Ollama: Phase1综合练习

# Step 1: Install
curl -fsSL https://ollama.com/install.sh | sh

# Step 2: Pull model
ollama pull qwen2.5

# Step 3: API test
curl http://localhost:11434/api/chat -d '{
  "model": "qwen2.5",
  "messages": [{"role": "user", "content": "Hello"}],
  "stream": false
}'

#!/bin/bash
# End-to-end verification script
set -e

echo "=== Step 1: Verify Installation ==="
ollama --version

echo "=== Step 2: Verify Service ==="
curl -s http://localhost:11434/api/tags | python3 -m json.tool > /dev/null
echo "Service is running."

echo "=== Step 3: Pull Model ==="
ollama pull qwen2.5

echo "=== Step 4: CLI Test ==="
ollama run qwen2.5 "Say hello in one sentence"

echo "=== Step 5: REST API Test ==="
curl -s http://localhost:11434/api/chat -d '{
  "model": "qwen2.5",
  "messages": [{"role": "user", "content": "Hello"}],
  "stream": false
}' | python3 -c "import sys,json; print('API works:', json.load(sys.stdin)['message']['content'][:50])"

echo "=== All Steps Passed ==="

I'm a helpful AI assistant running locally on your machine...

#!/bin/bash
# Batch test different models with the same questions

QUESTIONS=(
    "What is the return policy for electronics?"
    "Translate to French: Free shipping on orders over $50"
    "Write a SQL query to find top 10 customers by revenue"
)

MODELS=("llama3.2:3b" "llama3.1:8b" "qwen2.5:7b")

for model in "${MODELS[@]}"; do
    echo "=== Model: $model ==="
    for q in "${QUESTIONS[@]}"; do
        echo "Q: $q"
        start=$(date +%s%N)
        response=$(curl -s http://localhost:11434/api/chat -d "{
            \"model\": \"$model\",
            \"messages\": [{\"role\": \"user\", \"content\": \"$q\"}],
            \"stream\": false,
            \"options\": {\"temperature\": 0.3}
        }" | python3 -c "import sys,json; d=json.load(sys.stdin); print(d['message']['content'][:100])")
        end=$(date +%s%N)
        elapsed=$(( (end - start) / 1000000 ))
        echo "A: ${response}..."
        echo "Time: ${elapsed}ms"
        echo ""
    done
done

{"status":"ok","data":{}}

#!/bin/bash
# Simple interactive chatbot using curl

API="http://localhost:11434/api/chat"
MODEL="qwen2.5"
MESSAGES='[{"role":"system","content":"You are a helpful assistant. Be concise."}]'

echo "ChatBot (type /quit to exit)"
echo "--------------------------------"

while true; do
    read -p "You: " input
    if [ "$input" = "/quit" ]; then
        echo "Goodbye!"
        break
    fi

    # Append user message
    MESSAGES=$(echo "$MESSAGES" | python3 -c "
import sys, json
msgs = json.load(sys.stdin)
msgs.append({'role': 'user', 'content': '$input'})
print(json.dumps(msgs))
")

    # Call API
    response=$(curl -s "$API" -d "{
        \"model\": \"$MODEL\",
        \"messages\": $MESSAGES,
        \"stream\": false,
        \"options\": {\"temperature\": 0.5}
    }")

    # Extract and print response
    content=$(echo "$response" | python3 -c "import sys,json; print(json.load(sys.stdin)['message']['content'])")
    echo "Bot: $content"

    # Append assistant response
    MESSAGES=$(echo "$MESSAGES" | python3 -c "
import sys, json
msgs = json.load(sys.stdin)
msgs.append({'role': 'assistant', 'content': '''$content'''})
print(json.dumps(msgs))
")
    echo ""
done

{"status":"ok","data":{}}

#!/bin/bash
# Quick PoC benchmark for local AI

API="http://localhost:11434/api/chat"
MODEL="qwen2.5"
REQUESTS=10

echo "=== Local AI PoC Benchmark ==="
echo "Model: $MODEL"
echo "Requests: $REQUESTS"
echo ""

total_time=0
total_tokens=0

for i in $(seq 1 $REQUESTS); do
    start=$(date +%s%N)
    response=$(curl -s "$API" -d "{
        \"model\": \"$MODEL\",
        \"messages\": [{\"role\": \"user\", \"content\": \"Explain the return policy briefly\"}],
        \"stream\": false,
        \"options\": {\"temperature\": 0.3}
    }")
    end=$(date +%s%N)

    elapsed_ms=$(( (end - start) / 1000000 ))
    tokens=$(echo "$response" | python3 -c "import sys,json; print(json.load(sys.stdin).get('eval_count', 0))")

    total_time=$((total_time + elapsed_ms))
    total_tokens=$((total_tokens + tokens))
    echo "Request $i: ${elapsed_ms}ms, ${tokens} tokens"
done

avg_time=$((total_time / REQUESTS))
avg_tokens=$((total_tokens / REQUESTS))
tput=$((total_tokens * 1000 / total_time))

echo ""
echo "=== Results ==="
echo "Avg latency: ${avg_time}ms"
echo "Avg tokens:  ${avg_tokens}"
echo "Throughput:  ${tput} tokens/s"
echo "Target met:  $([ $avg_time -lt 5000 ] && echo 'YES' || echo 'NO')"

{"status":"ok","data":{}}

#!/bin/bash
# Phase 1 self-assessment checklist

echo "=== Phase 1 Self-Assessment ==="
echo ""

checks=0
total=6

# Check 1: Ollama installed
if command -v ollama &> /dev/null; then
    echo "[PASS] Ollama is installed"
    ((checks++))
else
    echo "[FAIL] Ollama is not installed"
fi

# Check 2: Service running
if curl -s http://localhost:11434/api/tags > /dev/null 2>&1; then
    echo "[PASS] Ollama service is running"
    ((checks++))
else
    echo "[FAIL] Ollama service is not running"
fi

# Check 3: At least one model available
model_count=$(ollama list 2>/dev/null | tail -n +2 | wc -l)
if [ "$model_count" -gt 0 ]; then
    echo "[PASS] $model_count model(s) available"
    ((checks++))
else
    echo "[FAIL] No models pulled"
fi

# Check 4: CLI interaction works
if ollama run llama3.2 "test" > /dev/null 2>&1; then
    echo "[PASS] CLI interaction works"
    ((checks++))
else
    echo "[FAIL] CLI interaction failed"
fi

# Check 5: REST API responds
if curl -s http://localhost:11434/api/generate -d '{"model":"llama3.2","prompt":"hi","stream":false}' > /dev/null 2>&1; then
    echo "[PASS] REST API responds"
    ((checks++))
else
    echo "[FAIL] REST API not responding"
fi

# Check 6: Streaming works
if curl -s http://localhost:11434/api/chat -d '{"model":"llama3.2","messages":[{"role":"user","content":"hi"}]}' | grep -q '"done":true'; then
    echo "[PASS] Streaming API works"
    ((checks++))
else
    echo "[FAIL] Streaming API failed"
fi

echo ""
echo "Score: $checks / $total"
if [ "$checks" -eq "$total" ]; then
    echo "✅ Ready for Phase 2!"
else
    echo "⚠️ Review failed items before proceeding."
fi

I'm a helpful AI assistant running locally on your machine...

#!/bin/bash
# ============================================
# Comprehensive: Full Phase 1 E2E workflow
# Install → Configure → Pull → Test → Report
# ============================================

set -e
REPORT="phase1_report_$(date +%Y%m%d_%H%M%S).txt"

echo "Phase 1 E2E Workflow" | tee "$REPORT"
echo "====================" | tee -a "$REPORT"
echo "" | tee -a "$REPORT"

# Step 1: Install verification
echo "## Installation" | tee -a "$REPORT"
echo "Ollama: $(ollama --version 2>&1)" | tee -a "$REPORT"
echo "OS: $(uname -s) $(uname -m)" | tee -a "$REPORT"
echo "RAM: $(free -g | awk '/^Mem:/{print $2}')GB" | tee -a "$REPORT"
if command -v nvidia-smi &> /dev/null; then
    echo "GPU: $(nvidia-smi --query-gpu=name --format=csv,noheader)" | tee -a "$REPORT"
else
    echo "GPU: CPU-only mode" | tee -a "$REPORT"
fi
echo "" | tee -a "$REPORT"

# Step 2: Pull SupportBot model stack
echo "## Model Stack" | tee -a "$REPORT"
ollama pull qwen2.5 2>&1 | tail -1 | tee -a "$REPORT"
ollama pull llama3.2:3b 2>&1 | tail -1 | tee -a "$REPORT"
ollama pull nomic-embed-text 2>&1 | tail -1 | tee -a "$REPORT"
echo "" | tee -a "$REPORT"

# Step 3: Quality test with 3 questions
echo "## Quality Test" | tee -a "$REPORT"
questions=(
    "What is your return policy?"
    "How do I track my order?"
    "Do you ship internationally?"
)
for q in "${questions[@]}"; do
    echo "Q: $q" | tee -a "$REPORT"
    answer=$(curl -s http://localhost:11434/api/chat -d "{
        \"model\": \"qwen2.5\",
        \"messages\": [{\"role\": \"system\", \"content\": \"You are an e-commerce support agent. Be concise.\"},
                       {\"role\": \"user\", \"content\": \"$q\"}],
        \"stream\": false,
        \"options\": {\"temperature\": 0.3}
    }" | python3 -c "import sys,json; print(json.load(sys.stdin)['message']['content'][:120])")
    echo "A: $answer" | tee -a "$REPORT"
    echo "" | tee -a "$REPORT"
done

# Step 4: Performance benchmark
echo "## Benchmark" | tee -a "$REPORT"
start=$(date +%s%N)
curl -s http://localhost:11434/api/chat -d '{
    "model": "qwen2.5",
    "messages": [{"role": "user", "content": "Hello"}],
    "stream": false
}' > /dev/null
end=$(date +%s%N)
latency=$(( (end - start) / 1000000 ))
echo "Single request latency: ${latency}ms" | tee -a "$REPORT"
echo "Target < 5000ms: $([ $latency -lt 5000 ] && echo PASS || echo FAIL)" | tee -a "$REPORT"
echo "" | tee -a "$REPORT"

echo "Report saved: $REPORT"