bisheng-langchain 0.3.0rc0__py3-none-any.whl → 0.3.0rc1__py3-none-any.whl

bisheng_langchain/chat_models/host_llm.py

@@ -163,7 +163,7 @@ class BaseHostChatLLM(BaseChatModel):
                     values[
                         'host_base_url'] = f"{values['host_base_url']}/{values['model_name']}/infer"
         except Exception:
-            raise Exception(f'Update Decoupled status faild for model {model}')
+            raise Exception(f'Update Decoupled status failed for model {model}')
 
         try:
             if values['headers']:

bisheng_langchain/gpts/auto_optimization.py

@@ -3,7 +3,11 @@ import os
 import re
 
 import httpx
-from bisheng_langchain.gpts.prompts import ASSISTANT_PROMPT_OPT, BREIF_DES_PROMPT, OPENDIALOG_PROMPT
+from bisheng_langchain.gpts.prompts import (
+    ASSISTANT_PROMPT_OPT,
+    BREIF_DES_PROMPT,
+    OPENDIALOG_PROMPT,
+)
 from langchain_core.language_models.base import LanguageModelLike
 from langchain_openai.chat_models import ChatOpenAI
 from loguru import logger
@@ -48,16 +52,13 @@ def optimize_assistant_prompt(
     Returns:
         assistant_prompt(str):
     """
-    chain = ({
-        'assistant_name': lambda x: x['assistant_name'],
-        'assistant_description': lambda x: x['assistant_description'],
-    }
-             | ASSISTANT_PROMPT_OPT
-             | llm)
-    chain_output = chain.invoke({
-        'assistant_name': assistant_name,
-        'assistant_description': assistant_description,
-    })
+    chain = ASSISTANT_PROMPT_OPT | llm
+    chain_output = chain.invoke(
+        {
+            'assistant_name': assistant_name,
+            'assistant_description': assistant_description,
+        }
+    )
     response = chain_output.content
     assistant_prompt = parse_markdown(response)
     return assistant_prompt
@@ -67,17 +68,15 @@ def generate_opening_dialog(
     llm: LanguageModelLike,
     description: str,
 ) -> str:
-    chain = ({
-        'description': lambda x: x['description'],
-    }
-             | OPENDIALOG_PROMPT
-             | llm)
+    chain = OPENDIALOG_PROMPT | llm
     time = 0
     while time <= 3:
         try:
-            chain_output = chain.invoke({
-                'description': description,
-            })
+            chain_output = chain.invoke(
+                {
+                    'description': description,
+                }
+            )
             output = parse_json(chain_output.content)
             output = json.loads(output)
             opening_lines = output[0]['开场白']
@@ -101,20 +100,22 @@ def generate_breif_description(
     llm: LanguageModelLike,
     description: str,
 ) -> str:
-    chain = ({
-        'description': lambda x: x['description'],
-    }
-             | BREIF_DES_PROMPT
-             | llm)
-    chain_output = chain.invoke({
-        'description': description,
-    })
+    chain = BREIF_DES_PROMPT | llm
+    chain_output = chain.invoke(
+        {
+            'description': description,
+        }
+    )
     breif_description = chain_output.content
     breif_description = breif_description.strip()
     return breif_description
 
 
 if __name__ == '__main__':
+    from dotenv import load_dotenv
+
+    load_dotenv('/app/.env', override=True)
+
     httpx_client = httpx.Client(proxies=os.getenv('OPENAI_PROXY'))
     llm = ChatOpenAI(model='gpt-4-0125-preview', temperature=0.01, http_client=httpx_client)
     # llm = ChatQWen(model="qwen1.5-72b-chat", temperature=0.01, api_key=os.getenv('QWEN_API_KEY'))

bisheng_langchain/gpts/auto_tool_selected.py

@@ -1,6 +1,9 @@
 from bisheng_langchain.gpts.prompts.select_tools_prompt import HUMAN_MSG, SYS_MSG
-from langchain.prompts import (ChatPromptTemplate, HumanMessagePromptTemplate,
-                               SystemMessagePromptTemplate)
+from langchain.prompts import (
+    ChatPromptTemplate,
+    HumanMessagePromptTemplate,
+    SystemMessagePromptTemplate,
+)
 from langchain_core.language_models.base import LanguageModelLike
 from pydantic import BaseModel
 
@@ -31,19 +34,15 @@ class ToolSelector:
             HumanMessagePromptTemplate.from_template(self.human_message),
         ]
 
-        chain = ({
-            'tool_pool': lambda x: x['tool_pool'],
-            'task_name': lambda x: x['task_name'],
-            'task_description': lambda x: x['task_description'],
-        }
-                 | ChatPromptTemplate.from_messages(messages)
-                 | self.llm)
-
-        chain_output = chain.invoke({
-            'tool_pool': tool_pool,
-            'task_name': task_name,
-            'task_description': task_description,
-        })
+        chain = ChatPromptTemplate.from_messages(messages) | self.llm
+
+        chain_output = chain.invoke(
+            {
+                'tool_pool': tool_pool,
+                'task_name': task_name,
+                'task_description': task_description,
+            }
+        )
 
         try:
             all_tool_name = set([tool.tool_name for tool in self.tools])

bisheng_langchain/gpts/load_tools.py

@@ -1,7 +1,11 @@
+import json
+import os
 import warnings
 from typing import Any, Callable, Dict, List, Optional, Tuple
 
 import httpx
+import pandas as pd
+import pymysql
 from bisheng_langchain.gpts.tools.api_tools import ALL_API_TOOLS
 from bisheng_langchain.gpts.tools.bing_search.tool import BingSearchRun
 from bisheng_langchain.gpts.tools.calculator.tool import calculator
@@ -13,6 +17,7 @@ from bisheng_langchain.gpts.tools.dalle_image_generator.tool import (
     DallEImageGenerator,
 )
 from bisheng_langchain.gpts.tools.get_current_time.tool import get_current_time
+from dotenv import load_dotenv
 from langchain_community.tools.arxiv.tool import ArxivQueryRun
 from langchain_community.tools.bearly.tool import BearlyInterpreterTool
 from langchain_community.utilities.arxiv import ArxivAPIWrapper
@@ -54,12 +59,14 @@ def _get_bing_search(**kwargs: Any) -> BaseTool:
 
 def _get_dalle_image_generator(**kwargs: Any) -> Tool:
     openai_api_key = kwargs.get('openai_api_key')
+    openai_api_base = kwargs.get('openai_api_base')
     http_async_client = httpx.AsyncClient(proxies=kwargs.get('openai_proxy'))
     httpc_client = httpx.Client(proxies=kwargs.get('openai_proxy'))
     return DallEImageGenerator(
         api_wrapper=DallEAPIWrapper(
             model='dall-e-3',
             api_key=openai_api_key,
+            base_url=openai_api_base,
             http_client=httpc_client,
             http_async_client=http_async_client,
         )
@@ -78,7 +85,7 @@ def _get_native_code_interpreter(**kwargs: Any) -> Tool:
 _EXTRA_PARAM_TOOLS: Dict[str, Tuple[Callable[[KwArg(Any)], BaseTool], List[Optional[str]], List[Optional[str]]]] = {  # type: ignore
     'dalle_image_generator': (_get_dalle_image_generator, ['openai_api_key', 'openai_proxy'], []),
     'bing_search': (_get_bing_search, ['bing_subscription_key', 'bing_search_url'], []),
-    'code_interpreter': (_get_native_code_interpreter, ["minio"], ['files']),
+    'bisheng_code_interpreter': (_get_native_code_interpreter, ["minio"], ['files']),
 }
 
 _API_TOOLS: Dict[str, Tuple[Callable[[KwArg(Any)], BaseTool], List[str]]] = {**ALL_API_TOOLS}  # type: ignore
@@ -159,3 +166,46 @@ def load_tools(
 def get_all_tool_names() -> List[str]:
     """Get a list of all possible tool names."""
     return list(_ALL_TOOLS.keys())
+
+
+def get_tool_table():
+
+    load_dotenv('.sql_env', override=True)
+    db = pymysql.connect(
+        host=os.getenv('MYSQL_HOST'),
+        user=os.getenv('MYSQL_USER'),
+        password=os.getenv('MYSQL_PASSWORD'),
+        database=os.getenv('MYSQL_DATABASE'),
+        port=int(os.getenv('MYSQL_PORT')),
+    )
+    cursor = db.cursor()
+    cursor.execute("SELECT name, t.desc, tool_key, extra FROM t_gpts_tools as t;")
+    results = cursor.fetchall()
+    db.close()
+    
+    df = pd.DataFrame(
+        columns=[
+            '前端工具名',
+            '前端工具描述',
+            'tool_key',
+            'tool参数配置',
+            'function_name',
+            'function_description',
+            'function_args',
+        ]
+    )
+    for i, result in enumerate(results):
+        name, desc, tool_key, extra = result
+        if not extra:
+            extra = '{}'
+        tool_func = load_tools({tool_key: json.loads(extra)})[0]
+
+        df.loc[i, '前端工具名'] = name
+        df.loc[i, '前端工具描述'] = desc
+        df.loc[i, 'tool_key'] = tool_key
+        df.loc[i, 'tool参数配置'] = extra
+        df.loc[i, 'function_name'] = tool_func.name
+        df.loc[i, 'function_description'] = tool_func.description
+        df.loc[i, 'function_args'] = f"{tool_func.args_schema.schema()['properties']}"
+
+    return df

bisheng_langchain/gpts/prompts/opening_dialog_prompt.py

@@ -6,7 +6,7 @@ from langchain_core.prompts.chat import (
 )
 
 system_template = """
-你是一个生成开场白和预置问题的助手。接下来，你会收到一段关于任务助手的描述，你需要带入描述中的角色，以描述中的角色身份生成一段开场白，同时你还需要以描述中的角色身份生成几个预置问题。输出格式如下：
+你是一个生成开场白和预置问题的助手。接下来，你会收到一段关于任务助手的描述，你需要带入描述中的角色，以描述中的角色身份生成一段开场白，同时你还需要站在用户的角度生成几个用户可能的提问。输出格式如下：
 [
     {{
         "开场白": "开场白内容",

bisheng_langchain/gpts/tools/api_tools/__init__.py

@@ -40,7 +40,7 @@ _MACRO_TOOLS: Dict[str, Tuple[Callable[[KwArg(Any)], BaseTool], List[str]]] = {
 
 _tmp_flow = ['knowledge_retrieve']
 _TMP_TOOLS: Dict[str, Tuple[Callable[[KwArg(Any)], BaseTool], List[str]]] = {
-    f'flow_{name}': (FlowTools.get_api_tool, ['collection_id'])
+    f'flow_{name}': (FlowTools.get_api_tool, ['collection_id', 'description'])
     for name in _tmp_flow
 }
 ALL_API_TOOLS = {}

bisheng_langchain/gpts/tools/api_tools/base.py

@@ -64,7 +64,7 @@ class APIToolBase(BaseModel):
         resp = self.client.get(url)
         if resp.status_code != 200:
             logger.info('api_call_fail res={}', resp.text)
-        return resp.text
+        return resp.text[:10000]
 
     async def arun(self, query: str, **kwargs) -> str:
         """Run query through api and parse result."""
@@ -79,8 +79,8 @@ class APIToolBase(BaseModel):
             url = self.url
         logger.info('api_call url={}', url)
         resp = await self.async_client.aget(url)
-        logger.info(resp)
-        return resp
+        logger.info(resp[:10000])
+        return resp[:10000]
 
     @classmethod
     def get_api_tool(cls, name, **kwargs: Any) -> BaseTool:

bisheng_langchain/gpts/tools/api_tools/flow.py

@@ -1,8 +1,9 @@
 from loguru import logger
 from pydantic import BaseModel, Field
-
+from typing import Any
 from .base import APIToolBase
-
+from .base import MultArgsSchemaTool
+from langchain_core.tools import BaseTool
 
 class FlowTools(APIToolBase):
 
@@ -34,10 +35,8 @@ class FlowTools(APIToolBase):
         return resp
 
     @classmethod
-    def knowledge_retrieve(cls, collection_id: int = None) -> str:
-        """
-        知识库检索工具，从内部知识库进行检索总结
-        """
+    def knowledge_retrieve(cls, collection_id: int = None) -> str:    
+
         flow_id = 'c7985115-a9d2-446a-9c55-40b5728ffb52'
         url = 'http://192.168.106.120:3002/api/v1/process/{}'.format(flow_id)
         input_key = 'inputs'
@@ -55,5 +54,18 @@ class FlowTools(APIToolBase):
         class InputArgs(BaseModel):
             """args_schema"""
             query: str = Field(description='questions to ask')
-
+              
         return cls(url=url, params=params, input_key=input_key, args_schema=InputArgs)
+    
+    @classmethod
+    def get_api_tool(cls, name, **kwargs: Any) -> BaseTool:
+        attr_name = name.split('_', 1)[-1]
+        class_method = getattr(cls, attr_name)
+        function_description = kwargs.get('description','')
+        kwargs.pop('description')
+        return MultArgsSchemaTool(name=name + '_' +str(kwargs.get('collection_id')),
+                                  description=function_description,
+                                  func=class_method(**kwargs).run,
+                                  coroutine=class_method(**kwargs).arun,
+                                  args_schema=class_method(**kwargs).args_schema)
+    

bisheng_langchain/gpts/tools/api_tools/macro_data.py

@@ -81,7 +81,7 @@ class MacroData(BaseModel):
         JS_CHINA_GDP_YEARLY_URL = 'https://cdn.jin10.com/dc/reports/dc_chinese_gdp_yoy_all.js?v={}&_={}'
         t = time.time()
         r = requests.get(JS_CHINA_GDP_YEARLY_URL.format(str(int(round(t * 1000))), str(int(round(t * 1000)) + 90)))
-        json_data = json.loads(r.text[r.text.find('{') : r.text.rfind('}') + 1])
+        json_data = json.loads(r.text[r.text.find('{'): r.text.rfind('}') + 1])
         date_list = [item['date'] for item in json_data['list']]
         value_list = [item['datas']['中国GDP年率报告'] for item in json_data['list']]
         value_df = pd.DataFrame(value_list)
@@ -249,6 +249,60 @@ class MacroData(BaseModel):
             temp_df = temp_df[(temp_df['月份'] >= start) & (temp_df['月份'] <= end)]
         return temp_df.to_markdown()
 
+    @classmethod
+    def china_pmi(cls, start_date: str = '', end_date: str = '') -> str:
+        """中国 PMI （采购经理人指数）月度统计数据。
+        返回数据包括：月份制造业 PMI，制造业 PMI 同比增长，非制造业 PMI，非制造业 PMI 同比增长。
+        """
+        url = "https://datacenter-web.eastmoney.com/api/data/v1/get"
+        params = {
+            "columns": "REPORT_DATE,TIME,MAKE_INDEX,MAKE_SAME,NMAKE_INDEX,NMAKE_SAME",
+            "pageNumber": "1",
+            "pageSize": "2000",
+            "sortColumns": "REPORT_DATE",
+            "sortTypes": "-1",
+            "source": "WEB",
+            "client": "WEB",
+            "reportName": "RPT_ECONOMY_PMI",
+            "p": "1",
+            "pageNo": "1",
+            "pageNum": "1",
+            "_": "1669047266881",
+        }
+        r = requests.get(url, params=params)
+        data_json = r.json()
+        temp_df = pd.DataFrame(data_json["result"]["data"])
+        temp_df.columns = [
+            "-",
+            "月份",
+            "制造业-指数",
+            "制造业-同比增长",
+            "非制造业-指数",
+            "非制造业-同比增长",
+        ]
+        temp_df = temp_df[
+            [
+                "月份",
+                "制造业-指数",
+                "制造业-同比增长",
+                "非制造业-指数",
+                "非制造业-同比增长",
+            ]
+        ]
+        temp_df["制造业-指数"] = pd.to_numeric(temp_df["制造业-指数"], errors="coerce")
+        temp_df["制造业-同比增长"] = pd.to_numeric(
+            temp_df["制造业-同比增长"], errors="coerce"
+        )
+        temp_df["非制造业-指数"] = pd.to_numeric(temp_df["非制造业-指数"], errors="coerce")
+        temp_df["非制造业-同比增长"] = pd.to_numeric(
+            temp_df["非制造业-同比增长"], errors="coerce"
+        )
+        if start_date and end_date:
+            start = start_date.split('-')[0] + '年' + start_date.split('-')[1] + '月份'
+            end = end_date.split('-')[0] + '年' + end_date.split('-')[1] + '月份'
+            temp_df = temp_df[(temp_df['月份'] >= start) & (temp_df['月份'] <= end)]
+        return temp_df.to_markdown()
+
     @classmethod
     def china_money_supply(cls, start_date: str = '', end_date: str = '') -> pd.DataFrame:
         """中国货币供应量（M2，M1，M0）月度统计数据。\
@@ -376,6 +430,121 @@ M0数量（单位：亿元），M0 同比（单位：%），M0 环比（单位
 
         return temp_df.to_markdown()
 
+    @classmethod
+    def bond_zh_us_rate(cls, start_date: str = "", end_date: str = "") -> str:
+        """
+        本接口返回指定时间段[start_date,end_date]内交易日的中美两国的 2 年、5 年、10 年、30 年、10 年-2 年收益率数据。
+        start_date表示起始日期，end_date表示结束日期，日期格式例如 2024-04-07
+        """
+        url = "https://datacenter.eastmoney.com/api/data/get"
+        params = {
+            "type": "RPTA_WEB_TREASURYYIELD",
+            "sty": "ALL",
+            "st": "SOLAR_DATE",
+            "sr": "-1",
+            "token": "894050c76af8597a853f5b408b759f5d",
+            "p": "1",
+            "ps": "500",
+            "pageNo": "1",
+            "pageNum": "1",
+            "_": "1615791534490",
+        }
+        r = requests.get(url, params=params)
+        data_json = r.json()
+        total_page = data_json["result"]["pages"]
+        big_df = pd.DataFrame()
+        for page in range(1, total_page + 1):
+            params = {
+                "type": "RPTA_WEB_TREASURYYIELD",
+                "sty": "ALL",
+                "st": "SOLAR_DATE",
+                "sr": "-1",
+                "token": "894050c76af8597a853f5b408b759f5d",
+                "p": page,
+                "ps": "500",
+                "pageNo": page,
+                "pageNum": page,
+                "_": "1615791534490",
+            }
+            r = requests.get(url, params=params)
+            data_json = r.json()
+            # 时间过滤
+            if start_date and end_date:
+                temp_data = []
+                for item in data_json["result"]["data"]:
+                    if start_date <= item["SOLAR_DATE"].split(" ")[0] <= end_date:
+                        temp_data.append(item)
+                    elif start_date > item["SOLAR_DATE"].split(" ")[0]:
+                        break
+                    else:
+                        continue
+            else:
+                temp_data = data_json["result"]["data"]
+            temp_df = pd.DataFrame(temp_data)
+            for col in temp_df.columns:
+                if temp_df[col].isnull().all():  # 检查列是否包含 None 或 NaN
+                    temp_df[col] = pd.to_numeric(temp_df[col], errors='coerce')
+            if big_df.empty:
+                big_df = temp_df
+            else:
+                big_df = pd.concat(objs=[big_df, temp_df], ignore_index=True)
+
+        big_df.rename(
+            columns={
+                "SOLAR_DATE": "日期",
+                "EMM00166462": "中国国债收益率5年",
+                "EMM00166466": "中国国债收益率10年",
+                "EMM00166469": "中国国债收益率30年",
+                "EMM00588704": "中国国债收益率2年",
+                "EMM01276014": "中国国债收益率10年-2年",
+                "EMG00001306": "美国国债收益率2年",
+                "EMG00001308": "美国国债收益率5年",
+                "EMG00001310": "美国国债收益率10年",
+                "EMG00001312": "美国国债收益率30年",
+                "EMG01339436": "美国国债收益率10年-2年",
+                "EMM00000024": "中国GDP年增率",
+                "EMG00159635": "美国GDP年增率",
+            },
+            inplace=True,
+        )
+        big_df = big_df[
+            [
+                "日期",
+                "中国国债收益率2年",
+                "中国国债收益率5年",
+                "中国国债收益率10年",
+                "中国国债收益率30年",
+                "中国国债收益率10年-2年",
+                "中国GDP年增率",
+                "美国国债收益率2年",
+                "美国国债收益率5年",
+                "美国国债收益率10年",
+                "美国国债收益率30年",
+                "美国国债收益率10年-2年",
+                "美国GDP年增率",
+            ]
+        ]
+        big_df = big_df.drop(["中国GDP年增率", "美国GDP年增率"], axis=1)
+        big_df["日期"] = pd.to_datetime(big_df["日期"], errors="coerce")
+        big_df["中国国债收益率2年"] = pd.to_numeric(big_df["中国国债收益率2年"], errors="coerce")
+        big_df["中国国债收益率5年"] = pd.to_numeric(big_df["中国国债收益率5年"], errors="coerce")
+        big_df["中国国债收益率10年"] = pd.to_numeric(big_df["中国国债收益率10年"], errors="coerce")
+        big_df["中国国债收益率30年"] = pd.to_numeric(big_df["中国国债收益率30年"], errors="coerce")
+        big_df["中国国债收益率10年-2年"] = pd.to_numeric(big_df["中国国债收益率10年-2年"], errors="coerce")
+        # big_df["中国GDP年增率"] = pd.to_numeric(big_df["中国GDP年增率"], errors="coerce")
+        big_df["美国国债收益率2年"] = pd.to_numeric(big_df["美国国债收益率2年"], errors="coerce")
+        big_df["美国国债收益率5年"] = pd.to_numeric(big_df["美国国债收益率5年"], errors="coerce")
+        big_df["美国国债收益率10年"] = pd.to_numeric(big_df["美国国债收益率10年"], errors="coerce")
+        big_df["美国国债收益率30年"] = pd.to_numeric(big_df["美国国债收益率30年"], errors="coerce")
+        big_df["美国国债收益率10年-2年"] = pd.to_numeric(big_df["美国国债收益率10年-2年"], errors="coerce")
+        # big_df["美国GDP年增率"] = pd.to_numeric(big_df["美国GDP年增率"], errors="coerce")
+        big_df.sort_values("日期", inplace=True)
+        big_df.set_index(["日期"], inplace=True)
+        big_df = big_df[pd.to_datetime(start_date):]
+        big_df.reset_index(inplace=True)
+        big_df["日期"] = pd.to_datetime(big_df["日期"]).dt.date
+        return big_df.to_markdown()
+
     @classmethod
     def get_api_tool(cls, name: str, **kwargs: Any) -> BaseTool:
         attr_name = name.split('_', 1)[-1]
@@ -385,13 +554,15 @@ M0数量（单位：亿元），M0 同比（单位：%），M0 环比（单位
 
 
 if __name__ == '__main__':
-    start_date = '2023-01-01'
-    end_date = '2023-05-01'
+    tmp_start_date = '2024-01-01'
+    tmp_end_date = '2024-01-03'
     # start_date = ''
     # end_date = ''
     # print(MacroData.china_ppi(start_date=start_date, end_date=end_date))
     # print(MacroData.china_shrzgm(start_date=start_date, end_date=end_date))
     # print(MacroData.china_consumer_goods_retail(start_date=start_date, end_date=end_date))
     # print(MacroData.china_cpi(start_date=start_date, end_date=end_date))
+    # print(MacroData.china_pmi(start_date=start_date, end_date=end_date))
     # print(MacroData.china_money_supply(start_date=start_date, end_date=end_date))
-    print(MacroData.china_gdp_yearly(start_date=start_date, end_date=end_date))
+    # print(MacroData.china_gdp_yearly(start_date=start_date, end_date=end_date))
+    print(MacroData.bond_zh_us_rate(start_date=tmp_start_date, end_date=tmp_end_date))

bisheng_langchain/gpts/tools/api_tools/sina.py

@@ -154,7 +154,7 @@ class StockInfo(APIToolBase):
         resp = super().run(query=stock_number)
         stock = self.devideStock(resp)[0]
         if isinstance(stock, Stock):
-            return json.dumps(stock.__dict__)
+            return json.dumps(stock.__dict__, ensure_ascii=False)
         else:
             return stock
 
@@ -183,7 +183,7 @@ class StockInfo(APIToolBase):
             resp = await super().arun(query=stock_number)
             stock = self.devideStock(resp)[0]
             if isinstance(stock, Stock):
-                return json.dumps(stock.__dict__)
+                return json.dumps(stock.__dict__, ensure_ascii=False)
             else:
                 return stock
 

bisheng_langchain/gpts/tools/code_interpreter/tool.py

@@ -1,6 +1,8 @@
+import glob
 import itertools
 import os
 import pathlib
+import re
 import subprocess
 import sys
 import tempfile
@@ -11,24 +13,18 @@ from pathlib import Path
 from typing import Dict, List, Optional, Tuple, Type
 from uuid import uuid4
 
-from autogen.code_utils import extract_code, infer_lang
+import matplotlib
 from langchain_community.tools import Tool
 from langchain_core.pydantic_v1 import BaseModel, Field
 from loguru import logger
 
-try:
-    from termcolor import colored
-except ImportError:
-
-    def colored(x, *args, **kwargs):
-        return x
-
-
+CODE_BLOCK_PATTERN = r"```(\w*)\n(.*?)\n```"
 DEFAULT_TIMEOUT = 600
 WIN32 = sys.platform == 'win32'
 PATH_SEPARATOR = WIN32 and '\\' or '/'
 WORKING_DIR = os.path.join(os.path.dirname(os.path.realpath(__file__)), 'extensions')
 TIMEOUT_MSG = 'Timeout'
+UNKNOWN = "unknown"
 
 
 def _cmd(lang):
@@ -41,6 +37,61 @@ def _cmd(lang):
     raise NotImplementedError(f'{lang} not recognized in code execution')
 
 
+def infer_lang(code):
+    """infer the language for the code.
+    TODO: make it robust.
+    """
+    if code.startswith("python ") or code.startswith("pip") or code.startswith("python3 "):
+        return "sh"
+
+    # check if code is a valid python code
+    try:
+        compile(code, "test", "exec")
+        return "python"
+    except SyntaxError:
+        # not a valid python code
+        return UNKNOWN
+
+
+def extract_code(
+    text: str, pattern: str = CODE_BLOCK_PATTERN, detect_single_line_code: bool = False
+) -> List[Tuple[str, str]]:
+    """Extract code from a text.
+
+    Args:
+        text (str): The text to extract code from.
+        pattern (str, optional): The regular expression pattern for finding the
+            code block. Defaults to CODE_BLOCK_PATTERN.
+        detect_single_line_code (bool, optional): Enable the new feature for
+            extracting single line code. Defaults to False.
+
+    Returns:
+        list: A list of tuples, each containing the language and the code.
+          If there is no code block in the input text, the language would be "unknown".
+          If there is code block but the language is not specified, the language would be "".
+    """
+    if not detect_single_line_code:
+        match = re.findall(pattern, text, flags=re.DOTALL)
+        return match if match else [(UNKNOWN, text)]
+
+    # Extract both multi-line and single-line code block, separated by the | operator
+    # `{3}(\w+)?\s*([\s\S]*?)`{3}: Matches multi-line code blocks.
+    #    The (\w+)? matches the language, where the ? indicates it is optional.
+    # `([^`]+)`: Matches inline code.
+    code_pattern = re.compile(r"`{3}(\w+)?\s*([\s\S]*?)`{3}|`([^`]+)`")
+    code_blocks = code_pattern.findall(text)
+
+    # Extract the individual code blocks and languages from the matched groups
+    extracted = []
+    for lang, group1, group2 in code_blocks:
+        if group1:
+            extracted.append((lang.strip(), group1.strip()))
+        elif group2:
+            extracted.append(("", group2.strip()))
+
+    return extracted
+
+
 def execute_code(
     code: Optional[str] = None,
     timeout: Optional[int] = None,
@@ -121,16 +172,66 @@ def head_file(path: str, n: int) -> List[str]:
         return []
 
 
-def upload_minio(param: dict, bucket: str, object_name: str, file_path, content_type='application/text'):
+def upload_minio(
+    param: dict,
+    bucket: str,
+    object_name: str,
+    file_path,
+    content_type='application/text',
+):
     # 初始化minio
     import minio
 
-    minio_client = minio.Minio(**param)
-    logger.debug('upload_file obj={} bucket={} file_paht={}', object_name, bucket, file_path)
+    minio_client = minio.Minio(
+        endpoint=param.get('MINIO_ENDPOINT'),
+        access_key=param.get('MINIO_ACCESS_KEY'),
+        secret_key=param.get('MINIO_SECRET_KEY'),
+        secure=param.get('SCHEMA'),
+        cert_check=param.get('CERT_CHECK'),
+    )
+    minio_share = minio.Minio(
+        endpoint=param.get('MINIO_SHAREPOIN'),
+        access_key=param.get('MINIO_ACCESS_KEY'),
+        secret_key=param.get('MINIO_SECRET_KEY'),
+        secure=param.get('SCHEMA'),
+        cert_check=param.get('CERT_CHECK'),
+    )
+    logger.debug(
+        'upload_file obj={} bucket={} file_paht={}',
+        object_name,
+        bucket,
+        file_path,
+    )
     minio_client.fput_object(
-        bucket_name=bucket, object_name=object_name, file_path=file_path, content_type=content_type
+        bucket_name=bucket,
+        object_name=object_name,
+        file_path=file_path,
+        content_type=content_type,
+    )
+    return minio_share.presigned_get_object(
+        bucket_name=bucket,
+        object_name=object_name,
+        expires=timedelta(days=7),
     )
-    return minio_client.presigned_get_object(bucket_name=bucket, object_name=object_name, expires=timedelta(days=7))
+
+
+def insert_set_font_code(code: str) -> str:
+    """判断python代码中是否导入了matplotlib库，如果有则插入设置字体的代码"""
+
+    split_code = code.split('\n')
+    cache_file = matplotlib.get_cachedir()
+    font_cache = glob.glob(f'{cache_file}/fontlist*')
+
+    for cache in font_cache:
+        os.remove(cache)
+
+    # todo: 如果生成的代码中已经有了设置字体的代码，可能会导致该段代码失效
+    if 'matplotlib' in code:
+        pattern = re.compile(r'(import matplotlib|from matplotlib)')
+        index = max(i for i, line in enumerate(split_code) if pattern.search(line))
+        split_code.insert(index + 1, 'import matplotlib\nmatplotlib.rc("font", family="WenQuanYi Zen Hei")')
+
+    return '\n'.join(split_code)
 
 
 class CodeInterpreterToolArguments(BaseModel):
@@ -169,7 +270,7 @@ class FileInfo(BaseModel):
 class CodeInterpreterTool:
     """Tool for evaluating python code in native environment."""
 
-    name = 'code_interpreter'
+    name = 'bisheng_code_interpreter'
     args_schema: Type[BaseModel] = CodeInterpreterToolArguments
 
     def __init__(
@@ -204,6 +305,7 @@ class CodeInterpreterTool:
         for i, code_block in enumerate(code_blocks):
             lang, code = code_block
             lang = infer_lang(code)
+            code = insert_set_font_code(code)
             temp_dir = tempfile.TemporaryDirectory()
             exitcode, logs, _ = execute_code(
                 code,
@@ -215,7 +317,7 @@ class CodeInterpreterTool:
                 return {'exitcode': exitcode, 'log': logs_all}
 
             # 获取文件
-            temp_output_dir = Path(temp_dir.name) / 'output'
+            temp_output_dir = Path(temp_dir.name)
             for root, dirs, files in os.walk(temp_output_dir):
                 for name in files:
                     file_name = os.path.join(root, name)
@@ -236,26 +338,3 @@ class CodeInterpreterTool:
             description=self.description,
             args_schema=self.args_schema,
         )
-
-
-if __name__ == '__main__':
-    code_string = """print('hha')"""
-    code_blocks = extract_code(code_string)
-    logger.info(code_blocks)
-    logs_all = ''
-    for i, code_block in enumerate(code_blocks):
-        lang, code = code_block
-        lang = infer_lang(code)
-        print(
-            colored(
-                f'\n>>>>>>>> EXECUTING CODE BLOCK {i} (inferred language is {lang})...',
-                'red',
-            ),
-            flush=True,
-        )
-        exitcode, logs, image = execute_code(code, lang=lang)
-        logs_all += '\n' + logs
-        if exitcode != 0:
-            logger.error(f'{exitcode}, {logs_all}')
-
-    logger.info(logs_all)

{bisheng_langchain-0.3.0rc0.dist-info → bisheng_langchain-0.3.0rc1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: bisheng-langchain
-Version: 0.3.0rc0
+Version: 0.3.0rc1
 Summary: bisheng langchain modules
 Home-page: https://github.com/dataelement/bisheng
 Author: DataElem

{bisheng_langchain-0.3.0rc0.dist-info → bisheng_langchain-0.3.0rc1.dist-info}/RECORD

@@ -28,7 +28,7 @@ bisheng_langchain/chains/router/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm
 bisheng_langchain/chains/router/multi_rule.py,sha256=BiFryj3-7rOxfttD-MyOkKWLCSGB9LVYd2rjOsIfQC8,375
 bisheng_langchain/chains/router/rule_router.py,sha256=R2YRUnwn7s_7DbsSn27uPn4cIV0D-5iXEORXir0tNGM,1835
 bisheng_langchain/chat_models/__init__.py,sha256=4-HTLE_SXO4hmNJu6yQxiQKBt2IFca_ezllVBLmvbEE,635
-bisheng_langchain/chat_models/host_llm.py,sha256=sBu_Vg-r7z6IJUV8Etwll4JTG5OvET-IXH7PZw8Ijrc,23152
+bisheng_langchain/chat_models/host_llm.py,sha256=35_jTdUm85mk-t2MARZYGC8dIPVtf5XXlGfFE6hQ1Gc,23153
 bisheng_langchain/chat_models/minimax.py,sha256=JLs_f6vWD9beZYUtjD4FG28G8tZHrGUAWOwdLIuJomw,13901
 bisheng_langchain/chat_models/proxy_llm.py,sha256=wzVBZik9WC3-f7kyQ1eu3Ooibqpcocln08knf5lV1Nw,17082
 bisheng_langchain/chat_models/qwen.py,sha256=W73KxDRQBUZEzttEM4K7ZzPqbN-82O6YQmpX-HB_wZU,19971
@@ -66,9 +66,9 @@ bisheng_langchain/embeddings/interface/types.py,sha256=VdurbtsnjCPdlOjPFcK2Mg6r9
 bisheng_langchain/embeddings/interface/wenxin.py,sha256=5d9gI4enmfkD80s0FHKiDt33O0mwM8Xc5WTubnMUy8c,3104
 bisheng_langchain/gpts/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 bisheng_langchain/gpts/assistant.py,sha256=KCYPU1Bs4GtWcLk9Ya2NuQyXE0Twn7-92eSBTIzpq7I,5083
-bisheng_langchain/gpts/auto_optimization.py,sha256=Vf3zzYEpVf916dYt4RV9E1uw4vTXjE7ZXogUIdxjHYU,3786
-bisheng_langchain/gpts/auto_tool_selected.py,sha256=25lFLadqQ36t63EKMEF3zJOG_jkoRB9IfP5eRkY1JZo,1777
-bisheng_langchain/gpts/load_tools.py,sha256=C7tlRLy4wAArr9qtkRl9dW6QXdspLLbcv0UvulW9A9U,6345
+bisheng_langchain/gpts/auto_optimization.py,sha256=WNsC19rgvuDYQlSIaYThq5RqCbuobDbzCwAJW4Ksw0c,3626
+bisheng_langchain/gpts/auto_tool_selected.py,sha256=21WETf9o0YS-QEBwv3mmZRObKWszefQkXEqAA6KzoaM,1582
+bisheng_langchain/gpts/load_tools.py,sha256=JZpwTH5cvaLdab8-TbTxBGHug-llnCQR0wB4VsduSrs,7871
 bisheng_langchain/gpts/message_types.py,sha256=7EJOx62j9E1U67jxWgxE_I7a8IjAvvKANknXkD2gFm0,213
 bisheng_langchain/gpts/utils.py,sha256=t3YDxaJ0OYd6EKsek7PJFRYnsezwzEFK5oVU-PRbu5g,6671
 bisheng_langchain/gpts/agent_types/__init__.py,sha256=bg0zlTYGfNXoSBqcICHlzNpVQbejMYeyji_dzvP5qQ0,261
@@ -77,21 +77,21 @@ bisheng_langchain/gpts/prompts/__init__.py,sha256=IfuoxVpsSLKJtDx0aJbRgnSZYZr_kD
 bisheng_langchain/gpts/prompts/assistant_prompt_opt.py,sha256=TZsRK4XPMrUhGg0PoMyiE3wE-aG34UmlVflkCl_c0QI,4151
 bisheng_langchain/gpts/prompts/base_prompt.py,sha256=v2eO0c6RF8e6MtGdleHs5B4YTkikg6IZUuBvL2zvyOI,55
 bisheng_langchain/gpts/prompts/breif_description_prompt.py,sha256=w4A5et0jB-GkxEMQBp4i6GKX3RkVeu7NzWEjOZZAicM,5336
-bisheng_langchain/gpts/prompts/opening_dialog_prompt.py,sha256=U6SDslWuXAB1ZamLZVujpEjAY8L244IZfD2qFVRTzPM,5962
+bisheng_langchain/gpts/prompts/opening_dialog_prompt.py,sha256=VVF0JLHtetupVB0kabiFHWDHlQaa4nFLcbYXgIBA3nw,5965
 bisheng_langchain/gpts/prompts/select_tools_prompt.py,sha256=AyvVnrLEsQy7RHuGTPkcrMUxgA98Q0TzF-xweoc7GyY,1400
 bisheng_langchain/gpts/tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-bisheng_langchain/gpts/tools/api_tools/__init__.py,sha256=mrmTV5bT5R1mEx9hbMAWKzNAAC4EL6biNn53dx5lYsc,1593
-bisheng_langchain/gpts/tools/api_tools/base.py,sha256=t0gFRiXD-2InCHNDU_T1H0eSMXsWP_2sHBeLJ0bZOkc,3594
-bisheng_langchain/gpts/tools/api_tools/flow.py,sha256=u1_ASWlCcZarKR-293kACB_qQ1RzJuzPC3YZSl2JR-E,1814
-bisheng_langchain/gpts/tools/api_tools/macro_data.py,sha256=rlFNhjJ3HEHfWeW9Wqb27eeF1Q1Qmd2SA8VfgUK4ACs,19270
-bisheng_langchain/gpts/tools/api_tools/sina.py,sha256=tY4MXHNBEUiBN1wld2un_w7nHW_njXV7haLo3sgpDf0,9502
+bisheng_langchain/gpts/tools/api_tools/__init__.py,sha256=CkEjgIFM4GIv86V1B7SsFLaB6M86c54QuO8wIRizUZ8,1608
+bisheng_langchain/gpts/tools/api_tools/base.py,sha256=fWQSDIOVb4JZrtJ9ML9q2ycsAa-_61gXTD0MT19J1LM,3618
+bisheng_langchain/gpts/tools/api_tools/flow.py,sha256=rHCRpaafriQomMaOqSeKjPXwVUO_nAsFDNRIjOofbuI,2486
+bisheng_langchain/gpts/tools/api_tools/macro_data.py,sha256=FyG-qtl2ECS1CDKt6olN0eDTDM91d-UvDkMDBiVLgYQ,27429
+bisheng_langchain/gpts/tools/api_tools/sina.py,sha256=GGA4ZYvNEpqBZ_l8MUYqgkI8xZe9XcGa9-KlHZVqr6I,9542
 bisheng_langchain/gpts/tools/api_tools/tianyancha.py,sha256=abDAz-yAH1-2rKiSmZ6TgnrNUnpgAZpDY8oDiWfWapc,6684
 bisheng_langchain/gpts/tools/bing_search/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 bisheng_langchain/gpts/tools/bing_search/tool.py,sha256=v_VlqcMplITA5go5qWA4qZ5p43E1-1s0bzmyY7H0hqY,1710
 bisheng_langchain/gpts/tools/calculator/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 bisheng_langchain/gpts/tools/calculator/tool.py,sha256=iwGPE7jvxZg_jUL2Aq9HHwnRJrF9-ongwrsBX6uk1U0,705
 bisheng_langchain/gpts/tools/code_interpreter/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-bisheng_langchain/gpts/tools/code_interpreter/tool.py,sha256=PGipxd-qtW31GonRGfGow7nylI-osSnmBsvEJDlMUCE,8717
+bisheng_langchain/gpts/tools/code_interpreter/tool.py,sha256=1VLkgngRR0k8YjA4eYkfPd1E7fD29tMKpqtCtn7WwYE,11443
 bisheng_langchain/gpts/tools/dalle_image_generator/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 bisheng_langchain/gpts/tools/dalle_image_generator/tool.py,sha256=mhxdNNhBESjbOy30Rnp6hQhnrV4evQpv-B1fFXcU-68,7528
 bisheng_langchain/gpts/tools/get_current_time/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -108,7 +108,7 @@ bisheng_langchain/vectorstores/__init__.py,sha256=zCZgDe7LyQ0iDkfcm5UJ5NxwKQSRHn
 bisheng_langchain/vectorstores/elastic_keywords_search.py,sha256=JV_GM40cYx0PtPPvH2JYxtsMV0psSW2CDKagpR4M_0o,13286
 bisheng_langchain/vectorstores/milvus.py,sha256=lrnezKnYXhyH5M1g3a-Mcwpj9mwzAj44TKmzyUXlQYY,36297
 bisheng_langchain/vectorstores/retriever.py,sha256=hj4nAAl352EV_ANnU2OHJn7omCH3nBK82ydo14KqMH4,4353
-bisheng_langchain-0.3.0rc0.dist-info/METADATA,sha256=-wUMNJfiSIK6i3D9pP74PdmDKuLtDcrW3BcNpNzqv1A,2414
-bisheng_langchain-0.3.0rc0.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-bisheng_langchain-0.3.0rc0.dist-info/top_level.txt,sha256=Z6pPNyCo4ihyr9iqGQbH8sJiC4dAUwA_mAyGRQB5_Fs,18
-bisheng_langchain-0.3.0rc0.dist-info/RECORD,,
+bisheng_langchain-0.3.0rc1.dist-info/METADATA,sha256=vHWUJcrt2hO4QpW5o0Al8bn23d6c3zpm9yf_2NWGEmE,2414
+bisheng_langchain-0.3.0rc1.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+bisheng_langchain-0.3.0rc1.dist-info/top_level.txt,sha256=Z6pPNyCo4ihyr9iqGQbH8sJiC4dAUwA_mAyGRQB5_Fs,18
+bisheng_langchain-0.3.0rc1.dist-info/RECORD,,