about summary refs log tree commit diff stats
path: root/bash/talk-to-computer/model_selector.sh
diff options
context:
space:
mode:
Diffstat (limited to 'bash/talk-to-computer/model_selector.sh')
-rwxr-xr-xbash/talk-to-computer/model_selector.sh380
1 files changed, 380 insertions, 0 deletions
diff --git a/bash/talk-to-computer/model_selector.sh b/bash/talk-to-computer/model_selector.sh
new file mode 100755
index 0000000..d3a46a1
--- /dev/null
+++ b/bash/talk-to-computer/model_selector.sh
@@ -0,0 +1,380 @@
+#!/bin/bash
+
+# Dynamic Model Selector
+# Intelligently selects models based on task type, availability, and capabilities
+
+# --- Model Capability Database ---
+
+# Model database using simple variables (compatible with older bash)
+MODEL_DB_DIR="${LOG_DIR:-/tmp/ai_thinking}/model_db"
+
+# Initialize model database with simple variables
+init_model_database() {
+    # Create model database directory
+    mkdir -p "$MODEL_DB_DIR"
+
+    # Model capabilities by task type (using file-based storage for compatibility)
+
+    # === CONFIGURED MODELS ===
+    cat > "$MODEL_DB_DIR/llama3_8b_instruct_q4_K_M" << 'EOF'
+coding=0.8
+reasoning=0.9
+creative=0.7
+size=8
+speed=0.8
+EOF
+
+    cat > "$MODEL_DB_DIR/phi3_3_8b_mini_4k_instruct_q4_K_M" << 'EOF'
+coding=0.7
+reasoning=0.8
+creative=0.6
+size=3.8
+speed=0.9
+EOF
+
+    cat > "$MODEL_DB_DIR/deepseek_r1_1_5b" << 'EOF'
+coding=0.6
+reasoning=0.9
+creative=0.5
+size=1.5
+speed=0.95
+EOF
+
+    cat > "$MODEL_DB_DIR/gemma3n_e2b" << 'EOF'
+coding=0.8
+reasoning=0.8
+creative=0.8
+size=2
+speed=0.85
+EOF
+
+    cat > "$MODEL_DB_DIR/dolphin3_latest" << 'EOF'
+coding=0.6
+reasoning=0.7
+creative=0.8
+size=7
+speed=0.7
+EOF
+
+    # === ADDITIONAL MODELS FROM OLLAMA LIST ===
+
+    # Llama 3.1 - Newer version, should be similar to Llama 3 but potentially better
+    cat > "$MODEL_DB_DIR/llama3_1_8b" << 'EOF'
+coding=0.82
+reasoning=0.92
+creative=0.72
+size=8
+speed=0.82
+EOF
+
+    # DeepSeek R1 7B - Larger reasoning model
+    cat > "$MODEL_DB_DIR/deepseek_r1_7b" << 'EOF'
+coding=0.65
+reasoning=0.95
+creative=0.55
+size=7
+speed=0.7
+EOF
+
+    # Gemma 3N Latest - Larger version of e2b
+    cat > "$MODEL_DB_DIR/gemma3n_latest" << 'EOF'
+coding=0.82
+reasoning=0.82
+creative=0.82
+size=7.5
+speed=0.8
+EOF
+
+    # Gemma 3 4B - Different model family
+    cat > "$MODEL_DB_DIR/gemma3_4b" << 'EOF'
+coding=0.75
+reasoning=0.78
+creative=0.75
+size=4
+speed=0.85
+EOF
+
+    # Qwen2.5 7B - Alibaba model, general purpose
+    cat > "$MODEL_DB_DIR/qwen2_5_7b" << 'EOF'
+coding=0.78
+reasoning=0.85
+creative=0.7
+size=7
+speed=0.75
+EOF
+
+    # Qwen3 8B - Latest Qwen model
+    cat > "$MODEL_DB_DIR/qwen3_8b" << 'EOF'
+coding=0.8
+reasoning=0.88
+creative=0.72
+size=8
+speed=0.78
+EOF
+
+    # Qwen3 4B - Smaller Qwen model
+    cat > "$MODEL_DB_DIR/qwen3_4b" << 'EOF'
+coding=0.75
+reasoning=0.82
+creative=0.68
+size=4
+speed=0.85
+EOF
+
+    # Qwen3 1.7B - Smallest Qwen model
+    cat > "$MODEL_DB_DIR/qwen3_1_7b" << 'EOF'
+coding=0.65
+reasoning=0.7
+creative=0.6
+size=1.7
+speed=0.95
+EOF
+
+    # DeepScaler - Performance optimization focus
+    cat > "$MODEL_DB_DIR/deepscaler_latest" << 'EOF'
+coding=0.7
+reasoning=0.8
+creative=0.65
+size=3.6
+speed=0.88
+EOF
+
+    # Yasser Qwen2.5 - Fine-tuned variant
+    cat > "$MODEL_DB_DIR/yasserrmd_Qwen2_5_7B_Instruct_1M_latest" << 'EOF'
+coding=0.82
+reasoning=0.9
+creative=0.75
+size=7
+speed=0.75
+EOF
+
+    # Nomic Embed Text - Specialized for embeddings, not general tasks
+    cat > "$MODEL_DB_DIR/nomic_embed_text_latest" << 'EOF'
+coding=0.1
+reasoning=0.1
+creative=0.1
+size=0.274
+speed=0.95
+EOF
+}
+
+# Get model capability score
+get_model_capability() {
+    local model_key="$1"
+    local task_type="$2"
+
+    # Convert model name to filename-friendly format
+    local safe_name=$(echo "$model_key" | tr ':' '_' | tr '.' '_')
+    local db_file="$MODEL_DB_DIR/$safe_name"
+
+    if [ -f "$db_file" ]; then
+        grep "^${task_type}=" "$db_file" | cut -d'=' -f2
+    else
+        echo "0.5"  # Default capability score
+    fi
+}
+
+# Get model size
+get_model_size() {
+    local model_key="$1"
+    local safe_name=$(echo "$model_key" | tr ':' '_' | tr '.' '_')
+    local db_file="$MODEL_DB_DIR/$safe_name"
+
+    if [ -f "$db_file" ]; then
+        grep "^size=" "$db_file" | cut -d'=' -f2
+    else
+        echo "5"  # Default size
+    fi
+}
+
+# Get model speed
+get_model_speed() {
+    local model_key="$1"
+    local safe_name=$(echo "$model_key" | tr ':' '_' | tr '.' '_')
+    local db_file="$MODEL_DB_DIR/$safe_name"
+
+    if [ -f "$db_file" ]; then
+        grep "^speed=" "$db_file" | cut -d'=' -f2
+    else
+        echo "0.5"  # Default speed
+    fi
+}
+
+# --- Model Discovery ---
+
+# Get list of available models
+get_available_models() {
+    ollama list 2>/dev/null | tail -n +2 | awk '{print $1}' | sort
+}
+
+# Check if a model is available
+is_model_available() {
+    local model="$1"
+    ollama list 2>/dev/null | grep -q "^${model}\s"
+}
+
+# --- Task Type Classification ---
+
+# Classify task type from prompt and mechanism
+classify_task_type() {
+    local prompt="$1"
+    local mechanism="$2"
+
+    # Task type classification based on mechanism
+    case "$mechanism" in
+        "puzzle")
+            echo "coding"
+            ;;
+        "socratic")
+            echo "reasoning"
+            ;;
+        "exploration")
+            echo "reasoning"
+            ;;
+        "consensus")
+            echo "reasoning"
+            ;;
+        "critique")
+            echo "reasoning"
+            ;;
+        "synthesis")
+            echo "reasoning"
+            ;;
+        "peer-review")
+            echo "reasoning"
+            ;;
+        *)
+            # Fallback to keyword-based classification
+            if echo "$prompt" | grep -q -i "code\|algorithm\|function\|program\|implement"; then
+                echo "coding"
+            elif echo "$prompt" | grep -q -i "write\|story\|creative\|poem\|essay"; then
+                echo "creative"
+            else
+                echo "reasoning"
+            fi
+            ;;
+    esac
+}
+
+# --- Model Selection Logic ---
+
+# Select best model for task
+select_best_model() {
+    local task_type="$1"
+    local available_models="$2"
+    local preferred_models="$3"
+
+    local best_model=""
+    local best_score=0
+
+    # First, try preferred models if available
+    if [ -n "$preferred_models" ]; then
+        for model in $preferred_models; do
+            if echo "$available_models" | grep -q "^${model}$" && is_model_available "$model"; then
+                local capability_score=$(get_model_capability "$model" "$task_type")
+                local speed_score=$(get_model_speed "$model")
+                local model_size=$(get_model_size "$model")
+                local size_score=$(echo "scale=2; $model_size / 10" | bc -l 2>/dev/null || echo "0.5")
+
+                # Calculate weighted score (capability is most important)
+                local total_score=$(echo "scale=2; ($capability_score * 0.6) + ($speed_score * 0.3) + ($size_score * 0.1)" | bc -l 2>/dev/null || echo "0.5")
+
+                if (( $(echo "$total_score > $best_score" | bc -l 2>/dev/null || echo "0") )); then
+                    best_score=$total_score
+                    best_model=$model
+                fi
+            fi
+        done
+    fi
+
+    # If no preferred model is good, find best available model
+    if [ -z "$best_model" ]; then
+        for model in $available_models; do
+            if is_model_available "$model"; then
+                local capability_score=$(get_model_capability "$model" "$task_type")
+                local speed_score=$(get_model_speed "$model")
+                local model_size=$(get_model_size "$model")
+                local size_score=$(echo "scale=2; $model_size / 10" | bc -l 2>/dev/null || echo "0.5")
+
+                local total_score=$(echo "scale=2; ($capability_score * 0.6) + ($speed_score * 0.3) + ($size_score * 0.1)" | bc -l 2>/dev/null || echo "0.5")
+
+                if (( $(echo "$total_score > $best_score" | bc -l 2>/dev/null || echo "0") )); then
+                    best_score=$total_score
+                    best_model=$model
+                fi
+            fi
+        done
+    fi
+
+    if [ -n "$best_model" ]; then
+        echo "Selected model: $best_model (score: $best_score, task: $task_type)" 1>&2
+        echo "$best_model"
+    else
+        echo "No suitable model found" >&2
+        echo ""
+    fi
+}
+
+# --- Main Selection Function ---
+
+# Smart model selection
+select_model_for_task() {
+    local prompt="$1"
+    local mechanism="$2"
+    local preferred_models="$3"
+
+    # Initialize database
+    init_model_database
+
+    # Get available models
+    local available_models
+    available_models=$(get_available_models)
+
+    if [ -z "$available_models" ]; then
+        echo "No models available via Ollama" >&2
+        echo ""
+        return 1
+    fi
+
+    # Classify task type
+    local task_type
+    task_type=$(classify_task_type "$prompt" "$mechanism")
+
+    # Select best model
+    local selected_model
+    selected_model=$(select_best_model "$task_type" "$available_models" "$preferred_models")
+
+    if [ -n "$selected_model" ]; then
+        echo "$selected_model"
+        return 0
+    else
+        echo ""
+        return 1
+    fi
+}
+
+# --- Utility Functions ---
+
+# Get model info
+get_model_info() {
+    local model="$1"
+
+    echo "Model: $model"
+    echo "Size: $(get_model_size "$model")B"
+    echo "Speed: $(get_model_speed "$model")"
+    echo "Coding: $(get_model_capability "$model" "coding")"
+    echo "Reasoning: $(get_model_capability "$model" "reasoning")"
+    echo "Creative: $(get_model_capability "$model" "creative")"
+}
+
+# Export functions
+export -f init_model_database
+export -f get_available_models
+export -f is_model_available
+export -f classify_task_type
+export -f select_best_model
+export -f select_model_for_task
+export -f get_model_info
+export -f get_model_capability
+export -f get_model_size
+export -f get_model_speed
generated by cgit-pink 1.4.1-2-gfad0 (git 2.36.2.497.gbbea4dcf42) at 2025-08-23 08:27:41 +0000