Spaces:
Running
Running
File size: 3,458 Bytes
74ebe5c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 |
import gradio as gr
import pandas as pd
import json
from model_handler import ModelHandler
from config import LING_1T
def _format_kb_for_prompt(df: pd.DataFrame) -> str:
"""Formats the knowledge base DataFrame into a simple list for the prompt."""
if df is None or df.empty:
return "无。"
terms = [f"- {row['Term']}" for _, row in df.iterrows()]
return "\n".join(terms)
def suggest_new_kb_terms_agent(kb_df: pd.DataFrame, editor_content: str):
"""
Agent to extract new terms from the text to recommend for the knowledge base using a real LLM.
"""
if editor_content is None or len(editor_content.strip()) < 50:
print("[Agent] Editor content too short, skipping KB suggestion.")
# Return empty data and keep components hidden
return gr.update(value=[], visible=False), gr.update(visible=False)
try:
# 1. Prepare Prompts
system_prompt = (
"你是一个实体提取机器人。你的任务是从给定文本中识别出新的、重要的、值得记录的专有名词（如人名、地名、组织、物品）或核心概念，并为它们提供一句简洁的描述。\n"
"你的回答必须是一个遵循以下规则的 JSON 数组：\n"
"1. 数组中的每个元素都是一个对象。\n"
"2. 每个对象必须包含两个键：`Term` (词条名) 和 `Description` (描述)。\n"
"3. 不要提取已经存在于'现有知识库'中的词条。\n"
"4. 最多返回 5 个最重要的词条。\n"
"5. 不要返回除了这个 JSON 数组之外的任何其他文本、解释或代码块标记。"
)
kb_str = _format_kb_for_prompt(kb_df)
user_prompt = (
f"### 现有知识库\n{kb_str}\n\n"
f"### 当前文本\n{editor_content[-4000:]}\n\n"
"### 指令\n请根据'当前文本'，分析并提取出新的知识库词条，并返回 JSON 数组。"
)
# 2. Call LLM
model_handler = ModelHandler()
response_generator = model_handler.generate_code(
system_prompt=system_prompt,
user_prompt=user_prompt,
model_choice=LING_1T
)
full_response = "".join(chunk for chunk in response_generator)
# 3. Parse JSON and format for DataFrame
print("【收到的完整上下文】")
print("full_response:", repr(full_response))
if full_response.strip().startswith("```json"):
full_response = full_response.strip()[7:-3].strip()
suggested_terms = json.loads(full_response)
# Convert list of dicts to list of lists for Gradio Dataframe
df_data = [[item.get("Term", ""), item.get("Description", "")] for item in suggested_terms]
print("【收到的完整上下文】")
print("suggested_terms:", repr(suggested_terms))
# Make components visible and return data
return gr.update(value=df_data, visible=True), gr.update(visible=True)
except json.JSONDecodeError:
print(f"[Agent] Error: Failed to decode JSON from LLM response for KB: {full_response}")
return gr.update(visible=False), gr.update(visible=False)
except Exception as e:
print(f"[Agent] Error suggesting new KB terms: {e}")
return gr.update(visible=False), gr.update(visible=False)
|