Upload 3 files

README.md

@@ -1,17 +1,19 @@
-# StreamSmart Recommender - Hugging Face Space
+# StreamSmart Recommender - Hugging Face Space with 2 n8n workflows
 
 Files included:
 - `app.py` - main Gradio app for Hugging Face Space
 - `requirements.txt` - Python dependencies
-- `n8n_streamsmart_workflow.json` - importable n8n workflow
+- `n8n_processing_workflow.json` - import into n8n for full-result intake
+- `n8n_report_workflow.json` - import into n8n for top-recommendation reporting
 
 ## 1) Hugging Face setup
 Create a new **Gradio Space** and replace the default files with:
 - `app.py`
 - `requirements.txt`
 
-Optional secret:
-- `N8N_WEBHOOK_URL` = your production n8n webhook URL
+Add these Space secrets:
+- `N8N_PROCESS_WEBHOOK_URL` = your production URL from the processing workflow
+- `N8N_REPORT_WEBHOOK_URL` = your production URL from the report workflow
 
 ## 2) CSV formats
 ### Reviews CSV required columns
@@ -36,15 +38,26 @@ Rates should be decimals such as `0.82`, not percentages like `82%`.
 
 ## 3) n8n setup
 In n8n:
-1. Import `n8n_streamsmart_workflow.json`
-2. Open the Webhook node and copy the **Production URL**
-3. In Hugging Face Space settings, add a secret named `N8N_WEBHOOK_URL`
-4. Rebuild the Space
-5. Run the analysis in the app, then click `Send Top Recommendations to n8n`
-
-## 4) What the app does
+1. Import `n8n_processing_workflow.json`
+2. Import `n8n_report_workflow.json`
+3. Open each Webhook node and copy the **Production URL**
+4. Paste those URLs into the two Hugging Face Space secrets above
+5. Rebuild the Space
+
+## 4) What each workflow does
+### Processing workflow
+- receives the full scored dataset from the app
+- counts how many titles fall into each action category
+- returns the top title and a short status message
+
+### Report workflow
+- receives the top recommendations and all results
+- computes average recommendation score by genre
+- returns a text summary you can show in the app
+
+## 5) What the app does
 - scores review sentiment with VADER
 - merges title-level sentiment with watch metrics
 - computes a weighted recommendation score
 - labels each title with a business action
-- sends the scored results to one n8n workflow
+- sends results to two separate n8n workflows

app.py

@@ -1,7 +1,7 @@
 import os
 import io
 import json
-from typing import Optional, Tuple
+from typing import Tuple
 
 import numpy as np
 import pandas as pd
@@ -168,9 +168,6 @@ def run_analysis(reviews_file, watch_file, use_demo: bool):
     reviews["sentiment_score"] = reviews["review_text"].apply(compute_sentiment)
     reviews["sentiment_label"] = reviews["sentiment_score"].apply(sentiment_label)
 
-    agg_dict = {
-        "sentiment_score": ["mean", "count"],
-    }
     if "genre" in reviews.columns:
         review_agg = reviews.groupby("title", as_index=False).agg(
             avg_sentiment=("sentiment_score", "mean"),
@@ -216,13 +213,12 @@ def run_analysis(reviews_file, watch_file, use_demo: bool):
         f"Average completion rate: {merged['completion_rate'].mean():.2f}"
     )
 
-    top_table = merged[
-        [
-            "title", "genre", "avg_sentiment", "avg_watch_time", "completion_rate",
-            "drop_off_rate", "rewatch_rate", "click_through_rate", "review_count",
-            "recommendation_score", "action"
-        ]
+    table_cols = [
+        "title", "genre", "avg_sentiment", "avg_watch_time", "completion_rate",
+        "drop_off_rate", "rewatch_rate", "click_through_rate", "review_count",
+        "recommendation_score", "action"
     ]
+    top_table = merged[table_cols]
 
     top_plot = px.bar(
         merged.head(10),
@@ -283,26 +279,44 @@ def update_title_choices(payload: str):
     return gr.Dropdown(choices=choices, value=value)
 
 
-def send_to_n8n(payload: str):
-    if not payload:
-        raise gr.Error("Run the analysis first.")
-
-    webhook_url = os.getenv("N8N_WEBHOOK_URL", "").strip()
+def _post_to_webhook(env_name: str, body: dict, success_label: str) -> str:
+    webhook_url = os.getenv(env_name, "").strip()
     if not webhook_url:
-        return (
-            "N8N_WEBHOOK_URL is not set yet. Add it as a Hugging Face Space secret, then try again."
-        )
+        return f"{env_name} is not set yet. Add it as a Hugging Face Space secret, then try again."
 
-    data = json.loads(payload)
-    top5 = data[:5]
-    response = requests.post(webhook_url, json={"app": APP_TITLE, "top_recommendations": top5, "all_results": data}, timeout=60)
+    response = requests.post(webhook_url, json=body, timeout=60)
     response.raise_for_status()
 
     try:
         result = response.json()
-        return f"n8n workflow ran successfully. Response: {json.dumps(result, indent=2)}"
+        return f"{success_label} ran successfully. Response: {json.dumps(result, indent=2)}"
     except Exception:
-        return f"n8n workflow ran successfully. Raw response: {response.text}"
+        return f"{success_label} ran successfully. Raw response: {response.text}"
+
+
+def send_to_processing_workflow(payload: str):
+    if not payload:
+        raise gr.Error("Run the analysis first.")
+
+    data = json.loads(payload)
+    return _post_to_webhook(
+        "N8N_PROCESS_WEBHOOK_URL",
+        {"app": APP_TITLE, "records": data, "record_count": len(data)},
+        "n8n processing workflow",
+    )
+
+
+def send_to_report_workflow(payload: str):
+    if not payload:
+        raise gr.Error("Run the analysis first.")
+
+    data = json.loads(payload)
+    top5 = data[:5]
+    return _post_to_webhook(
+        "N8N_REPORT_WEBHOOK_URL",
+        {"app": APP_TITLE, "top_recommendations": top5, "all_results": data},
+        "n8n report workflow",
+    )
 
 
 with gr.Blocks(title=APP_TITLE) as demo:
@@ -335,11 +349,14 @@ with gr.Blocks(title=APP_TITLE) as demo:
 
     with gr.Tab("4. n8n Automation"):
         gr.Markdown(
-            "This button sends your scored results to one n8n workflow through a webhook. "
-            "Set the `N8N_WEBHOOK_URL` secret in your Hugging Face Space first."
+            "Set these Hugging Face Space secrets before using the buttons below:\n\n"
+            "- `N8N_PROCESS_WEBHOOK_URL`\n"
+            "- `N8N_REPORT_WEBHOOK_URL`"
         )
-        n8n_btn = gr.Button("Send Top Recommendations to n8n")
-        n8n_status = gr.Textbox(label="n8n Status", lines=5)
+        process_btn = gr.Button("Send Full Results to n8n Processing Workflow")
+        process_status = gr.Textbox(label="Processing Workflow Status", lines=5)
+        report_btn = gr.Button("Send Top Recommendations to n8n Report Workflow")
+        report_status = gr.Textbox(label="Report Workflow Status", lines=5)
 
     with gr.Tab("5. Download"):
         download_file = gr.File(label="Download processed CSV")
@@ -370,10 +387,16 @@ with gr.Blocks(title=APP_TITLE) as demo:
         outputs=[detail_box],
     )
 
-    n8n_btn.click(
-        fn=send_to_n8n,
+    process_btn.click(
+        fn=send_to_processing_workflow,
+        inputs=[payload_state],
+        outputs=[process_status],
+    )
+
+    report_btn.click(
+        fn=send_to_report_workflow,
         inputs=[payload_state],
-        outputs=[n8n_status],
+        outputs=[report_status],
     )
 
 if __name__ == "__main__":

requirements.txt

@@ -1,6 +1,6 @@
 gradio>=4.44.0
-pandas>=2.2.2
-numpy>=1.26.4
-plotly>=5.24.1
-requests>=2.32.3
+pandas>=2.2.0
+numpy>=1.26.0
+plotly>=5.22.0
+requests>=2.31.0
 vaderSentiment>=3.3.2