refactor (model): replacing phi3 by phi4-mini

CONFIGURATION_GUIDE.md

@@ -76,7 +76,7 @@ The configuration file includes:
     {
       "title": "SQL Generator",
       "prompt": "Generate SQL for: {question}\nSchema: {schema}",
-      "model": "phi3",
+      "model": "phi4-mini",
       "subscribeTopic": "START",
       "publishTopic": "SQL_GENERATED",
       "showResult": true
@@ -351,7 +351,7 @@ config = {
         {
             "title": "SQL Generator",
             "prompt": "...",
-            "model": "phi3",
+            "model": "phi4-mini",
             "subscribeTopic": "START",
             "publishTopic": "SQL",
             "showResult": True
@@ -440,7 +440,7 @@ merge_configs("pipeline-a.json", "pipeline-b.json", "merged-pipeline.json")
 ### Issue: Agents not working after load
 
 **Cause**: Model might not be available  
-**Solution**: Check agent "model" field matches available models (phi3, cniongolo/biomistral)
+**Solution**: Check agent "model" field matches available models (phi4-mini, cniongolo/biomistral)
 
 ### Issue: Topics not matching after load
 

Dockerfile

@@ -31,7 +31,7 @@ EXPOSE 7860
 ENV OLLAMA_HOST=0.0.0.0:11434
 ENV PYTHONUNBUFFERED=1
 
-# Create startup script - only phi3 and biomistral for free tier
+# Create startup script - only phi4-mini and biomistral for free tier
 RUN echo '#!/bin/bash\n\
 set -e\n\
 \n\
@@ -42,8 +42,8 @@ OLLAMA_PID=$!\n\
 echo "Waiting for Ollama to be ready..."\n\
 sleep 10\n\
 \n\
-echo "Pulling phi3 model..."\n\
-ollama pull phi3\n\
+echo "Pulling phi4-mini model..."\n\
+ollama pull phi4-mini\n\
 \n\
 echo "Pulling MedGemma model..."\n\
 ollama pull MedAIBase/MedGemma1.5:4b\n\

ENHANCEMENTS_SUMMARY.md

@@ -95,7 +95,7 @@ Added complete configuration persistence:
     {
       "title": "SQL Generator",
       "prompt": "Generate SQL...",
-      "model": "phi3",
+      "model": "phi4-mini",
       "subscribeTopic": "START",
       "publishTopic": "SQL",
       "showResult": true

EXAMPLES.md

@@ -1,10 +1,10 @@
 # Pub/Sub Multi-Agent System - Example Configurations
 
-**Note**: This deployment includes **phi3** (general purpose), **MedAIBase/MedGemma1.5:4b** (medical/healthcare), and **deepseek-coder:1.3b** (coding) models.
+**Note**: This deployment includes **phi4-mini** (general purpose), **MedAIBase/MedGemma1.5:4b** (medical/healthcare), and **deepseek-coder:1.3b** (coding) models.
 
 **Important**: Use `{question}` in prompts to access the user's question, `{schema}` for database schema, and `{input}` for messages from subscribed topics (all case insensitive).
 
-## Example 1: Natural Language to SQL Pipeline (using phi3)
+## Example 1: Natural Language to SQL Pipeline (using phi4-mini)
 
 ### Agent 1: Question Analyzer
 - **Title**: Question Analyzer
@@ -22,7 +22,7 @@ Analyze the question and identify:
 
 Respond with a clear analysis.
 ```
-- **Model**: phi3
+- **Model**: phi4-mini
 - **Subscribe Topic**: START
 - **Publish Topic**: QUESTION_ANALYZED
 
@@ -41,7 +41,7 @@ Original question: {question}
 Generate a SQL query that answers the user's question.
 Return ONLY the SQL query, no explanation.
 ```
-- **Model**: phi3
+- **Model**: phi4-mini
 - **Subscribe Topic**: QUESTION_ANALYZED
 - **Publish Topic**: SQL_GENERATED
 
@@ -58,7 +58,7 @@ Schema:
 If valid, return "VALID: " followed by the query.
 If invalid, return "INVALID: " followed by the corrected query.
 ```
-- **Model**: phi3
+- **Model**: phi4-mini
 - **Subscribe Topic**: SQL_GENERATED
 - **Publish Topic**: FINAL
 
@@ -163,7 +163,7 @@ Analyze the abstract and extract:
 2. Methodology
 3. Key findings
 ```
-- **Model**: phi3
+- **Model**: phi4-mini
 - **Subscribe Topic**: START
 - **Publish Topic**: ABSTRACT_ANALYZED
 
@@ -179,7 +179,7 @@ Evaluate the research methodology:
 2. What are the strengths?
 3. What are potential limitations?
 ```
-- **Model**: phi3
+- **Model**: phi4-mini
 - **Subscribe Topic**: ABSTRACT_ANALYZED
 - **Publish Topic**: METHODOLOGY_REVIEWED
 
@@ -192,13 +192,13 @@ Based on this methodology review:
 
 Generate a comprehensive summary of the paper suitable for a literature review.
 ```
-- **Model**: phi3
+- **Model**: phi4-mini
 - **Subscribe Topic**: METHODOLOGY_REVIEWED
 - **Publish Topic**: SUMMARY_COMPLETE
 
 ---
 
-## Example 5: Content Moderation Pipeline (using phi3)
+## Example 5: Content Moderation Pipeline (using phi4-mini)
 
 ### Agent 1: Content Classifier
 - **Title**: Content Classifier
@@ -213,7 +213,7 @@ Classify this content into one of these categories:
 
 Provide classification and brief reasoning.
 ```
-- **Model**: phi3
+- **Model**: phi4-mini
 - **Subscribe Topic**: START
 - **Publish Topic**: CLASSIFIED
 
@@ -230,13 +230,13 @@ If the content was marked as NEEDS_REVIEW, provide:
 
 If not NEEDS_REVIEW, just respond "NO REVIEW NEEDED"
 ```
-- **Model**: phi3
+- **Model**: phi4-mini
 - **Subscribe Topic**: CLASSIFIED
 - **Publish Topic**: REVIEW_COMPLETE
 
 ---
 
-## Example 5: Medical Symptom Analysis (phi3 can handle basic medical tasks)
+## Example 5: Medical Symptom Analysis (phi4-mini can handle basic medical tasks)
 
 ### Agent 1: Symptom Categorizer
 - **Title**: Symptom Categorizer  
@@ -253,7 +253,7 @@ Categorize these symptoms by body system:
 
 List each symptom under its appropriate category.
 ```
-- **Model**: phi3
+- **Model**: phi4-mini
 - **Subscribe Topic**: START
 - **Publish Topic**: SYMPTOMS_CATEGORIZED
 
@@ -271,7 +271,7 @@ Based on these symptoms, provide:
 
 Note: This is for educational purposes only.
 ```
-- **Model**: phi3
+- **Model**: phi4-mini
 - **Subscribe Topic**: SYMPTOMS_CATEGORIZED  
 - **Publish Topic**: DIAGNOSIS_COMPLETE
 
@@ -288,7 +288,7 @@ Note: This is for educational purposes only.
    - All three can be used together in any prompt
 
 3. **Model Selection**:
-   - **phi3**: Versatile general-purpose model - text analysis, SQL, reasoning, classification
+   - **phi4-mini**: Versatile general-purpose model - text analysis, SQL, reasoning, classification
    - **cniongolo/biomistral**: Medical and scientific tasks - diagnosis, clinical reasoning, biomedical analysis
 
 4. **Final Results**:

NER_AGENTS_GUIDE.md

@@ -224,7 +224,7 @@ ECG shows ST elevation. Troponin levels elevated at 0.5 ng/mL.
 
 **Agent 2: Entity Summarizer**
 - Title: `Summarize Findings`
-- Model: `phi3`
+- Model: `phi4-mini`
 - Subscribe: `CLINICAL_ENTITIES`
 - Publish: *(empty)*
 - Prompt:
@@ -304,7 +304,7 @@ No evidence of [mediastinal:ANATOMY] lymphadenopathy.
 - ☑ Show result
 
 **Agent 2: Entity Categorization**
-- Model: `phi3`
+- Model: `phi4-mini`
 - Subscribe: `ENTITIES`
 - Publish: `CATEGORIZED`
 - Prompt:
@@ -406,7 +406,7 @@ NER Agent → Regular LLM → Medical LLM
 
 **Example**:
 1. NER extracts entities from clinical note
-2. phi3 categorizes entities by type
+2. phi4-mini categorizes entities by type
 3. MedGemma generates clinical assessment
 
 ### 4. Understanding What Gets Analyzed

NER_TRANSFORMERS_IMPLEMENTATION.md

@@ -11,7 +11,7 @@ NER (Named Entity Recognition) agents are now implemented using HuggingFace Tran
 The system now supports two types of models:
 
 **1. LLM Models (via Ollama)**:
-- phi3
+- phi4-mini
 - MedAIBase/MedGemma1.5:4b
 - deepseek-coder:1.3b
 
@@ -223,7 +223,7 @@ Models cached at:
 - Much faster with GPU acceleration
 
 **LLM Models** (Ollama):
-- phi3: ~2-5s per prompt
+- phi4-mini: ~2-5s per prompt
 - MedGemma: ~3-7s per prompt
 - DeepSeek: ~1-3s per prompt
 
@@ -291,7 +291,7 @@ Errors are:
 **With Both Models Loaded**: ~850MB RAM
 
 **Plus LLM Models (Ollama)**:
-- phi3: ~4GB RAM
+- phi4-mini: ~4GB RAM
 - MedGemma: ~5GB RAM
 - DeepSeek: ~2GB RAM
 

QUICK_START.md

@@ -96,7 +96,7 @@ These all work:
 - **Benefit**: No more errors from capitalization mismatches!
 
 ### 3. Three Specialized Models
-- **phi3**: General-purpose tasks (3.8B params)
+- **phi4-mini**: General-purpose tasks (3.8B params)
 - **MedAIBase/MedGemma1.5:4b**: Medical/healthcare (4B params)
 - **deepseek-coder:1.3b**: Code generation and analysis (1.3B params)
 
@@ -161,7 +161,7 @@ Database schema:
 Generate a SQL query to answer this question.
 ```
 Note: Used `{QUESTION}` and `{schema}` in different cases - both work!
-- Model: `phi3`
+- Model: `phi4-mini`
 - Subscribe: `START`
 - Publish: `SQL_QUERY` *(optional - leave empty if not needed)*
 - ☑ Show result
@@ -175,7 +175,7 @@ Explain this SQL query in simple terms:
 
 Original question: {question}
 ```
-- Model: `phi3`
+- Model: `phi4-mini`
 - Subscribe: `SQL_QUERY`
 - Publish: *(leave empty)*
 - ☑ Show result

README.md

@@ -96,7 +96,7 @@ Final result displayed to user
 
 This deployment includes five specialized models:
 
-- **phi3**: General-purpose model (3.8B parameters) - Great for text analysis, SQL generation, summarization, reasoning, and general tasks
+- **phi4-mini**: General-purpose model (3.8B parameters) - Great for text analysis, SQL generation, summarization, reasoning, and general tasks
 - **MedAIBase/MedGemma1.5:4b**: Medical/healthcare model (4B parameters) - Specialized for clinical reasoning, medical documentation, and healthcare-related tasks
 - **deepseek-coder:1.3b**: Code generation model (1.3B parameters) - Optimized for programming, code analysis, debugging, and technical documentation
 - **samrawal/bert-base-uncased_clinical-ner**: Clinical NER model - Extracts medical entities (diseases, symptoms, medications) from clinical text

TUTORIAL.md

@@ -28,7 +28,7 @@ Briefly answer the question:
 
 Answer:
 ```
-- **Model**: phi3
+- **Model**: phi4-mini
 - **Subscribe Topic**: START
 - **Publish Topic**: SHORT_ANSWER
 - **Show result in Final Result box** [x]

static/index.html

@@ -27,7 +27,7 @@
           const fileInputRef = useRef(null);
 
           const models = [
-            "phi3",
+            "phi4-mini",
             "MedAIBase/MedGemma1.5:4b",
             "deepseek-coder:1.3b",
             "samrawal/bert-base-uncased_clinical-ner",
@@ -45,7 +45,7 @@
               id: Date.now(),
               title: `Agent ${agents.length + 1}`,
               prompt: '',
-              model: 'phi3',
+              model: 'phi4-mini',
               subscribeTopic: '',
               publishTopic: '',
               showResult: false