add visual prior art

app.py

@@ -4,7 +4,10 @@ from typing import Dict, List
 import gradio as gr
 import pandas as pd
 import json
+import re
 from src.core import *
+from src.ressources.main_css import *
+
 
 app = FastAPI(
     title="Insight Finder",
@@ -58,13 +61,13 @@ async def process_constraints(constraints: InputConstraints):
 
 @app.post("/prior-art-constraints", response_model=OutputPriorArt)
 async def prior_art_constraints(data: InputPriorArtConstraints):
-    prior_art = process_prior_art(data.technologies, data.constraints, "constraints")
+    prior_art = process_prior_art(data.technologies, data.constraints, "constraints", "pydantic")
     print(prior_art)
     return prior_art
 
 @app.post("/prior-art-problems", response_model=OutputPriorArt)
 async def prior_art_problems(data: InputPriorArtProblem):
-    prior_art = process_prior_art(data.technologies, data.problems, "problem")
+    prior_art = process_prior_art(data.technologies, data.problems, "problem", "pydantic")
     return prior_art
 
 def make_json_serializable(data):
@@ -135,7 +138,120 @@ def format_final_technologies_html(technologies_list: list) -> str:
             """
     html_content += "</div>"
     return "<h1>The best technologies combinations </h1>" + html_content
-    
+
+def format_prior_art_html(prior_art_data: dict) -> str:
+    if not prior_art_data or 'content' not in prior_art_data:
+        return "<div class='prior-art-container'><p>No prior art data available.</p></div>"
+
+    content = prior_art_data['content']
+    uris = prior_art_data.get('uris', [])
+
+    # 1. Convert **text** to <strong>text</strong>
+    processed_content = re.sub(r'\*\*(.*?)\*\*', r'<strong>\1</strong>', content)
+
+    # 2. Convert [x](uri) to clickable links
+    # This regex handles cases where [x] is followed by (uri)
+    # It captures the number (group 1) and the URI (group 2)
+    processed_content = re.sub(r'\[(\d+)\]\((https?:\/\/[^\s\)]+)\)', r'<a href="\2" target="_blank" class="prior-art-inline-link">\1</a>', processed_content)
+
+    # Split content into initial summary and then document sections
+    sections = processed_content.split("Here are the documents found and the technologies used within them:\n\n")
+
+    summary_html = ""
+    documents_html = ""
+
+    # Process summary part (the first part of the split)
+    if len(sections) > 0:
+        summary_lines = sections[0].strip().split('\n')
+        summary_html += "    <div class='prior-art-summary'>\n"
+        for line in summary_lines:
+            if line.strip().startswith('*'):
+                # For bullet points, specially format bold text
+                # The bolding for **text** is already handled by re.sub
+                parts = line.split(':', 1)
+                if len(parts) > 1:
+                    summary_html += f"        <p class='summary-bullet'><strong>{parts[0].replace('*', '').strip()}:</strong> {parts[1].strip()}</p>\n"
+                else:
+                    summary_html += f"        <p class='summary-bullet'>{line.replace('*', '').strip()}</p>\n"
+            elif line.strip():
+                summary_html += f"        <p>{line.strip()}</p>\n"
+        summary_html += "    </div>\n"
+
+    # Process documents part (the second part of the split)
+    if len(sections) > 1:
+        documents_raw = sections[1].strip()
+        # Split by "number. **" to get individual document entries reliably
+        document_entries = re.split(r'(\d+\.\s*\*\*.*?\*\*)', documents_raw)
+        
+        parsed_docs = []
+        for i in range(1, len(document_entries), 2):
+            title_line = document_entries[i].strip()
+            content_block = document_entries[i+1].strip() if i+1 < len(document_entries) else ""
+            parsed_docs.append({'title_line': title_line, 'content_block': content_block})
+
+        documents_html += "    <div class='prior-art-documents'>\n"
+        for doc in parsed_docs:
+            doc_number_title = doc['title_line']
+            doc_content_lines = [l.strip() for l in doc['content_block'].split('\n') if l.strip()]
+
+            doc_description = ""
+            tech_used_section = []
+            
+            desc_start_idx = -1
+            tech_start_idx = -1
+
+            for idx, line in enumerate(doc_content_lines):
+                if line.startswith("Description:"):
+                    desc_start_idx = idx
+                elif line.startswith("Technologies Used:"):
+                    tech_start_idx = idx
+
+            if desc_start_idx != -1:
+                desc_end_idx = tech_start_idx if tech_start_idx != -1 else len(doc_content_lines)
+                doc_description = " ".join(doc_content_lines[desc_start_idx:desc_end_idx]).replace("Description:", "").strip()
+            
+            if tech_start_idx != -1:
+                tech_used_section = [l.replace('*', '').strip() for l in doc_content_lines[tech_start_idx:] if l.strip().startswith('*')]
+
+
+            documents_html += f"""\
+        <div class='prior-art-document-card'>
+            <h4 class='document-title'>{doc_number_title}</h4>
+            <p class='document-description'><strong>Description:</strong> {doc_description}</p>\n"""
+            if tech_used_section:
+                documents_html += "            <div class='document-technologies'>\n"
+                documents_html += "                <h5>Technologies Used:</h5>\n                <ul>\n"
+                for tech_item in tech_used_section:
+                    if tech_item.strip():
+                        tech_parts = tech_item.split(':', 1)
+                        if len(tech_parts) > 1:
+                            documents_html += f"                    <li><strong>{tech_parts[0].strip()}:</strong> {tech_parts[1].strip()}</li>\n"
+                        else:
+                            documents_html += f"                    <li>{tech_item.strip()}</li>\n"
+                documents_html += "                </ul>\n            </div>\n"
+            documents_html += "        </div>\n"
+        documents_html += "    </div>\n"
+
+    # Grouped URLs at the end
+    grouped_uris_html = ""
+    if uris:
+        grouped_uris_html += "    <div class='grouped-uris-section'>\n"
+        grouped_uris_html += "        <hr class='disruptive-line'>\n" # Disruptive line
+        grouped_uris_html += "        <h3>Referenced Documents (URIs):</h3>\n"
+        grouped_uris_html += "        <ul>\n"
+        for idx, uri in enumerate(uris):
+            grouped_uris_html += f"            <li>{idx + 1}. <a href='{uri}' target='_blank' class='prior-art-grouped-link'>Document {idx + 1} Link</a></li>\n"
+        grouped_uris_html += "        </ul>\n    </div>\n"
+
+    return f"<div class='prior-art-container'>\n{summary_html}{documents_html}{grouped_uris_html}</div>"
+
+
+def gradio_prior_art(best_technologies, constraints):
+    prior_art = process_prior_art(best_technologies, constraints, "constraints", "dict")
+    html_prior_art = format_prior_art_html(prior_art)
+    print(html_prior_art)
+    return html_prior_art
+
 def process_input_gradio(problem_description: str):
     """
     Processes the input problem description step-by-step for Gradio.
@@ -169,12 +285,6 @@ def process_input_gradio(problem_description: str):
 
     # Step 8: Get Technologies by ID
     best_technologies = get_technologies_by_id(best_technologies_id, global_tech)
-
-    print(constraints)
-
-    print(best_combinations)
-
-    print(best_technologies)
     
     # Format outputs for Gradio
     # For Constraints:
@@ -186,17 +296,20 @@ def process_input_gradio(problem_description: str):
     # For Final Technologies:
     final_technologies_html = format_final_technologies_html(best_technologies)
 
-    prior_art = process_prior_art(best_technologies, constraints, "constraints")
-    print(prior_art)
-
     return (
         prompt,
         constraints_html, # Output HTML for constraints
         best_combinations_html, # Output HTML for best combinations
         ", ".join(map(str, best_technologies_id)), # Still a simple text list
-        final_technologies_html # Output HTML for final technologies
+        final_technologies_html, # Output HTML for final technologies
+        {"technologies": best_technologies}, # `best_technologies` is the actual list of dicts
+        constraints
     )
 
+   
+    # Return a gr.update object to change the value and visibility in one step
+#    return gr.update(value=html_prior_art, visible=True)
+   
 
 # --- Gradio Interface Setup ---
 input_problem = gr.Textbox(
@@ -209,212 +322,11 @@ output_constraints = gr.HTML(label="2. Retrieved Constraints") # Changed to HTML
 output_best_combinations = gr.HTML(label="7. Best Technology Combinations Found") # Changed to HTML
 output_selected_ids = gr.Textbox(label="8. Selected Technology IDs", interactive=False)
 output_final_technologies = gr.HTML(label="9. Final Best Technologies") # Changed to HTML
+output_prior_art = gr.HTML(label="10. Prior Art Analysis") # Initially hidden
+
+stock_technologies = gr.JSON(visible=False)
+stock_constraints = gr.JSON(visible=False)
 
-# Custom CSS for a professional look and specific output styling
-custom_css = """
-/* General Body and Font Styling */
-body {
-    font-family: 'Segoe UI', 'Roboto', 'Helvetica Neue', Arial, sans-serif;
-    color: #333;
-    background-color: #f0f2f5;
-}
-
-/* Header Styling */
-.gradio-container h1 {
-    color: #0056b3; /* A deep blue for the main title */
-    text-align: center;
-    margin-bottom: 10px;
-    font-weight: 600;
-    font-size: 2.5em;
-    text-shadow: 1px 1px 2px rgba(0,0,0,0.1);
-}
-
-.gradio-container h2 {
-    color: #007bff; /* A slightly lighter blue for subtitles */
-    text-align: center;
-    margin-top: 0;
-    margin-bottom: 30px;
-    font-weight: 400;
-    font-size: 1.2em;
-}
-
-/* Card-like styling for individual components */
-.gradio-container .gr-box {
-    background-color: #ffffff;
-    border-radius: 12px;
-    box-shadow: 0 4px 12px rgba(0, 0, 0, 0.08);
-    padding: 20px;
-    margin-bottom: 20px;
-    border: 1px solid #e0e0e0;
-}
-
-/* Input Textbox Styling */
-.gradio-container input[type="text"],
-.gradio-container textarea {
-    border: 1px solid #ced4da;
-    border-radius: 8px;
-    padding: 12px 15px;
-    font-size: 1em;
-    color: #495057;
-    transition: border-color 0.2s ease-in-out, box-shadow 0.2s ease-in-out;
-}
-
-.gradio-container input[type="text"]:focus,
-.gradio-container textarea:focus {
-    border-color: #007bff;
-    box-shadow: 0 0 0 0.2rem rgba(0, 123, 255, 0.25);
-    outline: none;
-}
-
-/* Button Styling */
-.gradio-container button {
-    background-color: #28a745; /* A vibrant green for action */
-    color: white;
-    border: none;
-    border-radius: 8px;
-    padding: 12px 25px;
-    font-size: 1.1em;
-    font-weight: 500;
-    cursor: pointer;
-    transition: background-color 0.2s ease-in-out, transform 0.1s ease-in-out;
-    box-shadow: 0 4px 6px rgba(0, 0, 0, 0.1);
-}
-
-.gradio-container button:hover {
-    background-color: #218838; /* Darker green on hover */
-    transform: translateY(-2px);
-}
-
-.gradio-container button:active {
-    transform: translateY(0);
-}
-
-/* Labels for outputs */
-.gradio-container label {
-    font-weight: 600;
-    color: #495057;
-    margin-bottom: 8px;
-    display: block; /* Ensure labels are on their own line */
-    font-size: 1.1em;
-}
-
-/* --- Specific Styling for Outputs --- */
-
-/* 2. Retrieved Constraints Styling */
-.constraints-container {
-    padding: 15px;
-    background-color: #f8f9fa;
-    border-radius: 8px;
-    border: 1px solid #e9ecef;
-    font-family: 'Trebuchet MS', 'Lucida Grande', 'Lucida Sans Unicode', 'Lucida Sans', Tahoma, sans-serif; /* Different font */
-    line-height: 1.6;
-    max-height: 300px;
-    overflow-y: auto;
-}
-.constraint-item {
-    margin-bottom: 10px;
-    padding-bottom: 10px;
-    border-bottom: 1px dashed #e0e0e0;
-}
-.constraint-item:last-child {
-    border-bottom: none;
-    margin-bottom: 0;
-    padding-bottom: 0;
-}
-.constraint-title {
-    font-weight: bold;
-    color: #004085; /* Darker blue for constraint titles */
-    font-size: 1.1em;
-}
-.constraint-description {
-    color: #333;
-    font-size: 1em;
-}
-
-/* 7. Best Technology Combinations Found & 9. Final Best Technologies Styling */
-.combinations-outer-container, .final-tech-container {
-    padding: 15px;
-    background-color: #f8f9fa;
-    border-radius: 8px;
-    border: 1px solid #e9ecef;
-    max-height: 500px; /* Adjust as needed */
-    overflow-y: auto;
-    font-family: 'Trebuchet MS', 'Lucida Grande', 'Lucida Sans Unicode', 'Lucida Sans', Tahoma, sans-serif; /* Different font */
-}
-
-.problem-card {
-    background-color: #ffffff;
-    border: 1px solid #cfe2ff; /* Light blue border for problem card */
-    border-radius: 10px;
-    padding: 20px;
-    margin-bottom: 20px;
-    box-shadow: 0 4px 10px rgba(0, 0, 0, 0.05);
-}
-.problem-card-title {
-    color: #0056b3; /* Deep blue for problem title */
-    font-size: 1.4em;
-    margin-top: 0;
-    margin-bottom: 15px;
-    border-bottom: 2px solid #cfe2ff;
-    padding-bottom: 10px;
-}
-
-.technologies-inner-container {
-    display: grid;
-    grid-template-columns: repeat(auto-fit, minmax(280px, 1fr)); /* Responsive grid for technologies */
-    gap: 15px;
-}
-
-.technology-card, .final-tech-card {
-    background-color: #f0faff; /* Very light blue for technology cards */
-    border: 1px solid #b0d9ff; /* Slightly darker blue border */
-    border-radius: 8px;
-    padding: 15px;
-    box-shadow: 0 2px 5px rgba(0, 0, 0, 0.05);
-    transition: transform 0.2s ease-in-out;
-}
-
-.technology-card:hover, .final-tech-card:hover {
-    transform: translateY(-3px);
-}
-
-.tech-card-title, .final-tech-title {
-    color: #007bff; /* Gradio's primary blue */
-    font-size: 1.2em;
-    margin-top: 0;
-    margin-bottom: 10px;
-    font-weight: 600;
-}
-
-.technology-card p, .final-tech-card p {
-    font-size: 0.95em;
-    line-height: 1.5;
-    margin-bottom: 5px;
-    color: #555;
-}
-.technology-card p strong, .final-tech-card p strong {
-    color: #004085; /* Darker blue for bold labels */
-}
-
-/* Responsive adjustments */
-@media (max-width: 768px) {
-    .gradio-container {
-        padding: 15px;
-    }
-    .gradio-container h1 {
-        font-size: 2em;
-    }
-    .gradio-container button {
-        width: 100%;
-        padding: 15px;
-    }
-    .technologies-inner-container {
-        grid-template-columns: 1fr; /* Stack columns on smaller screens */
-    }
-}
-"""
-
-# Create the Gradio Blocks demo with custom theme and CSS
 with gr.Blocks(
     theme=gr.themes.Soft(),
     css=custom_css
@@ -436,12 +348,19 @@ with gr.Blocks(
     with gr.Row():
         with gr.Column():
             output_prompt.render()
-            output_constraints.render() # Renders HTML
+            output_constraints.render()
         with gr.Column():
-            output_selected_ids.render() # This remains a Textbox
-            output_best_combinations.render() # Renders HTML
-            output_final_technologies.render() # Renders HTML
-
+            output_selected_ids.render()
+            output_best_combinations.render()
+            output_final_technologies.render()
+    
+    gr.Markdown("---")
+    gr.Markdown("### Prior Art Analysis")
+    prior_art_button = gr.Button("Find Prior Art", elem_id="prior_art_button")
+    output_prior_art.render()
+    stock_technologies.render()
+    stock_constraints.render()
+    
     process_button.click(
         fn=process_input_gradio,
         inputs=input_problem,
@@ -450,10 +369,19 @@ with gr.Blocks(
             output_constraints,
             output_best_combinations,
             output_selected_ids,
-            output_final_technologies
+            output_final_technologies,
+            stock_technologies,
+            stock_constraints
         ]
     )
 
+    prior_art_button.click(
+        fn=gradio_prior_art,
+        inputs=[stock_technologies, stock_constraints],
+        outputs=output_prior_art
+    )
+
+
 gr.mount_gradio_app(app, gradio_app_blocks, path="/gradio")
 #if __name__ == "__main__":
 #    gradio_app_blocks.launch()

src/core.py

@@ -30,13 +30,13 @@ def process_input(data, global_tech, global_tech_embeddings, data_type):
     
     return best_technologies
 
-def process_prior_art(technologies, data, data_type):
+def process_prior_art(technologies, data, data_type, techno_type):
     try:
-        prior_art_reponse = search_prior_art(technologies, data, data_type)
+        prior_art_reponse = search_prior_art(technologies, data, data_type, techno_type)
         prior_art_search = add_citations_and_collect_uris(prior_art_reponse)
     except Exception as e:
         print(f"An error occured during the process, trying again : {e}")
-        prior_art_reponse = search_prior_art(technologies, data, data_type)
+        prior_art_reponse = search_prior_art(technologies, data, data_type, techno_type)
         prior_art_search = add_citations_and_collect_uris(prior_art_reponse)
 
     return prior_art_search

src/services/processor.py

@@ -217,19 +217,26 @@ def select_technologies(problem_technology_list):
         return set()
     return set(best_set)
 
-
-def search_prior_art(technologies_input: list, data: str, type: str) -> json:
+def load_titles(techno, data_type):
+    if data_type == "pydantic":
+        technology_titles = [tech.title for tech in techno]
+    else: # data_type == "dict"
+        technologies = techno["technologies"]
+        technology_titles = [tech["title"] for tech in technologies]
+    return technology_titles
+
+def search_prior_art(technologies_input: list, data: str, data_type: str, techno_type: str) -> json:
     """
     Searches for prior art patents online that solve a given technical problem
     using a set of specified technologies, leveraging the Gemini model's search capabilities.
     """
 
-    technology_titles = [tech.title for tech in technologies_input]
+    technology_titles = load_titles(technologies_input, techno_type)
 
-    if type == "problem":
+    if data_type == "problem":
         prompt = f"Find prior art patents or research paper online that address the technical problem: '{data}'. " \
              
-    elif type == "constraints":
+    elif data_type == "constraints":
         prompt = f"Find prior art patents or research paper online that address those constraints: '{data}'. " \
 
     prompt += f"Using any combination of the following technologies:  {', '.join(technology_titles)}. " \
@@ -274,5 +281,4 @@ def add_citations_and_collect_uris(response):
         return {"content": text,"uris": list(uris_added)}
     except Exception as e:
         print(f"Error : {e}")
-        return {"content": e, "uris": []}
-
+        return {"content": e, "uris": []}