feat(core): Support multi round conversation operator

[fangyinc]

• New Data Analyst assistant example with AWEL
• New conversation serve package

[fangyinc]

How to run Data Analyst assistant example

Run awel file with dev_mode

export OPENAI_API_KEY=xxx
export OPENAI_API_BASE=https://api.openai.com/v1
python examples/awel/simple_chat_history_example.py

Test with curl

Open a new terminal

DBGPT_SERVER="http://127.0.0.1:5555"
MODEL="gpt-3.5-turbo"

curl -X POST $DBGPT_SERVER/api/v1/awel/trigger/examples/data_analyst/copilot \
-H "Content-Type: application/json" -d '{
    "command": "dbgpt_awel_data_analyst_code_fix",
    "model": "gpt-3.5-turbo",
    "stream": false,
    "context": {
        "conv_uid": "uuid_conv_copilot_1234",
        "chat_mode": "chat_with_code"
    },
    "messages": "SELECT * FRM orders WHERE order_amount > 500;"
}'

The result like:

{
    "text": "修复后的代码如下：\n\nSELECT * FROM orders WHERE order_amount > 500;\n\n逐行解释：\n1. \"SELECT *\" 表示选择所有的列，即返回整个表的所有列的数据。\n2. \"FROM orders\" 表示从名为 \"orders\" 的表中检索数据。\n3. \"WHERE order_amount > 500\" 是一个过滤条件，表示只选择订单金额大于500的订单。\n4. 修复后的代码中，修正了一个拼写错误，将 \"FRM\" 改为了 \"FROM\"。这样才能正确地从表中检索数据。",
    "error_code": 0,
    "model_context": {
        "prompt_echo_len_char": -1,
        "has_format_prompt": false
    },
    "finish_reason": null,
    "usage": null,
    "metrics": {
        "collect_index": 139,
        "start_time_ms": 1703684771627,
        "end_time_ms": 1703684780862,
        "current_time_ms": 1703684780862,
        "first_token_time_ms": null,
        "first_completion_time_ms": 1703684775563,
        "first_completion_tokens": null,
        "prompt_tokens": null,
        "completion_tokens": null,
        "total_tokens": null,
        "speed_per_second": null,
        "current_gpu_infos": null,
        "avg_gpu_infos": null
    }
}

[csunny]

LGTM

[Aralhi]

r+