diff --git a/backend/.coding/functions.py b/backend/.coding/functions.py index 401cd47..cf83d19 100644 --- a/backend/.coding/functions.py +++ b/backend/.coding/functions.py @@ -1,116 +1,61 @@ -import pandas -import glob -import os +import requests -def get_max_uv_wavelength_from_txt(latest_file_path: str): - import pandas as pd - import os - # 文件检查 - if not os.path.isfile(latest_file_path): - res = "ERROR: 指定的文件不存在" - return res +def retrieval_from_knowledge_base( + query: str, + topk: int + ) -> str: + """ + Retrieval for knowledge from the knowledge base based on the specified query and returns the topk results. + + Parameters: + query (str): The query for knowledge retrieval. + topk (int): The number of top results to return, default is 3. + + Returns: + str: The result of the knowledge retrieval in JSON format. + """ + url = 'http://127.0.0.1:7080/v1/chat-messages' + headers = { + 'Authorization': f'Bearer app-uJgo3TQKcS1O9PMCDHko71Fp', + 'Content-Type': 'application/json' + } + data = { + "inputs": {"topK": topk}, + "query": query, + "response_mode": "blocking", + "user": "tangger", + "files": [] + } - # 打开并读取最新文件 - with open(latest_file_path, 'r') as file: - lines = file.readlines() + response = requests.post(url, headers=headers, json=data) - # 找到数据开始的行号 - data_start_index = -1 - for i, line in enumerate(lines): - if "Wavelength Scan Data Record" in line: - data_start_index = i + 2 # 数据从该行的下两行开始 - break + if response.status_code == 524: + print("Server is not responding. Please try again later. Maybe GPU was down in the container.") + return None - if data_start_index == -1: - res = "ERROR: 无法找到数据记录部分" - return res + try: + result = response.json() + except ValueError: + return [{"error": "Response is not in JSON format"}] - # 解析数据并构建表格 - data = [] - for line in lines[data_start_index:]: - parts = line.split() - if len(parts) == 7: # 保证每行有7列数据 - no, wavelength, abs_value, trans, energy, energy_100, energy_0 = parts - try: - data.append({ - 'No': int(no), - 'Wavelength(nm)': float(wavelength), - 'Abs': float(abs_value), - 'Trans(%T)': float(trans), - 'Energy': float(energy), - 'Energy(100%T)': float(energy_100), - 'Energy(0%T)': float(energy_0) - }) - except ValueError: - print(f"跳过无法解析的行: {line}") - - if not data: - res = "ERROR: 未解析到任何有效数据" - return res - - # 构建DataFrame - df = pd.DataFrame(data) - - # 找到Abs值最大的行 - max_abs_row = df.loc[df['Abs'].idxmax()] - - # 获取最大Abs值对应的波长 - max_abs_wavelength = max_abs_row['Wavelength(nm)'] - res = f"本次实验的UV波长为: {max_abs_wavelength} nm" - print(res) - return res - - -def get_max_pl_peak_from_txt(latest_file_path: str): - import pandas as pd - import os - # 文件检查 - if not os.path.isfile(latest_file_path): - res = "ERROR: 指定的文件不存在" - return res - - # 打开并读取最新文件 - with open(latest_file_path, 'r') as file: - lines = file.readlines() - - # 找到 'Data Points' 开始的行号 - data_start_index = -1 - for i, line in enumerate(lines): - if "Data Points" in line: - data_start_index = i + 1 # 数据从该行的下一行开始 - break - - if data_start_index == -1: - res = "ERROR: 无法找到数据记录部分" - return res - - # 解析nm和Data数据 - data = [] - for line in lines[data_start_index:]: - parts = line.split() - if len(parts) == 2: # 每行应该有2列数据，nm 和 Data - try: - nm = float(parts[0]) - data_value = float(parts[1]) - data.append({'nm': nm, 'Data': data_value}) - except ValueError: - print(f"跳过无法解析的行: {line}") - - if not data: - res = "ERROR: 未解析到任何有效数据" - return res - - # 构建DataFrame - df = pd.DataFrame(data) - - # 找到Data值最大的行 - max_data_row = df.loc[df['Data'].idxmax()] - - # 获取最大Data值对应的nm - max_data_nm = max_data_row['nm'] - - res = f"本次实验的PL峰位为: {max_data_nm} nm" - print(res) - return res + useful_results = [] + try: + answer = eval(result.get("answer", "[]")) + for item in answer: + metadata = item.get("metadata", {}) + useful_info = { + "id": metadata.get("document_id"), + "title": item.get("title"), + "content": item.get("content"), + "metadata": None, + "embedding": None, + "score": metadata.get("score") + } + useful_results.append(useful_info) + except Exception as e: + return [{"error": f"Error processing result: {e}", "status": "TERMINATE"}] + if useful_results == []: + useful_results = "NULL" + return str(useful_results) diff --git a/backend/views.py b/backend/views.py index b926e10..48ca2b9 100644 --- a/backend/views.py +++ b/backend/views.py @@ -67,6 +67,10 @@ class ChatConsumer(AsyncWebsocketConsumer): print(f" - Connected to server on {uri}", flush=True) print(" - Sending message to server.", flush=True) + print(text_data) + # json_data = json.loads(text_data) + # chat_id = json_data['chat_id'] + # websocket.send(json_data['message']) websocket.send(text_data) import re @@ -116,7 +120,7 @@ class ChatConsumer(AsyncWebsocketConsumer): if current_agent in ['analysis_executor','analysis_pl_uv', 'analysis_picturer', 'Experiment_Optimizer', 'optimizer_critic', 'Outer_Analysis_Admin']: group_name = 'Optimizer' - content = {"group_name": group_name, "agent_name": current_agent.replace("_", " ").title(), "content": cleaned_string} + content = {"group_name": group_name, "agent_name": current_agent.replace("_", " ").title(), "content": cleaned_string.replace('>>>>>>>>', '')} # 通过 WebSocket 消费者发送消息 asyncio.run(self.send(text_data=json.dumps(content)))