Merge pull request #535 from jamesbroadhead/ace-review-fixes-main

fix: small correctness/security cleanups in apps-python / python-sdk examples

Author: QuentinAmbard

.github/workflows/ci.yml

@@ -8,6 +8,28 @@ permissions:
   contents: read
 
 jobs:
+  skills-unit-tests:
+    name: databricks-skills unit tests
+    runs-on: linux-ubuntu-latest
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+
+      - uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
+        with:
+          version: "0.11.4"
+
+      - name: Run databricks-skills unit tests
+        run: |
+          if [ -d databricks-skills/.tests ]; then
+            uvx --python 3.11 \
+              --with pytest \
+              --with databricks-sdk \
+              --with requests \
+              pytest databricks-skills/.tests/ -m "not integration" -v
+          else
+            echo "databricks-skills/.tests/ not present on this branch; skipping."
+          fi
+
   lint:
     name: Lint & Format
     runs-on: linux-ubuntu-latest

databricks-skills/databricks-apps-python/examples/fm-minimal-chat.py

@@ -16,11 +16,11 @@
     export DATABRICKS_TOKEN="dapi..."
     export DATABRICKS_SERVING_BASE_URL="https://<workspace>/serving-endpoints"
     export DATABRICKS_MODEL="<endpoint-name>"  # See databricks-model-serving
-    streamlit run 2-minimal-chat-app.py
+    streamlit run fm-minimal-chat.py
 
 Databricks Apps Deployment:
     1. Create app.yaml:
-       command: ["streamlit", "run", "2-minimal-chat-app.py"]
+       command: ["streamlit", "run", "fm-minimal-chat.py"]
        env:
          - name: DATABRICKS_SERVING_BASE_URL
            value: "https://<workspace>/serving-endpoints"

databricks-skills/databricks-apps-python/examples/fm-parallel-calls.py

@@ -224,42 +224,44 @@ def check_audience_fit(client: OpenAI, text: str) -> Dict[str, Any]:
     time_saved = (total_latency / 1000) - total_time
     print(f"\n{'='*60}")
     print(f"Time saved vs serial execution: {time_saved:.2f}s")
-    print(f"Speedup: {(total_latency/1000) / total_time:.1f}×")
+    if total_time > 0:
+        print(f"Speedup: {(total_latency/1000) / total_time:.1f}×")
+    else:
+        print("Speedup: N/A (total_time below resolution)")
     print(f"{'='*60}")
 
 
 # =============================================================================
 # Production Best Practices
 # =============================================================================
-"""
-Best practices from databricksters-check-and-pub:
-
-1. Configurable concurrency
-   - Use LLM_MAX_CONCURRENCY env var (default: 5 in the production app)
-   - Balance throughput vs rate limits
-   - Too high = rate limit errors
-   - Too low = underutilized resources
-
-2. Error handling
-   - Capture exceptions per job
-   - Return None for failed jobs
-   - Collect error messages for debugging
-   - Continue execution even if some jobs fail
-
-3. Bounded execution
-   - Only parallelize independent checks
-   - Cap concurrency with an env var rather than firing unlimited requests
-   - Keep the job contract simple: name -> (callable, args, kwargs)
-
-4. When to use parallel calls
-   - Multiple independent evaluations of same content
-   - Batch processing multiple documents
-   - A/B testing different prompts
-   - Multi-aspect analysis
-
-5. When NOT to use parallel calls
-   - Dependent/sequential operations
-   - Single evaluation needed
-   - Rate limits are very strict
-   - Debugging (use serial for easier troubleshooting)
-"""
+#
+# Best practices from databricksters-check-and-pub:
+#
+# 1. Configurable concurrency
+#    - Use LLM_MAX_CONCURRENCY env var (default: 5 in the production app)
+#    - Balance throughput vs rate limits
+#    - Too high = rate limit errors
+#    - Too low = underutilized resources
+#
+# 2. Error handling
+#    - Capture exceptions per job
+#    - Return None for failed jobs
+#    - Collect error messages for debugging
+#    - Continue execution even if some jobs fail
+#
+# 3. Bounded execution
+#    - Only parallelize independent checks
+#    - Cap concurrency with an env var rather than firing unlimited requests
+#    - Keep the job contract simple: name -> (callable, args, kwargs)
+#
+# 4. When to use parallel calls
+#    - Multiple independent evaluations of same content
+#    - Batch processing multiple documents
+#    - A/B testing different prompts
+#    - Multi-aspect analysis
+#
+# 5. When NOT to use parallel calls
+#    - Dependent/sequential operations
+#    - Single evaluation needed
+#    - Rate limits are very strict
+#    - Debugging (use serial for easier troubleshooting)

databricks-skills/databricks-apps-python/examples/llm_config.py

@@ -218,8 +218,10 @@ def get_databricks_bearer_token(
         access_token = payload.get("access_token")
         expires_in = int(payload.get("expires_in", 300))
         if not access_token:
+            payload_keys = sorted(payload.keys()) if isinstance(payload, dict) else []
             raise DatabricksLLMConfigError(
-                f"Token endpoint response is missing access_token: {payload}"
+                "Token endpoint response is missing access_token "
+                f"(keys present: {payload_keys})"
             )
 
         expires_at = int(time.time()) + expires_in
@@ -278,8 +280,7 @@ def validate_databricks_llm_config(
     if response.status_code >= 400:
         raise DatabricksLLMConfigError(
             f"Failed to validate DATABRICKS_MODEL={config.model!r} in workspace "
-            f"{config.workspace_host} (HTTP {response.status_code}). "
-            f"Response: {response.text[:300]}"
+            f"{config.workspace_host} (HTTP {response.status_code})."
         )
 
     _validation_cache[cache_key] = int(time.time()) + VALIDATION_TTL_SECONDS

databricks-skills/databricks-python-sdk/examples/5-serving-and-vector-search.py

@@ -168,10 +168,15 @@
 
 
 # Query with embedding vector directly
+# query_vector must be a list[float] whose length matches your index's
+# embedding dimension (e.g. 768 for bge-small, 1024 for bge-large, 1536 for
+# text-embedding-3-small / ada-002). The [0.0] * N below is a stand-in;
+# replace with the actual vector returned by your embedding model.
+query_vector = [0.0] * 768
 results = w.vector_search_indexes.query_index(
     index_name="main.default.my_index",
     columns=["id", "text"],
-    query_vector=[0.1, 0.2, 0.3, ...],  # Your embedding vector
+    query_vector=query_vector,
     num_results=10
 )