Update app.py

app.py

@@ -6,10 +6,8 @@ from langchain_community.llms import HuggingFaceEndpoint
 from langchain_community.embeddings import HuggingFaceInferenceAPIEmbeddings
 import gradio as gr
 import subprocess
-import redis
-from langchain_community.vectorstores.redis import RedisVectorStore
+import json
 
-#Using Mistral Modal
 # Ensure Playwright installs required browsers and dependencies
 subprocess.run(["playwright", "install"])
 #subprocess.run(["playwright", "install-deps"])
@@ -23,22 +21,16 @@ repo_id = "mistralai/Mistral-7B-Instruct-v0.2"
 llm_model_instance = HuggingFaceEndpoint(
     repo_id=repo_id, max_length=128, temperature=0.5, token=HUGGINGFACEHUB_API_TOKEN
 )
-#Calling Sentence Transformer
+
 embedder_model_instance = HuggingFaceInferenceAPIEmbeddings(
     api_key=HUGGINGFACEHUB_API_TOKEN, model_name="sentence-transformers/all-MiniLM-l6-v2"
 )
 
-
-r = redis.Redis(host="localhost", port=6379)
-vector_store = RedisVectorStore(redis=r)
-
 graph_config = {
     "llm": {"model_instance": llm_model_instance},
-    "embeddings": {"model_instance": embedder_model_instance},
-    "vector_store": {"model_instance": vector_store}
+    "embeddings": {"model_instance": embedder_model_instance}
 }
 
-#To Scrape the data and summarize it
 def scrape_and_summarize(prompt, source):
     smart_scraper_graph = SmartScraperGraph(
         prompt=prompt,
@@ -47,24 +39,45 @@ def scrape_and_summarize(prompt, source):
     )
     result = smart_scraper_graph.run()
     exec_info = smart_scraper_graph.get_execution_info()
-    return result, prettify_exec_info(exec_info)
+    
+    # Ensure the result is properly formatted as JSON
+    if isinstance(result, dict):
+        result_json = result
+    else:
+        try:
+            result_json = json.loads(result)
+        except json.JSONDecodeError as e:
+            # Attempt to extract JSON from the result
+            start_index = result.find("[")
+            end_index = result.rfind("]")
+            if start_index != -1 and end_index != -1:
+                json_str = result[start_index:end_index+1]
+                try:
+                    result_json = json.loads(json_str)
+                except json.JSONDecodeError as inner_e:
+                    raise ValueError(f"Invalid JSON output: {result}") from inner_e
+            else:
+                raise ValueError(f"Invalid JSON output: {result}") from e
 
-# Gradio User interface
+    return result_json, prettify_exec_info(exec_info)
+
+# Gradio interface
 with gr.Blocks() as demo:
-    gr.Markdown("A project on WEB-SCRAPING using Mistral model")
-    gr.Markdown("""Effortlessly extract and condense web content using cutting-edge AI models from the Hugging Face Hub—no coding required! Simply provide your desired prompt and source URL to begin. This no-code solution is inspired by the impressive library ScrapeGraphAI, and while it’s currently a basic demo, we encourage contributions to enhance its utility!""")
-#(https://github.com/VinciGit00/Scrapegraph-ai) is suggested by the tutor
+    gr.Markdown("# Scrape websites, no-code version")
+    gr.Markdown("""Easily scrape and summarize web content using advanced AI models on the Hugging Face Hub without writing any code. Input your desired prompt and source URL to get started.
+                This is a no-code version of the excellent lib [ScrapeGraphAI](https://github.com/VinciGit00/Scrapegraph-ai).
+                It's a basic demo and a work in progress. Please contribute to it to make it more useful!""")
+
     with gr.Row():
         with gr.Column():
-            
-            model_dropdown = gr.Textbox(label="Model", value="Mistral-7B-Instruct-v0.2, As all-MiniLM-l6-v2")
-            prompt_input = gr.Textbox(label="Prompt", value="List me all the doctors name and their timing")
-            source_input = gr.Textbox(label="Source URL", value="https://www.yelp.com/search?find_desc=dentist&find_loc=San+Francisco%2C+CA")
-            scrape_button = gr.Button("Scrape the data")
+            model_dropdown = gr.Textbox(label="Model", value="Mistral-7B-Instruct-v0.2")
+            prompt_input = gr.Textbox(label="Prompt", value="List me all the press releases with their headlines and urls.")
+            source_input = gr.Textbox(label="Source URL", value="https://www.whitehouse.gov/")
+            scrape_button = gr.Button("Scrape and Summarize")
         
         with gr.Column():
             result_output = gr.JSON(label="Result")
-            exec_info_output = gr.Textbox(label="Output Info")
+            exec_info_output = gr.Textbox(label="Execution Info")
 
     scrape_button.click(
         scrape_and_summarize,