Upload app.py

app.py

@@ -10,7 +10,7 @@ import os
 from PIL import Image
 import io
 import PyPDF2
-from datetime import datetime
+import secrets
 
 # Configure logging
 logging.basicConfig(level=logging.INFO)
@@ -22,6 +22,10 @@ AWS_ACCESS_KEY = os.getenv("AWS_ACCESS_KEY", "")
 AWS_SECRET_KEY = os.getenv("AWS_SECRET_KEY", "")
 AWS_REGION = os.getenv("AWS_REGION", "us-east-1")
 
+# If we're on HuggingFace Spaces, use the HF_TOKEN (if available)
+HF_TOKEN = os.getenv("HF_TOKEN", "")
+USE_HF_INFERENCE = bool(HF_TOKEN) and len(HF_TOKEN) > 0
+
 # Initialize Bedrock client if credentials are available
 bedrock_client = None
 if AWS_ACCESS_KEY and AWS_SECRET_KEY:
@@ -52,10 +56,6 @@ SAMPLE_TRANSCRIPT = """*PAR: today I would &-um like to talk about &-um a fun tr
 *PAR: my mom said to &-um that I could have &-um two scoops next time.
 *PAR: I want to go back to the beach [/] beach next year."""
 
-# ===============================
-# Utility Functions
-# ===============================
-
 def read_pdf(file_path):
     """Read text from a PDF file"""
     try:
@@ -69,31 +69,15 @@ def read_pdf(file_path):
         logger.error(f"Error reading PDF: {str(e)}")
         return ""
 
-def process_upload(file):
-    """Process an uploaded file (PDF or text)"""
-    if file is None:
-        return ""
-    
-    file_path = file.name
-    if file_path.endswith('.pdf'):
-        return read_pdf(file_path)
-    else:
-        with open(file_path, 'r', encoding='utf-8', errors='ignore') as f:
-            return f.read()
-
-# ===============================
-# AI Model Interface Functions
-# ===============================
-
-def call_bedrock(prompt, max_tokens=4096):
+def call_bedrock(prompt):
     """Call the AWS Bedrock API to analyze text using Claude"""
     if not bedrock_client:
-        return "AWS credentials not configured. Please set your AWS credentials as secrets in the Space settings."
+        return "AWS credentials not configured. Please set your AWS credentials as secrets in the HuggingFace Space settings."
     
     try:
         body = json.dumps({
             "anthropic_version": "bedrock-2023-05-31",
-            "max_tokens": max_tokens,
+            "max_tokens": 4096,
             "messages": [
                 {
                     "role": "user",
@@ -117,8 +101,8 @@ def call_bedrock(prompt, max_tokens=4096):
         logger.error(f"Error in call_bedrock: {str(e)}")
         return f"Error: {str(e)}"
 
-def generate_demo_response(prompt):
-    """Generate a simulated response for demo purposes"""
+def call_hf_inference(prompt):
+    """Simulate LLM output for demo purposes when no API credentials are available"""
     # This function generates a realistic but fake response for demo purposes
     # In a real deployment, you would call an actual LLM API
     
@@ -180,34 +164,8 @@ def generate_demo_response(prompt):
     
     return response
 
-def generate_demo_transcription(audio_path):
-    """Generate a simulated transcription response"""
-    # In a real app, this would process an audio file
-    return "*PAR: today I want to tell you about my favorite toy.\n*PAR: it's a &-um teddy bear that I got for my birthday.\n*PAR: he has &-um brown fur and a red bow.\n*PAR: I like to sleep with him every night.\n*PAR: sometimes I take him to school in my backpack."
-
-def generate_demo_qa_response(question):
-    """Generate a simulated Q&A response"""
-    qa_responses = {
-        "what is casl": "CASL-2 (Comprehensive Assessment of Spoken Language, Second Edition) is a standardized assessment tool used by Speech-Language Pathologists to evaluate a child's oral language abilities across multiple domains including lexical/semantic, syntactic, and supralinguistic skills. It helps identify language disorders and guides intervention planning.",
-        "how do i interpret scores": "CASL-2 scores include standard scores (mean=100, SD=15), percentile ranks, and performance levels. Standard scores below 85 indicate below average performance, 85-115 is average, and above 115 is above average. Percentile ranks show how a child performs relative to same-age peers.",
-        "what activities help word finding": "Activities to improve word-finding skills include semantic feature analysis (describing attributes of objects), categorization tasks, word association games, rapid naming practice, and structured conversation with gentle cueing. Visual supports and semantic mapping can also be helpful.",
-        "how often should therapy occur": "The recommended frequency for speech-language therapy typically ranges from 1-3 sessions per week, depending on the severity of the impairment. For moderate difficulties, twice weekly sessions of 30-45 minutes are common. Consistency is important for progress.",
-        "when should i reassess": "Reassessment is typically recommended every 3-6 months to track progress and adjust treatment goals. For educational settings, annual reassessment is common. More frequent informal assessments can help guide ongoing intervention.",
-    }
-    
-    # Simple keyword matching for demo purposes
-    for key, response in qa_responses.items():
-        if key in question.lower():
-            return response
-    
-    return "I don't have specific information about that topic. For detailed professional guidance, consult with a licensed Speech-Language Pathologist who can provide advice specific to your situation."
-
-# ===============================
-# Analysis Functions
-# ===============================
-
-def parse_casl_response(response):
-    """Parse the LLM response for CASL analysis into structured data"""
+def parse_analysis_response(response):
+    """Parse the LLM response into structured data"""
     lines = response.split('\n')
     data = {
         'Factor': [],
@@ -310,8 +268,8 @@ def parse_casl_response(response):
         'additional_analysis': additional_analysis
     }
 
-def create_casl_plots(speech_factors, casl_data):
-    """Create visualizations for the CASL analysis results"""
+def create_plots(speech_factors, casl_data):
+    """Create visualizations for the analysis results"""
     
     # Set a professional style for the plots
     plt.style.use('seaborn-v0_8-pastel')
@@ -389,7 +347,7 @@ def create_casl_plots(speech_factors, casl_data):
     
     return buf
 
-def create_casl_radar_chart(speech_factors):
+def create_radar_chart(speech_factors):
     """Create a radar chart for speech factors (percentiles)"""
     
     if speech_factors.empty or 'Severity' not in speech_factors.columns:
@@ -444,7 +402,7 @@ def create_casl_radar_chart(speech_factors):
     return buf
 
 def analyze_transcript(transcript, age, gender):
-    """Analyze a speech transcript using the CASL framework"""
+    """Analyze a speech transcript using the Bedrock API or fallback to demo mode"""
     
     # Instructions for the LLM analysis
     instructions = """
@@ -498,164 +456,19 @@ def analyze_transcript(transcript, age, gender):
     if bedrock_client:
         response = call_bedrock(prompt)
     else:
-        response = generate_demo_response(prompt)
+        response = call_hf_inference(prompt)
     
     # Parse the response
-    results = parse_casl_response(response)
+    results = parse_analysis_response(response)
     
     # Create visualizations
-    plot_image = create_casl_plots(results['speech_factors'], results['casl_data'])
-    radar_image = create_casl_radar_chart(results['speech_factors'])
+    plot_image = create_plots(results['speech_factors'], results['casl_data'])
+    radar_image = create_radar_chart(results['speech_factors'])
     
     return results, plot_image, radar_image, response
 
-def generate_report(patient_info, analysis_results, report_type="formal"):
-    """Generate a professional report based on analysis results"""
-    
-    patient_name = patient_info.get("name", "")
-    record_id = patient_info.get("record_id", "")
-    age = patient_info.get("age", "")
-    gender = patient_info.get("gender", "")
-    assessment_date = patient_info.get("assessment_date", datetime.now().strftime('%m/%d/%Y'))
-    clinician = patient_info.get("clinician", "")
-    
-    prompt = f"""
-    You are a professional Speech-Language Pathologist creating a {report_type} report based on an assessment.
-    
-    PATIENT INFORMATION:
-    Name: {patient_name}
-    Record ID: {record_id}
-    Age: {age}
-    Gender: {gender}
-    Assessment Date: {assessment_date}
-    Clinician: {clinician}
-    
-    ASSESSMENT RESULTS:
-    {analysis_results}
-    
-    Please create a professional {report_type} report that includes:
-    1. Patient information and assessment details
-    2. Summary of findings (strengths and areas of concern)
-    3. Detailed analysis of language domains
-    4. Specific recommendations for therapy
-    5. Recommendation for frequency and duration of services
-    
-    Use clear, professional language appropriate for {'educational professionals' if report_type == 'formal' else 'parents and caregivers'}.
-    Format the report with proper headings and sections.
-    """
-    
-    # Call the API or use demo mode
-    if bedrock_client:
-        report = call_bedrock(prompt, max_tokens=6000)
-    else:
-        # For demo, create a simulated report
-        report = f"""
-        # {'FORMAL LANGUAGE ASSESSMENT REPORT' if report_type == 'formal' else 'PARENT-FRIENDLY LANGUAGE ASSESSMENT SUMMARY'}
-        
-        **Date of Assessment:** {assessment_date}
-        **Clinician:** {clinician}
-        
-        ## PATIENT INFORMATION
-        **Name:** {patient_name}
-        **Record ID:** {record_id}
-        **Age:** {age}
-        **Gender:** {gender}
-        
-        ## ASSESSMENT SUMMARY
-        
-        {'The patient was assessed using the Comprehensive Assessment of Spoken Language, Second Edition (CASL-2) to evaluate language skills across multiple domains. The assessment involved language sample analysis and standardized testing.' if report_type == 'formal' else 'We completed a language assessment to better understand your child\'s communication strengths and challenges. This helps us create a plan to support their development.'}
-        
-        ## KEY FINDINGS
-        
-        **Areas of Strength:**
-        - Ability to maintain conversational topics 
-        - Good vocabulary for everyday topics
-        - Strong nonverbal communication skills
-        
-        **Areas of Challenge:**
-        - Word-finding difficulties during conversation
-        - Grammatical errors in complex sentences
-        - Difficulty with abstract language concepts
-        
-        ## DETAILED ANALYSIS
-        
-        **Lexical/Semantic Skills:** Standard Score 91 (27th percentile) - Low Average Range
-        The student demonstrates adequate vocabulary but struggles with retrieving specific words during conversation. Word-finding pauses were noted throughout the language sample.
-        
-        **Syntactic Skills:** Standard Score 85 (16th percentile) - Low Average Range
-        The student shows difficulty with complex grammatical structures, particularly verb tense consistency and complex sentence formation.
-        
-        **Supralinguistic Skills:** Standard Score 83 (13th percentile) - Below Average Range
-        The student struggles with understanding figurative language, making inferences, and comprehending abstract concepts.
-        
-        ## RECOMMENDATIONS
-        
-        {'1. Speech-Language Therapy focused on:' if report_type == 'formal' else 'We recommend:'}
-           - Word-finding strategies using semantic feature analysis
-           - Structured grammatical exercises to improve sentence complexity
-           - Explicit instruction in figurative language comprehension
-           - Narrative language development using visual supports
-        
-        {'2. Frequency of service: Twice weekly sessions of 30 minutes each for 12 weeks, followed by a reassessment to measure progress.' if report_type == 'formal' else '2. We recommend therapy twice a week for 30 minutes. This consistency will help your child make better progress.'}
-        
-        {'3. Classroom accommodations including:' if report_type == 'formal' else '3. In school, your child may benefit from:'}
-           - Extended time for verbal responses
-           - Visual supports for complex instructions
-           - Pre-teaching of vocabulary for academic units
-        
-        ## PROGNOSIS
-        
-        {'The prognosis for improvement is good with consistent therapeutic intervention and support. Regular reassessment is recommended to monitor progress.' if report_type == 'formal' else 'With regular therapy and support at home, we expect your child to make good progress in these areas.'}
-        
-        {'Respectfully submitted,' if report_type == 'formal' else 'Please reach out with any questions!'}
-        
-        {clinician}
-        Speech-Language Pathologist
-        """
-    
-    return report
-
-def transcribe_audio(audio_path, patient_age):
-    """Transcribe an audio recording using CHAT format"""
-    # In a real implementation, this would use a speech-to-text service
-    # For demo purposes, we'll return a simulated transcription
-    
-    if bedrock_client:
-        # In a real implementation, you would process the audio file and send it to a transcription service
-        # Here we just simulate the result
-        transcription = generate_demo_transcription(audio_path)
-    else:
-        transcription = generate_demo_transcription(audio_path)
-    
-    return transcription
-
-def answer_slp_question(question):
-    """Answer a question about SLP practice or CASL assessment"""
-    
-    prompt = f"""
-    You are an experienced Speech-Language Pathologist answering a question from a colleague.
-    
-    QUESTION:
-    {question}
-    
-    Please provide a clear, evidence-based answer focused specifically on the question asked.
-    Reference best practices and current research where appropriate.
-    Keep your answer concise but comprehensive.
-    """
-    
-    if bedrock_client:
-        answer = call_bedrock(prompt)
-    else:
-        answer = generate_demo_qa_response(question)
-    
-    return answer
-
-# ===============================
-# Gradio Interface
-# ===============================
-
 def create_interface():
-    """Create the main Gradio interface"""
+    """Create the Gradio interface"""
     
     # Define custom theme colors
     primary_color = "#2C7FB8"  # Professional blue
@@ -757,274 +570,189 @@ def create_interface():
         gr.HTML(
             """
             <div class="header">
-                <h1>SLP Analysis Tool</h1>
-                <p>A comprehensive assessment tool for Speech-Language Pathologists</p>
+                <h1>CASL Speech Analysis Tool</h1>
+                <p>A professional assessment tool for Speech-Language Pathologists</p>
             </div>
             """
         )
         
-        # Main tabs
-        with gr.Tabs() as main_tabs:
-            # ===============================
-            # CASL Analysis Tab
-            # ===============================
-            with gr.TabItem("CASL Analysis", id=0):
-                with gr.Row():
-                    # Left column - Input section
-                    with gr.Column(scale=1):
-                        # Patient information panel
-                        with gr.Box(elem_classes="container patient-info"):
-                            gr.Markdown("### Patient Information")
-                            
-                            with gr.Row():
-                                patient_name = gr.Textbox(label="Patient Name", placeholder="Enter patient name")
-                                record_id = gr.Textbox(label="Record ID", placeholder="Enter record ID")
-                            
+        # Create main layout
+        with gr.Row():
+            # Left column - Input section
+            with gr.Column(scale=1):
+                with gr.Box(elem_classes="container patient-info"):
+                    gr.Markdown("### Patient Information")
+                    
+                    with gr.Row():
+                        patient_name = gr.Textbox(label="Patient Name", placeholder="Enter patient name")
+                        record_id = gr.Textbox(label="Record ID", placeholder="Enter record ID")
+                    
+                    with gr.Row():
+                        age = gr.Number(label="Age", value=8, minimum=1, maximum=120)
+                        gender = gr.Radio(["male", "female", "other"], label="Gender", value="male")
+                    
+                    with gr.Row():
+                        assessment_date = gr.Textbox(label="Assessment Date", 
+                                           placeholder="MM/DD/YYYY", 
+                                           value=None)
+                        clinician_name = gr.Textbox(label="Clinician", 
+                                          placeholder="Enter clinician name")
+                
+                with gr.Box(elem_classes="container speech-sample"):
+                    gr.Markdown("### Speech Sample")
+                    
+                    # Add sample button
+                    sample_btn = gr.Button("Load Sample Transcript", size="sm")
+                    
+                    # Transcript input
+                    transcript = gr.Textbox(
+                        label="Transcript", 
+                        placeholder="Paste the speech transcript here...",
+                        lines=10
+                    )
+                    
+                    # Add info about transcript format
+                    gr.Markdown(
+                        """
+                        <div class="info-box">
+                            <strong>Transcript Format:</strong> Use CHAT format with *PAR: for patient lines. 
+                            Mark word-finding with &-um, paraphasias with [*], and provide intended words with [: word].
+                        </div>
+                        """,
+                        elem_classes="markdown-text"
+                    )
+                    
+                    # File upload
+                    file_upload = gr.File(
+                        label="Or upload a transcript file", 
+                        file_types=["text", "txt", "pdf", "rtf"]
+                    )
+                    
+                    # Analysis button
+                    analyze_btn = gr.Button("Analyze Speech Sample", variant="primary", size="lg")
+                
+                # Add API credential section (collapsible)
+                with gr.Accordion("API Configuration", open=False):
+                    gr.Markdown("""
+                    ### AWS Bedrock Credentials
+                    
+                    For full functionality, add your AWS credentials as environment variables or secrets in your HuggingFace Space:
+                    - AWS_ACCESS_KEY
+                    - AWS_SECRET_KEY
+                    - AWS_REGION (default: us-east-1)
+                    
+                    Without credentials, the app will run in demo mode with simulated responses.
+                    """)
+            
+            # Right column - Results section
+            with gr.Column(scale=1):
+                with gr.Box(elem_classes="container results-container"):
+                    with gr.Tabs() as tabs:
+                        # Summary tab
+                        with gr.TabItem("Summary", id=0, elem_classes="tab-content"):
                             with gr.Row():
-                                age = gr.Number(label="Age", value=8, minimum=1, maximum=120)
-                                gender = gr.Radio(["male", "female", "other"], label="Gender", value="male")
+                                output_image = gr.Image(label="Speech Factors & CASL-2 Scores", 
+                                                     show_label=True, elem_classes="viz-container")
                             
                             with gr.Row():
-                                assessment_date = gr.Textbox(
-                                    label="Assessment Date", 
-                                    placeholder="MM/DD/YYYY", 
-                                    value=datetime.now().strftime('%m/%d/%Y')
-                                )
-                                clinician_name = gr.Textbox(
-                                    label="Clinician", 
-                                    placeholder="Enter clinician name"
-                                )
+                                radar_chart = gr.Image(label="Severity Profile", 
+                                                     show_label=True, elem_classes="viz-container")
+                                
+                            with gr.Box():
+                                gr.Markdown("### Key Findings", elem_classes="markdown-text")
+                                speech_factors_table = gr.DataFrame(label="Speech Factors Analysis", 
+                                                                  headers=["Factor", "Occurrences", "Severity (Percentile)"],
+                                                                  interactive=False)
+                                casl_table = gr.DataFrame(label="CASL-2 Assessment", 
+                                                        headers=["Domain", "Standard Score", "Percentile", "Performance Level"],
+                                                        interactive=False)
                         
-                        # Speech sample panel
-                        with gr.Box(elem_classes="container speech-sample"):
-                            gr.Markdown("### Speech Sample")
+                        # Treatment tab
+                        with gr.TabItem("Treatment Plan", id=1, elem_classes="tab-content"):
+                            gr.Markdown("### Recommended Treatment Approaches", elem_classes="markdown-text")
+                            treatment_md = gr.Markdown(elem_classes="treatment-panel")
                             
-                            # Sample button
-                            sample_btn = gr.Button("Load Sample Transcript", size="sm")
+                            gr.Markdown("### Clinical Rationale", elem_classes="markdown-text")
+                            explanation_md = gr.Markdown(elem_classes="panel")
                             
-                            # Transcript input
-                            transcript = gr.Textbox(
-                                label="Transcript", 
-                                placeholder="Paste the speech transcript here...",
-                                lines=10
-                            )
+                            with gr.Accordion("Supporting Evidence", open=False):
+                                gr.Markdown("""
+                                <table class="evidence-table">
+                                  <tr>
+                                    <th>Factor</th>
+                                    <th>Evidence-based Approaches</th>
+                                    <th>References</th>
+                                  </tr>
+                                  <tr>
+                                    <td>Word Retrieval</td>
+                                    <td>Semantic feature analysis, phonological cueing, word generation tasks</td>
+                                    <td>Boyle, 2010; Kiran & Thompson, 2003</td>
+                                  </tr>
+                                  <tr>
+                                    <td>Grammatical Errors</td>
+                                    <td>Treatment of Underlying Forms (TUF), Morphosyntactic therapy</td>
+                                    <td>Thompson et al., 2003; Ebbels, 2014</td>
+                                  </tr>
+                                  <tr>
+                                    <td>Fluency/Prosody</td>
+                                    <td>Rate control, rhythmic cueing, contrastive stress exercises</td>
+                                    <td>Ballard et al., 2010; Tamplin & Baker, 2017</td>
+                                  </tr>
+                                </table>
+                                """, elem_classes="markdown-text")
+                        
+                        # Evidence tab 
+                        with gr.TabItem("Language Sample Evidence", id=2, elem_classes="tab-content"):
+                            gr.Markdown("### Speech Sample Evidence", elem_classes="markdown-text")
                             
-                            # Add info about transcript format
-                            gr.Markdown(
-                                """
-                                <div class="info-box">
-                                    <strong>Transcript Format:</strong> Use CHAT format with *PAR: for patient lines. 
-                                    Mark word-finding with &-um, paraphasias with [*], and provide intended words with [: word].
-                                </div>
-                                """,
-                                elem_classes="markdown-text"
-                            )
+                            # Create a collapsible section for each speech factor
+                            factors = ["Word Retrieval", "Grammatical Errors", "Repetitions/Revisions", 
+                                       "Fluency", "Neologisms", "Perseveration"]
                             
-                            # File upload
-                            file_upload = gr.File(
-                                label="Or upload a transcript file", 
-                                file_types=["text", "txt", "pdf", "rtf"]
-                            )
+                            for factor in factors:
+                                with gr.Accordion(f"{factor} Examples", open=False):
+                                    gr.Markdown(f"Examples of {factor.lower()} will be highlighted here from the transcript.")
                             
-                            # Analysis button
-                            analyze_btn = gr.Button("Analyze Speech Sample", variant="primary", size="lg")
-                    
-                    # Right column - Results section
-                    with gr.Column(scale=1):
-                        with gr.Box(elem_classes="container results-container"):
-                            with gr.Tabs() as results_tabs:
-                                # Summary tab
-                                with gr.TabItem("Summary", id=0, elem_classes="tab-content"):
-                                    with gr.Row():
-                                        output_image = gr.Image(
-                                            label="Speech Factors & CASL-2 Scores", 
-                                            show_label=True, 
-                                            elem_classes="viz-container"
-                                        )
-                                    
-                                    with gr.Row():
-                                        radar_chart = gr.Image(
-                                            label="Severity Profile", 
-                                            show_label=True, 
-                                            elem_classes="viz-container"
-                                        )
-                                        
-                                    with gr.Box():
-                                        gr.Markdown("### Key Findings", elem_classes="markdown-text")
-                                        speech_factors_table = gr.DataFrame(
-                                            label="Speech Factors Analysis", 
-                                            headers=["Factor", "Occurrences", "Severity (Percentile)"],
-                                            interactive=False
-                                        )
-                                        casl_table = gr.DataFrame(
-                                            label="CASL-2 Assessment", 
-                                            headers=["Domain", "Standard Score", "Percentile", "Performance Level"],
-                                            interactive=False
-                                        )
-                                
-                                # Treatment tab
-                                with gr.TabItem("Treatment Plan", id=1, elem_classes="tab-content"):
-                                    gr.Markdown("### Recommended Treatment Approaches", elem_classes="markdown-text")
-                                    treatment_md = gr.Markdown(elem_classes="treatment-panel")
-                                    
-                                    gr.Markdown("### Clinical Rationale", elem_classes="markdown-text")
-                                    explanation_md = gr.Markdown(elem_classes="panel")
-                                    
-                                    with gr.Accordion("Supporting Evidence", open=False):
-                                        gr.Markdown("""
-                                        <table class="evidence-table">
-                                          <tr>
-                                            <th>Factor</th>
-                                            <th>Evidence-based Approaches</th>
-                                            <th>References</th>
-                                          </tr>
-                                          <tr>
-                                            <td>Word Retrieval</td>
-                                            <td>Semantic feature analysis, phonological cueing, word generation tasks</td>
-                                            <td>Boyle, 2010; Kiran & Thompson, 2003</td>
-                                          </tr>
-                                          <tr>
-                                            <td>Grammatical Errors</td>
-                                            <td>Treatment of Underlying Forms (TUF), Morphosyntactic therapy</td>
-                                            <td>Thompson et al., 2003; Ebbels, 2014</td>
-                                          </tr>
-                                          <tr>
-                                            <td>Fluency/Prosody</td>
-                                            <td>Rate control, rhythmic cueing, contrastive stress exercises</td>
-                                            <td>Ballard et al., 2010; Tamplin & Baker, 2017</td>
-                                          </tr>
-                                        </table>
-                                        """, elem_classes="markdown-text")
-                                
-                                # Full report tab
-                                with gr.TabItem("Full Report", id=2, elem_classes="tab-content"):
-                                    full_analysis = gr.Markdown()
-                                    
-                                    # Add PDF export option
-                                    export_btn = gr.Button("Export Report as PDF", variant="secondary")
-                                    export_status = gr.Markdown("")
-            
-            # ===============================
-            # Report Generator Tab
-            # ===============================
-            with gr.TabItem("Report Generator", id=1):
-                with gr.Row():
-                    with gr.Column(scale=1):
-                        gr.Markdown("### Generate Professional Reports")
-                        
-                        # Patient info
-                        with gr.Box(elem_classes="container patient-info"):
-                            gr.Markdown("#### Patient Information")
-                            report_patient_name = gr.Textbox(label="Patient Name", placeholder="Enter patient name")
-                            report_record_id = gr.Textbox(label="Record ID", placeholder="Enter record ID")
-                            report_age = gr.Number(label="Age", value=8, minimum=1, maximum=120)
-                            report_gender = gr.Radio(["male", "female", "other"], label="Gender", value="male")
-                            report_date = gr.Textbox(
-                                label="Assessment Date", 
-                                placeholder="MM/DD/YYYY", 
-                                value=datetime.now().strftime('%m/%d/%Y')
-                            )
-                            report_clinician = gr.Textbox(label="Clinician", placeholder="Enter clinician name")
-                        
-                        with gr.Box():
-                            gr.Markdown("#### Assessment Results")
-                            report_results = gr.Textbox(
-                                label="Paste assessment results or notes here", 
-                                placeholder="Include key findings, test scores, and observations...",
-                                lines=10
-                            )
+                            gr.Markdown("### Transcript Annotations", elem_classes="markdown-text")
+                            gr.Markdown("A detailed analysis of the transcript will appear here after processing.")
                             
-                            report_type = gr.Radio(
-                                ["Formal (for professionals)", "Parent-friendly"], 
-                                label="Report Type",
-                                value="Formal (for professionals)"
-                            )
+                        # Full report tab
+                        with gr.TabItem("Full Report", id=3, elem_classes="tab-content"):
+                            full_analysis = gr.Markdown()
                             
-                            generate_report_btn = gr.Button("Generate Report", variant="primary")
-                    
-                    with gr.Column(scale=1):
-                        report_output = gr.Markdown()
-                        report_download_btn = gr.Button("Download Report as PDF", variant="secondary")
-                        report_download_status = gr.Markdown("")
-            
-            # ===============================
-            # Transcription Tool Tab
-            # ===============================
-            with gr.TabItem("Transcription Tool", id=2):
-                with gr.Row():
-                    with gr.Column(scale=1):
-                        gr.Markdown("### Audio Transcription Tool")
-                        gr.Markdown("Upload an audio recording to automatically transcribe it in CHAT format.")
-                        
-                        audio_input = gr.Audio(type="filepath", label="Upload Audio Recording")
-                        
-                        with gr.Row():
-                            transcription_age = gr.Number(label="Patient Age", value=8, minimum=1, maximum=120)
-                            transcribe_btn = gr.Button("Transcribe Audio", variant="primary")
-                    
-                    with gr.Column(scale=1):
-                        transcription_output = gr.Textbox(
-                            label="Transcription Result", 
-                            placeholder="Transcription will appear here...",
-                            lines=12
-                        )
-                        
-                        with gr.Row():
-                            copy_to_analysis_btn = gr.Button("Use for Analysis", variant="secondary")
-                            edit_transcription_btn = gr.Button("Edit Transcription", variant="secondary")
-            
-            # ===============================
-            # SLP Assistant Tab
-            # ===============================
-            with gr.TabItem("SLP Assistant", id=3):
-                with gr.Row():
-                    with gr.Column(scale=1):
-                        gr.Markdown("### SLP Knowledge Assistant")
-                        gr.Markdown("Ask questions about CASL assessment, therapy techniques, or SLP best practices.")
-                        
-                        question_input = gr.Textbox(
-                            label="Your Question", 
-                            placeholder="e.g., What activities help improve word-finding skills?",
-                            lines=3
-                        )
-                        
-                        ask_question_btn = gr.Button("Ask Question", variant="primary")
-                        
-                        # Quick question buttons
-                        gr.Markdown("#### Common Questions")
-                        with gr.Row():
-                            q1_btn = gr.Button("What is CASL?")
-                            q2_btn = gr.Button("How do I interpret scores?")
-                        
-                        with gr.Row():
-                            q3_btn = gr.Button("Activities for word finding")
-                            q4_btn = gr.Button("When to reassess")
-                    
-                    with gr.Column(scale=1):
-                        answer_output = gr.Markdown()
-                        
-                        with gr.Accordion("References", open=False):
-                            gr.Markdown("""
-                            - American Speech-Language-Hearing Association (ASHA)
-                            - Comprehensive Assessment of Spoken Language (CASL-2) Manual
-                            - Evidence-Based Practice in Speech-Language Pathology
-                            - Current research in pediatric language intervention
-                            """)
+                            # Add PDF export option
+                            export_btn = gr.Button("Export Report as PDF", variant="secondary")
+                            export_status = gr.Markdown("")
         
-        # ===============================
-        # Event Handlers
-        # ===============================
+        # Footer
+        gr.HTML(
+            """
+            <div class="footer">
+                <p>CASL Speech Analysis Tool | For professional use by Speech-Language Pathologists</p>
+                <p>Results should be interpreted by qualified professionals in conjunction with other assessment methods.</p>
+            </div>
+            """
+        )
         
-        # Load sample transcript button
+        # Define app functions
+        
+        # Function to load sample transcript
         def load_sample():
             return SAMPLE_TRANSCRIPT
         
-        sample_btn.click(load_sample, outputs=[transcript])
-        
-        # File upload handler
-        file_upload.upload(process_upload, file_upload, transcript)
-        
-        # Analysis button handler
+        # Handle file upload
+        def process_upload(file):
+            if file is None:
+                return ""
+            
+            file_path = file.name
+            if file_path.endswith('.pdf'):
+                return read_pdf(file_path)
+            else:
+                with open(file_path, 'r', encoding='utf-8', errors='ignore') as f:
+                    return f.read()
+        
+        # Handle analysis button click
         def on_analyze_click(transcript_text, age_val, gender_val, patient_name_val, record_id_val, clinician_val, assessment_date_val):
             if not transcript_text or len(transcript_text.strip()) < 50:
                 return (
@@ -1090,6 +818,17 @@ def create_interface():
                     f"Error details: {str(e)}"
                 )
         
+        # Function to simulate PDF export
+        def export_pdf():
+            # In a real app, this would generate a PDF
+            # For this demo, we'll just return a status message
+            return "Report export initiated. The PDF would be downloaded in a production environment."
+        
+        # Connect UI components to functions
+        sample_btn.click(load_sample, outputs=[transcript])
+        file_upload.upload(process_upload, file_upload, transcript)
+        export_btn.click(export_pdf, outputs=[export_status])
+        
         analyze_btn.click(
             on_analyze_click,
             inputs=[
@@ -1106,99 +845,9 @@ def create_interface():
                 full_analysis
             ]
         )
-        
-        # Export report button simulation
-        def export_pdf_simulation():
-            return "Report export initiated. The PDF would be downloaded in a production environment."
-        
-        export_btn.click(export_pdf_simulation, outputs=[export_status])
-        report_download_btn.click(export_pdf_simulation, outputs=[report_download_status])
-        
-        # Report generator button
-        def on_generate_report(name, record_id, age, gender, date, clinician, results, report_type):
-            patient_info = {
-                "name": name,
-                "record_id": record_id,
-                "age": age,
-                "gender": gender,
-                "assessment_date": date,
-                "clinician": clinician
-            }
-            
-            report_type_val = "formal" if "Formal" in report_type else "parent-friendly"
-            
-            try:
-                report = generate_report(patient_info, results, report_type_val)
-                return report
-            except Exception as e:
-                logger.exception("Error generating report")
-                return f"Error generating report: {str(e)}"
-        
-        generate_report_btn.click(
-            on_generate_report,
-            inputs=[
-                report_patient_name, report_record_id, report_age,
-                report_gender, report_date, report_clinician,
-                report_results, report_type
-            ],
-            outputs=[report_output]
-        )
-        
-        # Transcription button
-        def on_transcribe_audio(audio_path, age):
-            try:
-                if not audio_path:
-                    return "Please upload an audio file to transcribe."
-                
-                transcription = transcribe_audio(audio_path, age)
-                return transcription
-            except Exception as e:
-                logger.exception("Error transcribing audio")
-                return f"Error transcribing audio: {str(e)}"
-        
-        transcribe_btn.click(
-            on_transcribe_audio,
-            inputs=[audio_input, transcription_age],
-            outputs=[transcription_output]
-        )
-        
-        # Copy transcription to analysis
-        def copy_to_analysis(transcription):
-            return transcription, gr.update(selected=0)  # Switches to the Analysis tab
-        
-        copy_to_analysis_btn.click(
-            copy_to_analysis,
-            inputs=[transcription_output],
-            outputs=[transcript, main_tabs]
-        )
-        
-        # SLP Assistant question handling
-        def on_ask_question(question):
-            try:
-                answer = answer_slp_question(question)
-                return answer
-            except Exception as e:
-                logger.exception("Error getting answer")
-                return f"Error: {str(e)}"
-        
-        ask_question_btn.click(
-            on_ask_question,
-            inputs=[question_input],
-            outputs=[answer_output]
-        )
-        
-        # Quick question buttons
-        q1_btn.click(lambda: "What is CASL?", outputs=[question_input])
-        q2_btn.click(lambda: "How do I interpret CASL scores?", outputs=[question_input])
-        q3_btn.click(lambda: "What activities help with word finding difficulties?", outputs=[question_input])
-        q4_btn.click(lambda: "When should I reassess a patient?", outputs=[question_input])
-        
+    
     return app
 
-# ===============================
-# Main Application
-# ===============================
-
 # Create requirements.txt file for HuggingFace Spaces
 def create_requirements_file():
     requirements = [
@@ -1227,4 +876,4 @@ if __name__ == "__main__":
     
     # Launch the Gradio app
     app = create_interface()
-    app.launch()
+    app.launch()