She explains topics clearly using anecdotes and analogies, teaching in an engaging and captivating way.
+Speaker 2: Jon, the co-host. He keeps the conversation on track, asks curious follow-up questions, and reacts with excitement or confusion, often using interjections like “hmm” or “umm.”
+Instructions:
+- Write dynamic, easy-to-follow dialogue.
+- Include natural interruptions and interjections.
+- Avoid repetitive phrasing between speakers.
+- Format output as a JSON conversation.
+Example:
 {
-    "Speaker 1": "Welcome to our podcast, where we explore the latest advancements in AI and technology. I'm your host, and today we're going to dive into the exciting world of TrustWorthy AI.",
-    "Speaker 2": "Hi, I'm excited to be here, so what is TrustWorthy AI?",
-    "Speaker 1":"Ah, great question! It is a term used by the European High Level Expert Group on AI. Mozilla defines trustworthy AI as AI that is demonstrably worthy of trust, tech that considers accountability, agency, and individual and collective well-being."
+  "Speaker 1": "Welcome to our podcast! Today, we’re exploring...",
+  "Speaker 2": "Hi Laura! I’m excited to hear about this. Can you explain...",
+  "Speaker 1": "Sure! Imagine it like this...",
+  "Speaker 2": "Oh, that’s cool! But how does..."
 }
 """
 

tests/integration/test_model_load_and_inference.py

@@ -12,12 +12,12 @@ def test_model_load_and_inference_text_to_text():
         "HuggingFaceTB/smollm-135M-instruct-v0.2-Q8_0-GGUF/smollm-135m-instruct-add-basics-q8_0.gguf"
     )
     result = text_to_text(
-        "What is the capital of France?",
+        "Answer to: What is the capital of France?",
         model=model,
         system_prompt="",
     )
     assert isinstance(result, str)
-    assert json.loads(result)["Capital"] == "Paris"
+    assert json.loads(result)
 
 
 def test_model_load_and_inference_text_to_text_no_json():
@@ -37,19 +37,6 @@ def test_model_load_and_inference_text_to_text_no_json():
     assert result.startswith("The capital of France is Paris")
 
 
-def test_model_load_and_inference_text_to_text_stream():
-    model = load_llama_cpp_model(
-        "HuggingFaceTB/smollm-135M-instruct-v0.2-Q8_0-GGUF/smollm-135m-instruct-add-basics-q8_0.gguf"
-    )
-    result = text_to_text_stream(
-        "What is the capital of France?",
-        model=model,
-        system_prompt="",
-    )
-    assert isinstance(result, Iterator)
-    assert json.loads("".join(result))["Capital"] == "Paris"
-
-
 def test_model_load_and_inference_text_to_text_stream_no_json():
     model = load_llama_cpp_model(
         "HuggingFaceTB/smollm-135M-instruct-v0.2-Q8_0-GGUF/smollm-135m-instruct-add-basics-q8_0.gguf"