Update Gradio_en.py

Gradio_en.py

@@ -3,9 +3,126 @@ import gradio as gr
 import pandas as pd
 import json
 import random
+import numpy as np
+import faiss
+from transformers import AutoTokenizer, AutoModel
+import torch
+from collections import defaultdict
 from LLM import zero_shot
 from prompt_generate import generate_prompt_with_examples as generate_prompt
 
+# Global KNN retriever instance
+_knn_retriever = None
+
+class EntityLevelRetriever:
+    def __init__(self, model_name='bert-base-uncased'):
+        self.tokenizer = AutoTokenizer.from_pretrained(model_name)
+        self.model = AutoModel.from_pretrained(model_name)
+        self.index = faiss.IndexFlatL2(768)  
+        self.entity_db = []
+        self.metadata = []
+        self.train_data = []
+
+    def _get_entity_span(self, text, entity):
+        start = text.find(entity)
+        if start == -1:
+            return None
+        return (start, start + len(entity))
+
+    def _generate_entity_embedding(self, text, entity):
+        span = self._get_entity_span(text, entity)
+        if not span:
+            return None
+
+        inputs = self.tokenizer(text, return_tensors='pt', truncation=True)
+        with torch.no_grad():
+            outputs = self.model(**inputs)
+
+        char_to_token = lambda x: inputs.char_to_token(x)
+        start_token = char_to_token(span[0])
+        end_token = char_to_token(span[1]-1)
+
+        if not start_token or not end_token:
+            return None
+
+        entity_embedding = outputs.last_hidden_state[0, start_token:end_token+1].mean(dim=0).numpy()
+        return entity_embedding.astype('float32')
+
+    def build_index(self, train_path):
+        with open(train_path, 'r', encoding='utf-8') as f:
+            dataset = json.load(f)
+        
+        # Use data from index 500-999 (501-1000 in 1-based indexing)
+        self.train_data = dataset[500:1000]
+        
+        for item in self.train_data:
+            text = item['text']
+            for triple in item['triple_list']:
+                for entity in [triple[0], triple[2]]:
+                    embedding = self._generate_entity_embedding(text, entity)
+                    if embedding is not None:
+                        self.entity_db.append(embedding)
+                        self.metadata.append({
+                            'entity': entity,
+                            'type': triple[1], 
+                            'context': text,
+                            'full_item': item
+                        })
+
+        if self.entity_db:
+            self.index.add(np.array(self.entity_db))
+
+    def search_similar_texts(self, query_text, top_k=3):
+        """Search for similar texts based on entity embeddings"""
+        if not self.train_data:
+            return []
+            
+        # Extract entities from query text (simplified approach)
+        # For better results, you might want to use NER or other entity extraction methods
+        query_entities = self._extract_potential_entities(query_text)
+        
+        context_scores = defaultdict(float)
+        context_items = {}
+        
+        for entity in query_entities:
+            embedding = self._generate_entity_embedding(query_text, entity)
+            if embedding is None:
+                continue
+                
+            distances, indices = self.index.search(np.array([embedding]), top_k * 2)
+            
+            for j in range(len(indices[0])):
+                idx = indices[0][j]
+                if 0 <= idx < len(self.metadata):
+                    ctx_info = self.metadata[idx]
+                    distance = distances[0][j]
+                    context = ctx_info['context']
+                    
+                    # Weight by inverse distance
+                    score = 1 / (1 + distance)
+                    context_scores[context] += score
+                    context_items[context] = ctx_info['full_item']
+        
+        # Sort by score and return top_k
+        scored_contexts = sorted(context_scores.items(), key=lambda x: x[1], reverse=True)
+        
+        results = []
+        for context, score in scored_contexts[:top_k]:
+            if context in context_items:
+                results.append(context_items[context])
+        
+        return results
+    
+    def _extract_potential_entities(self, text):
+        """Simple entity extraction - you can improve this with better NER"""
+        # Split by common delimiters and filter meaningful terms
+        import re
+        # Extract potential geological terms (capitalized words, formations, etc.)
+        entities = re.findall(r'\b[A-Z][a-z]+(?:\s+[A-Z][a-z]+)*\b', text)
+        # Also include technical terms
+        entities.extend(re.findall(r'\b\w+(?:stone|rock|formation|group|member)\b', text, re.IGNORECASE))
+        return list(set(entities))
+
 def get_model_options():
     """Get available model series options"""
     return ['gpt', 'llama', 'qwen', 'deepSeek', 'gemini', 'claude']
@@ -26,7 +143,7 @@ def get_prompt_templates():
     """Get predefined prompt templates"""
     templates = {
         "Custom": "",
-        "Zero-shot Basic Extraction": """You are a professional and experienced expert in engineering geology. Your task is to extract "entity-relation-entity" triples from the given input text. There are 24 types of relations: "Lithology", "Paleontological", "Thickness", "Outcrop", "Develop", "Exposed", "Distribution pattern", "Contained", "Coordinates", "Age", "Integration of contacts", "Unconformity contact", "Fault contact", "Belongs to", "Elevation", "Located at", "Exposed area", "Geotectonic position", "Stratigraphical zoning", "Consolidated contact", "Administrative area", "Engulfed", "Length", "Invade", Please follow these specifications for extraction:
+        "Zero-shot prompting": """You are a professional and experienced expert in engineering geology. Your task is to extract "entity-relation-entity" triples from the given input text. There are 24 types of relations: "Lithology", "Paleontological", "Thickness", "Outcrop", "Develop", "Exposed", "Distribution pattern", "Contained", "Coordinates", "Age", "Integration of contacts", "Unconformity contact", "Fault contact", "Belongs to", "Elevation", "Located at", "Exposed area", "Geotectonic position", "Stratigraphical zoning", "Consolidated contact", "Administrative area", "Engulfed", "Length", "Invade", Please follow these specifications for extraction:
 1. Output format:
 Strictly follow JSON array format, no additional text, each element contains:
 [
@@ -39,7 +156,7 @@ Strictly follow JSON array format, no additional text, each element contains:
 2. Complex relationship handling:
 - If the same entity participates in multiple relationships, list different triples separately""",
         
-        "knowledge-injected Enhanced Extraction": """You are a professional and experienced expert in engineering geology. Your task is to extract "entity-relation-entity" triples from the given input text. There are 24 types of relations: "Lithology", "Paleontological", "Thickness", "Outcrop", "Develop", "Exposed", "Distribution pattern", "Contained", "Coordinates", "Age", "Integration of contacts", "Unconformity contact", "Fault contact", "Belongs to", "Elevation", "Located at", "Exposed area", "Geotectonic position", "Stratigraphical zoning", "Consolidated contact", "Administrative area", "Engulfed", "Length", "Invade", Please follow these specifications for extraction:
+        "Knowledge-injected prompting": """You are a professional and experienced expert in engineering geology. Your task is to extract "entity-relation-entity" triples from the given input text. There are 24 types of relations: "Lithology", "Paleontological", "Thickness", "Outcrop", "Develop", "Exposed", "Distribution pattern", "Contained", "Coordinates", "Age", "Integration of contacts", "Unconformity contact", "Fault contact", "Belongs to", "Elevation", "Located at", "Exposed area", "Geotectonic position", "Stratigraphical zoning", "Consolidated contact", "Administrative area", "Engulfed", "Length", "Invade", Please follow these specifications for extraction:
 1. Output format:
 Strictly follow JSON array format, no additional text, each element contains:
 [
@@ -52,53 +169,53 @@ Strictly follow JSON array format, no additional text, each element contains:
 2. Complex relationship handling:
 - If the same entity participates in multiple relationships, list different triples separately
 3. Relationship explanations:
-Outcrop at: Refers to rocks or strata exposed at the surface or near-surface, not covered or buried. Example: (Late Ordovician-Silurian intrusive rocks, outcrop at, southern investigation area).
+Exposed: Refers to rocks or strata exposed at the surface or near-surface, not covered or buried. Example: (Late Ordovician-Silurian intrusive rocks, Exposed, southern investigation area).
 
-Located in: Establishes the subordinate relationship of geological units within a larger spatial framework (administrative region/tectonic unit). Example: (Kumuqi Silurian basaltic basic rocks, located in, central-western investigation area)
+Located at: Establishes the subordinate relationship of geological units within a larger spatial framework (administrative region/tectonic unit). Example: (Kumuqi Silurian basaltic basic rocks, Located at, central-western investigation area)
 
-Conformable contact: Indicates contact relationships formed by continuous deposition of upper and lower strata, reflecting gradational lithological characteristics without significant depositional hiatus. Example: (Solake Formation, conformable contact, Middle Ordovician Lin Formation).
+Integration of contacts: Indicates contact relationships formed by continuous deposition of upper and lower strata, reflecting gradational lithological characteristics without significant depositional hiatus. Example: (Solake Formation, Integration of contacts, Middle Ordovician Lin Formation).
 
-Unconformable contact: Describes stratigraphic contact interfaces with depositional gaps, including contact features with angular differences or lithological abrupt changes. Example: (Tongziyan Formation, unconformable contact, Maokou Formation).
+Unconformity contact: Describes stratigraphic contact interfaces with depositional gaps, including contact features with angular differences or lithological abrupt changes. Example: (Tongziyan Formation, Unconformity contact, Maokou Formation).
 
-Paraconformable contact: Specifically refers to parallel unconformity types with consistent attitudes, emphasizing depositional sequence interruption but without structural deformation. Example: (Solake Formation, paraconformable contact, Middle Ordovician Lin Formation).
+Consolidated contact: Specifically refers to parallel unconformity types with consistent attitudes, emphasizing depositional sequence interruption but without structural deformation. Example: (Solake Formation, Consolidated contact, Middle Ordovician Lin Formation).
 
-Fault contact: Two strata are separated by fault zones or fault planes, often accompanied by dynamic crushing and other structural phenomena. Example: (Solake Formation, fault contact, Upper Ordovician Lapai Spring Formation).
+Fault contact: Two strata are separated by fault zones or fault planes, often accompanied by dynamic crushing and other structural phenomena. Example: (Solake Formation, Fault contact, Upper Ordovician Lapai Spring Formation).
 
-Distribution pattern: Depicts spatial distribution characteristics of geological units, including geometric morphology and extension direction combinations. Example: (Carboniferous, distribution pattern, banded).
+Distribution pattern: Depicts spatial distribution characteristics of geological units, including geometric morphology and extension direction combinations. Example: (Carboniferous, Distribution pattern, banded).
 
-Tectonic position: Locates geological units' attribution in plate tectonic framework, associated with orogenic belts or tectonic unit divisions. Example: (Carboniferous, tectonic position, northern margin of Gondwana tectonic belt).
+Geotectonic position: Locates geological units' attribution in plate tectonic framework, associated with orogenic belts or tectonic unit divisions. Example: (Carboniferous, Geotectonic position, northern margin of Gondwana tectonic belt).
 
-Stratigraphic division: Characterizes hierarchical attribution and zoning attributes of stratigraphic units in regional stratigraphic division systems. Example: (Carboniferous, stratigraphic division, Gondwana).
+Stratigraphical zoning: Characterizes hierarchical attribution and zoning attributes of stratigraphic units in regional stratigraphic division systems. Example: (Carboniferous, Stratigraphical zoning, Gondwana).
 
-Exposed strata: Specifically refers to actually exposed stratigraphic entities in a region, emphasizing observable surface geological units. Example: (Hongliugou gold-copper mining area, exposed strata, Nanhua-Lower Ordovician Hongliugou Group).
+Outcrop: Specifically refers to actually exposed stratigraphic entities in a region, emphasizing observable surface geological units. Example: (Hongliugou gold-copper mining area, Outcrop, Nanhua-Lower Ordovician Hongliugou Group).
 
 Lithology: Defines material composition and structural characteristics of rocks, including hierarchical descriptive elements of composite lithology. Example: (Late Ordovician-Silurian syenite, lithology, altered syenite).
 
 Thickness: Quantifies vertical dimensions of strata/rock bodies, including dimensional expressions with absolute values and relative descriptions. Example: (syenite, thickness, 35.60 m).
 
-Area: Characterizes horizontal distribution range of geological units, presented in standardized form combining numerical values and units. Example: (intrusive rocks, outcrop area, 54 m2)
+Exposed area: Characterizes horizontal distribution range of geological units, presented in standardized form combining numerical values and units. Example: (intrusive rocks, Exposed area, 54 m2)
 
 Coordinates: Specifically refers to geographical spatial positioning data recording geological feature points. Example: (Solake copper-gold mine site, coordinates, 90°11′47″E).
 
 Length: Describes spatial extension dimensions of linear geological bodies. Example: Triple (Shibien fault zone, length, 20m) can be extracted.
 
-Contains: Indicates compositional inclusion relationships of main materials, specifically referring to mineral composition or fossil occurrence states, different from everyday meaning. Example: (medium gray-black massive chert, contains, chert bands).
+Contained: Indicates compositional inclusion relationships of main materials, specifically referring to mineral composition or fossil occurrence states, different from everyday meaning. Example: (medium gray-black massive chert, Contained, chert bands).
 
 Age: Establishes correspondence between geological units and standard geological chronological systems. Example: (Hongliugou gold-copper mining area, age, Early-Middle Permian).
 
-Administrative division: Defines subordinate hierarchy and territorial attribution of geological entities in administrative management systems. Example: (investigation area, administrative division, Chayang County).
+Administrative area: Defines subordinate hierarchy and territorial attribution of geological entities in administrative management systems. Example: (investigation area, Administrative area, Chayang County).
 
-Development: Describes manifestation degree and formation state intensity of geological structures or depositional features. Example: (Lanhuaweng Formation, development, horizontal bedding).
+Develop: Describes manifestation degree and formation state intensity of geological structures or depositional features. Example: (Lanhuaweng Formation, Develop, horizontal bedding).
 
-Paleontology: Records fossil biological information occurring in strata, requiring complete Latin scientific names and classification features. Example: (strata, paleontology, Lumu et al).
+Paleontological: Records fossil biological information occurring in strata, requiring complete Latin scientific names and classification features. Example: (strata, Paleontological, Lumu et al).
 
 Elevation: Quantifies elevation data of geological feature points relative to sea level, retaining measurement reference identification. Example: (Solake copper-gold mine site, elevation, 2800m).
 
-Belongs to: Establishes type attribution of geological units in classification systems. Example: (mining area, belongs to, polymetallic mineralization subarea).
+Paleontological: Establishes type attribution of geological units in classification systems. Example: (mining area, belongs to, polymetallic mineralization subarea).
 
-Engulf: Characterizes spatial replacement processes of intrusive bodies on country rocks, reflecting transformation effects of magmatic activities. Example: (Nintendo Rock Formation, engulf, Jurassic granite).
+Engulfed: Characterizes spatial replacement processes of intrusive bodies on country rocks, reflecting transformation effects of magmatic activities. Example: (Nintendo Rock Formation, Engulfed, Jurassic granite).
 
-Intrude: Describes geological processes of magmatic rock bodies penetrating country rocks, including accompanying phenomena such as contact metamorphism. Example: (Gaozhou Shell Stone Formation, intrude, gneissic granite).
+Invade: Describes geological processes of magmatic rock bodies penetrating country rocks, including accompanying phenomena such as contact metamorphism. Example: (Gaozhou Shell Stone Formation, Invade, gneissic granite).
 
 4. Other key points:
 All triple relationships must be one of the above 24 types
@@ -110,10 +227,10 @@ def get_qa_prompt_templates():
     """Get QA module prompt templates"""
     templates = {
         "Custom": "",
-        "Zero-shot True/False": "Please judge true or false based on the given text.",
-        "Zero-shot Q&A": "Please answer the question based on the given text.",
-        "COT True/False": "Please first judge true or false, and provide your reasoning basis.",
-        "COT Q&A": "Please first answer the question, and provide your reasoning basis.",
+        "Yes/No QA": "Please judge true or false based on the given text.",
+        "Factoid QA": "Please answer the question based on the given text.",
+        "CoT prompting of Yes/No QA": "Please first judge true or false, and provide your reasoning basis.",
+        "CoT prompting of Factoid QA": "Please first answer the question, and provide your reasoning basis.",
     }
     return templates
 
@@ -131,37 +248,76 @@ def load_train_data():
             _text_series = _train_data['text']
             _label_series = _train_data['triple_list']
         except Exception as e:
-            print(f"Failed to load training data: {e}")
+            # print(f"Failed to load training data: {e}")
             return False
     return True
 
+def initialize_knn_retriever():
+    """Initialize the KNN retriever"""
+    global _knn_retriever
+    if _knn_retriever is None:
+        try:
+            # print("Initializing KNN retriever...")
+            _knn_retriever = EntityLevelRetriever()
+            _knn_retriever.build_index('./data/train_triples.json')
+            # print("KNN retriever initialized successfully!")
+        except Exception as e:
+            # print(f"Failed to initialize KNN retriever: {e}")
+            _knn_retriever = None
+    return _knn_retriever is not None
+
 def generate_random_context_prompt(user_text, num_examples):
-    """Generate random context prompts"""
+    """Generate Random sampling prompts"""
     if not load_train_data():
         return "Unable to load training data"
     
     try:
         random_prompt = generate_prompt(_text_series, _label_series, num_examples)
+        print(random_prompt)
         return f"Here are geological description text and triple extraction examples:\n\n{random_prompt}\nPlease extract triples based on the examples:\n{user_text}"
     except Exception as e:
-        return f"Failed to generate random context prompt: {e}"
+        return f"Failed to generate Random sampling prompt: {e}"
+
+def generate_knn_context_prompt(user_text, num_examples):
+    """Generate KNN-based sampling prompts"""
+    global _knn_retriever
+    
+    if not initialize_knn_retriever():
+        return "Unable to initialize KNN retriever"
+    
+    try:
+        similar_items = _knn_retriever.search_similar_texts(user_text, num_examples)
+        
+        if not similar_items:
+            return f"No similar examples found, performing zero-shot extraction:\n{user_text}"
+        
+        examples_text = ""
+        for i, item in enumerate(similar_items):
+            examples_text += f"Example {i+1}:\n"
+            examples_text += f"Text: {item['text']}\n"
+            examples_text += f"Triples: {json.dumps(item['triple_list'], ensure_ascii=False)}\n\n"
+        print(examples_text)
+        return f"Here are geological description text and triple extraction examples based on KNN similarity:\n\n{examples_text}Please extract triples based on the examples:\n{user_text}"
+    
+    except Exception as e:
+        return f"Failed to generate KNN-based sampling prompt: {e}"
 
 def update_model_names(model_series):
     """Update model name dropdown list when model series changes"""
     names = get_common_model_names(model_series)
-    return gr.Dropdown(choices=names, value=names[0] if names else "", label="Model Name", allow_custom_value=True)
+    return gr.Dropdown(choices=names, value=names[0] if names else "", label="Select the specific model", allow_custom_value=True)
 
 def update_prompt_content(template_name):
     """Update content when prompt template changes"""
     templates = get_prompt_templates()
     content = templates.get(template_name, "")
-    return gr.Textbox(value=content, label="Prompt Content", lines=15, max_lines=25)
+    return gr.Textbox(value=content, label="Prompt ", lines=15, max_lines=25)
 
 def update_qa_prompt_content(template_name):
     """Update content when QA prompt template changes"""
     templates = get_qa_prompt_templates()
     content = templates.get(template_name, "")
-    return gr.Textbox(value=content, label="QA Prompt Content", lines=3, max_lines=10)
+    return gr.Textbox(value=content, label="QA Prompt ", lines=3, max_lines=10)
 
 def call_llm_model(model_series, model_name, prompt_content, user_content, context_type, num_examples):
     """LLM model wrapper function (triple extraction)"""
@@ -172,18 +328,24 @@ def call_llm_model(model_series, model_name, prompt_content, user_content, conte
         if not user_content:
             return "Please input text content to process"
         
-        # Combine complete input content based on context type
-        if context_type == "No Context":
+        # Combine complete input content based on Demonstration type
+        if context_type == "No demonstration":
             if prompt_content.strip():
                 full_content = prompt_content.strip() + "\n\n" + user_content
             else:
                 full_content = user_content
-        elif context_type == "Random Context":
+        elif context_type == "Random sampling":
             context_prompt = generate_random_context_prompt(user_content, num_examples)
             if prompt_content.strip():
                 full_content = prompt_content.strip() + "\n\n" + context_prompt
             else:
                 full_content = context_prompt
+        elif context_type == "KNN-based sampling":
+            context_prompt = generate_knn_context_prompt(user_content, num_examples)
+            if prompt_content.strip():
+                full_content = prompt_content.strip() + "\n\n" + context_prompt
+            else:
+                full_content = context_prompt
         else:
             if prompt_content.strip():
                 full_content = prompt_content.strip() + "\n\n" + user_content
@@ -215,18 +377,18 @@ def call_qa_model(model_series, model_name, qa_prompt_content, geological_text,
             return "Please input geological text"
         
         if not question_or_statement:
-            if qa_type == "True/False":
+            if qa_type == "Yes/No QA":
                 return "Please input factual statement to judge"
             else:
                 return "Please input question to answer"
         
         # Combine complete input content
-        if qa_type == "True/False":
+        if qa_type == "Yes/No QA":
             if qa_prompt_content.strip():
                 full_content = f"{qa_prompt_content.strip()}\n\nGeological text:\n{geological_text}\n\nStatement to judge:\n{question_or_statement}"
             else:
                 full_content = f"Geological text:\n{geological_text}\n\nStatement to judge:\n{question_or_statement}"
-        else:  # Q&A
+        else:  # Factoid QA
             if qa_prompt_content.strip():
                 full_content = f"{qa_prompt_content.strip()}\n\nGeological text:\n{geological_text}\n\nQuestion:\n{question_or_statement}"
             else:
@@ -251,13 +413,13 @@ def create_interface():
     """Create Gradio interface"""
     
     with gr.Blocks(title="GeoLLM Model Interface", theme=gr.themes.Soft()) as demo:
-        gr.Markdown("# 🚀 GeoLLM Geological Intelligence Platform")
-        gr.Markdown("Professional geological text analysis tool integrating triple extraction and intelligent Q&A functions")
+        gr.Markdown("# 🚀 GeoLLM-Toolkit: An Interactive Platform for Geological Text Understanding and Knowledge Extraction")
+        gr.Markdown("A domain-specific, modular framework designed to operationalize large language models (LLMs) for advanced geological natural language processing")
         
         # Add tabs
         with gr.Tabs():
             # Triple extraction module
-            with gr.TabItem("🔗 Triple Extraction", elem_id="triple_extraction"):
+            with gr.TabItem("🔗 KG Triple Extraction", elem_id="triple_extraction"):
                 with gr.Row():
                     with gr.Column(scale=1):
                         # Model selection area
@@ -272,18 +434,11 @@ def create_interface():
                         model_name = gr.Dropdown(
                             choices=get_common_model_names("gpt"),
                             value="gpt-3.5-turbo",
-                            label="Model Name",
-                            info="Select specific model name, or input manually",
+                            label="Select the specific model",
+                            info="Select specific model name",
                             allow_custom_value=True
                         )
                         
-                        # Custom model name input box
-                        custom_model_name = gr.Textbox(
-                            label="Custom Model Name (Optional)",
-                            placeholder="If your desired model is not in the options above, please input here",
-                            info="Input here will override the selection above"
-                        )
-                        
                         # Prompt template selection
                         gr.Markdown("## 📝 Prompt Template")
                         prompt_template = gr.Dropdown(
@@ -293,13 +448,13 @@ def create_interface():
                             info="Select predefined prompt template or customize"
                         )
                         
-                        # Context type selection
-                        gr.Markdown("## 🎯 Context Configuration")
+                        # Demonstration type selection
+                        gr.Markdown("## 🎯 Few-Shot Prompting Settings")
                         context_type = gr.Dropdown(
-                            choices=["No Context", "Random Context"],
-                            value="No Context",
-                            label="Context Type",
-                            info="Choose whether to use context examples"
+                            choices=["No demonstration", "Random sampling", "KNN-based sampling"],
+                            value="No demonstration",
+                            label="Demonstration type",
+                            info="Choose the method for selecting context examples"
                         )
                         
                         num_examples = gr.Slider(
@@ -312,14 +467,14 @@ def create_interface():
                         )
                         
                     with gr.Column(scale=2):
-                        # Prompt content area
-                        gr.Markdown("## 🎯 Prompt Content")
+                        # Prompt  area
+                        gr.Markdown("## 🎯 Prompt")
                         prompt_content = gr.Textbox(
-                            label="Prompt Content",
+                            label="Prompt ",
                             placeholder="Select template or customize your prompt...",
                             lines=15,
                             max_lines=25,
-                            info="Will be sent to the model as system prompt"
+                            info="Defines the task-specific prompt during geological NLP tasks"
                         )
                         
                         # User input area
@@ -349,19 +504,18 @@ def create_interface():
                 gr.Markdown("## 💡 Usage Examples")
                 gr.Examples(
                     examples=[
-                        ["gpt", "gpt-3.5-turbo", "No Context", 2, "The Noriba Gari Bao Formation originally refers to gray-green thick-bedded medium- to fine-grained lithic feldspar sandstone, feldspar quartz sandstone, feldspar sandstone occasionally interbedded with siltstone, clay rock and micritic limestone, only bivalve fossils are seen, and continuous deposition with the overlying Ninety Road Class Formation."],
-                        ["gemini", "gemini-1.5-pro-002", "Random Context", 3, "The Quemo Cuo Formation has only a small outcrop in the Sewang Yongqu area in the southwest corner of the map sheet within the survey area, with an area of less than 10m2 and a thickness greater than 29.25m."],
-                        ["claude", "claude-3-5-haiku-20241022", "No Context", 2, "Hecosmilia sp. scabbard coral was collected from limestone; Complexastraea sp. and Radulopccten sp. scraping sea fan; Oscillopha sp., dated to the Middle Jurassic."],
-                        ["deepSeek", "deepseek-ai/DeepSeek-V3", "Random Context", 3, "Late Triassic granite is mainly distributed in the Ladi Gongma Mianche Ri Ahri Qu area of the survey area. Regionally controlled by NW-SE trending regional faults within the structural melange zone, it is distributed in long strips. The intrusive bodies have good gregariousness and excellent zonal extensibility, with 8 exposed intrusive bodies covering an area of about 227m2."],
+                        ["gpt", "gpt-3.5-turbo", "No demonstration", 2, "The Noriba Gari Bao Formation originally refers to gray-green thick-bedded medium- to fine-grained lithic feldspar sandstone, feldspar quartz sandstone, feldspar sandstone occasionally interbedded with siltstone, clay rock and micritic limestone, only bivalve fossils are seen, and continuous deposition with the overlying Ninety Road Class Formation."],
+                        ["gemini", "gemini-1.5-pro-002", "Random sampling", 3, "The Quemo Cuo Formation has only a small outcrop in the Sewang Yongqu area in the southwest corner of the map sheet within the survey area, with an area of less than 10m2 and a thickness greater than 29.25m."],
+                        ["claude", "claude-3-5-haiku-20241022", "KNN-based sampling", 2, "Hecosmilia sp. scabbard coral was collected from limestone; Complexastraea sp. and Radulopccten sp. scraping sea fan; Oscillopha sp., dated to the Middle Jurassic."],
+                        ["deepSeek", "deepseek-ai/DeepSeek-V3", "KNN-based sampling", 3, "Late Triassic granite is mainly distributed in the Ladi Gongma Mianche Ri Ahri Qu area of the survey area. Regionally controlled by NW-SE trending regional faults within the structural melange zone, it is distributed in long strips. The intrusive bodies have good gregariousness and excellent zonal extensibility, with 8 exposed intrusive bodies covering an area of about 227m2."],
                     ],
                     inputs=[model_series, model_name, context_type, num_examples, user_content]
                 )
                 
                 # Event handling
-                def submit_request(series, name, custom_name, template, prompt, content, ctx_type, num_ex):
-                    # Use custom model name if provided
-                    final_model_name = custom_name.strip() if custom_name.strip() else name
-                    return call_llm_model(series, final_model_name, prompt, content, ctx_type, num_ex)
+                def submit_request(series, name, template, prompt, content, ctx_type, num_ex):
+                    # Use the selected model name directly
+                    return call_llm_model(series, name, prompt, content, ctx_type, num_ex)
                 
                 # Update model name options
                 model_series.change(
@@ -370,7 +524,7 @@ def create_interface():
                     outputs=[model_name]
                 )
                 
-                # Update prompt content
+                # Update Prompt 
                 prompt_template.change(
                     fn=update_prompt_content,
                     inputs=[prompt_template],
@@ -380,7 +534,7 @@ def create_interface():
                 # Submit button event
                 submit_btn.click(
                     fn=submit_request,
-                    inputs=[model_series, model_name, custom_model_name, prompt_template, prompt_content, user_content, context_type, num_examples],
+                    inputs=[model_series, model_name, prompt_template, prompt_content, user_content, context_type, num_examples],
                     outputs=[output]
                 )
                 
@@ -393,12 +547,12 @@ def create_interface():
                 # Enter key submission
                 user_content.submit(
                     fn=submit_request,
-                    inputs=[model_series, model_name, custom_model_name, prompt_template, prompt_content, user_content, context_type, num_examples],
+                    inputs=[model_series, model_name, prompt_template, prompt_content, user_content, context_type, num_examples],
                     outputs=[output]
                 )
             
             # QA module
-            with gr.TabItem("❓ Intelligent Q&A", elem_id="qa_module"):
+            with gr.TabItem("❓ Geological Q&A", elem_id="qa_module"):
                 with gr.Row():
                     with gr.Column(scale=1):
                         # Model selection area
@@ -413,23 +567,16 @@ def create_interface():
                         qa_model_name = gr.Dropdown(
                             choices=get_common_model_names("gpt"),
                             value="gpt-3.5-turbo",
-                            label="Model Name",
-                            info="Select specific model name, or input manually",
+                            label="Select the specific model",
+                            info="Select specific model name",
                             allow_custom_value=True
                         )
                         
-                        # Custom model name input box
-                        qa_custom_model_name = gr.Textbox(
-                            label="Custom Model Name (Optional)",
-                            placeholder="If your desired model is not in the options above, please input here",
-                            info="Input here will override the selection above"
-                        )
-                        
                         # QA type selection
-                        gr.Markdown("## 🎯 Q&A Type")
+                        gr.Markdown("## 🎯 Geological Q&A")
                         qa_type = gr.Dropdown(
-                            choices=["True/False", "Q&A"],
-                            value="True/False",
+                            choices=["Yes/No QA", "Factoid QA"],
+                            value="Yes/No QA",
                             label="Task Type",
                             info="Choose between judging true/false or answering questions"
                         )
@@ -438,31 +585,31 @@ def create_interface():
                         gr.Markdown("## 📝 Prompt Template")
                         qa_prompt_template = gr.Dropdown(
                             choices=list(get_qa_prompt_templates().keys()),
-                            value="Zero-shot True/False",
+                            value="Yes/No QA",
                             label="Select QA Prompt Template",
                             info="Select predefined prompt template or customize"
                         )
                         
                     with gr.Column(scale=2):
-                        # QA Prompt content area
-                        gr.Markdown("## 🎯 Prompt Content")
+                        # QA Prompt  area
+                        gr.Markdown("## 🎯 Prompt")
                         qa_prompt_content = gr.Textbox(
-                            label="QA Prompt Content",
+                            label="QA Prompt ",
                             value="Please judge true or false based on the given text.",
                             placeholder="Select template or customize your prompt...",
                             lines=3,
                             max_lines=10,
-                            info="Will be sent to the model as system prompt"
+                            info="Defines the task-specific prompt during geological NLP tasks"
                         )
                         
                         # Geological text input area
                         gr.Markdown("## 📄 Geological Text")
                         geological_text = gr.Textbox(
-                            label="Geological Background Text",
+                            label="Contextual Text in Geological Domain",
                             placeholder="Please input geological description text as background...",
                             lines=8,
                             max_lines=15,
-                            info="Provides contextual information for answering questions or judging facts"
+                            info="Provides contextual information for Q&A tasks"
                         )
                         
                         # Question or statement input area
@@ -492,50 +639,49 @@ def create_interface():
                 # Example area
                 gr.Markdown("## 💡 Usage Examples")
                 
-                # True/False examples
-                with gr.Accordion("True/False Examples", open=False):
+                # Yes/No QA examples
+                with gr.Accordion("Yes/No QA Examples", open=False):
                     gr.Examples(
                         examples=[
-                            ["gpt", "gpt-3.5-turbo", "True/False", "Sudden geological disasters in Huoshan County are mainly collapses, landslides, and debris flows. A total of 190 sudden geological disaster points (including hidden danger points) have been identified, including 74 collapses, 96 landslides, 14 debris flows, and 6 unstable slopes. There are 58 newly discovered geological disaster points, accounting for 30.5% of the total. Among the 190 collapses, landslides, debris flows and other sudden geological disasters in Huoshan County, most are caused by human factors. There are 163 geological disasters caused by human factors, accounting for 85.8%; there are 27 disasters formed by natural factors, accounting for 14.2%.", "In the sudden geological disasters in Huoshan County, the number of landslides exceeds the number of collapses."],
-                            ["deepSeek", "deepseek-ai/DeepSeek-V3", "True/False", "Sudden geological disasters in Huoshan County are mainly collapses, landslides, and debris flows. A total of 190 sudden geological disaster points (including hidden danger points) have been identified, including 74 collapses, 96 landslides, 14 debris flows, and 6 unstable slopes.", "The total number of geological disaster points in Huoshan County exceeds 200."],
+                            ["gpt", "gpt-3.5-turbo", "Yes/No QA", "Sudden geological disasters in Huoshan County are mainly collapses, landslides, and debris flows. A total of 190 sudden geological disaster points (including hidden danger points) have been identified, including 74 collapses, 96 landslides, 14 debris flows, and 6 unstable slopes. There are 58 newly discovered geological disaster points, accounting for 30.5% of the total. Among the 190 collapses, landslides, debris flows and other sudden geological disasters in Huoshan County, most are caused by human factors. There are 163 geological disasters caused by human factors, accounting for 85.8%; there are 27 disasters formed by natural factors, accounting for 14.2%.", "In the sudden geological disasters in Huoshan County, the number of landslides exceeds the number of collapses."],
+                            ["deepSeek", "deepseek-ai/DeepSeek-V3", "Yes/No QA", "Sudden geological disasters in Huoshan County are mainly collapses, landslides, and debris flows. A total of 190 sudden geological disaster points (including hidden danger points) have been identified, including 74 collapses, 96 landslides, 14 debris flows, and 6 unstable slopes.", "The total number of geological disaster points in Huoshan County exceeds 200."],
                         ],
                         inputs=[qa_model_series, qa_model_name, qa_type, geological_text, question_or_statement]
                     )
                 
-                # Q&A examples
-                with gr.Accordion("Q&A Examples", open=False):
+                # Factoid QA examples
+                with gr.Accordion("Factoid QA Examples", open=False):
                     gr.Examples(
                         examples=[
-                            ["gpt", "gpt-3.5-turbo", "Q&A", "Sudden geological disasters in Huoshan County are mainly collapses, landslides, and debris flows. A total of 190 sudden geological disaster points (including hidden danger points) have been identified, including 74 collapses, 96 landslides, 14 debris flows, and 6 unstable slopes. There are 58 newly discovered geological disaster points, accounting for 30.5% of the total.", "How many sudden geological disaster points are there in Huoshan County in total?"],
-                            ["claude", "claude-3-5-haiku-20241022", "Q&A", "Sudden geological disasters in Huoshan County are mainly collapses, landslides, and debris flows. A total of 190 sudden geological disaster points (including hidden danger points) have been identified, including 74 collapses, 96 landslides, 14 debris flows, and 6 unstable slopes.", "Among the geological disasters in Huoshan County, which type of disaster has the largest number?"],
+                            ["gpt", "gpt-3.5-turbo", "Factoid QA", "Sudden geological disasters in Huoshan County are mainly collapses, landslides, and debris flows. A total of 190 sudden geological disaster points (including hidden danger points) have been identified, including 74 collapses, 96 landslides, 14 debris flows, and 6 unstable slopes. There are 58 newly discovered geological disaster points, accounting for 30.5% of the total.", "How many sudden geological disaster points are there in Huoshan County in total?"],
+                            ["claude", "claude-3-5-haiku-20241022", "Factoid QA", "Sudden geological disasters in Huoshan County are mainly collapses, landslides, and debris flows. A total of 190 sudden geological disaster points (including hidden danger points) have been identified, including 74 collapses, 96 landslides, 14 debris flows, and 6 unstable slopes.", "Among the geological disasters in Huoshan County, which type of disaster has the largest number?"],
                         ],
                         inputs=[qa_model_series, qa_model_name, qa_type, geological_text, question_or_statement]
                     )
                 
                 # QA event handling
-                def submit_qa_request(series, name, custom_name, q_type, template, prompt, geo_text, question):
-                    # Use custom model name if provided
-                    final_model_name = custom_name.strip() if custom_name.strip() else name
-                    return call_qa_model(series, final_model_name, prompt, geo_text, question, q_type)
+                def submit_qa_request(series, name, q_type, template, prompt, geo_text, question):
+                    # Use the selected model name directly (no custom name override)
+                    return call_qa_model(series, name, prompt, geo_text, question, q_type)
                 
                 def update_qa_prompt_on_type_change(qa_type_value):
                     """Update prompt template options and content when QA type changes"""
-                    if qa_type_value == "True/False":
-                        new_choices = ["Custom", "Zero-shot True/False", "COT True/False"]
-                        new_value = "Zero-shot True/False"
+                    if qa_type_value == "Yes/No QA":
+                        new_choices = ["Custom", "Yes/No QA", "CoT prompting of Yes/No QA"]
+                        new_value = "Yes/No QA"
                         new_prompt = "Please judge true or false based on the given text."
                         new_placeholder = "Please input statement to judge..."
                         new_label = "Statement"
-                    else:  # Q&A
-                        new_choices = ["Custom", "Zero-shot Q&A", "COT Q&A"]
-                        new_value = "Zero-shot Q&A"
+                    else:  # Factoid QA
+                        new_choices = ["Custom", "Factoid QA", "CoT prompting of Factoid QA"]
+                        new_value = "Factoid QA"
                         new_prompt = "Please answer the question based on the given text."
                         new_placeholder = "Please input question to answer..."
                         new_label = "Question"
                     
                     return (
                         gr.Dropdown(choices=new_choices, value=new_value, label="Select QA Prompt Template"),
-                        gr.Textbox(value=new_prompt, label="QA Prompt Content", lines=3, max_lines=10),
+                        gr.Textbox(value=new_prompt, label="QA Prompt ", lines=3, max_lines=10),
                         gr.Textbox(label=new_label, placeholder=new_placeholder, lines=3, max_lines=8)
                     )
                 
@@ -546,7 +692,7 @@ def create_interface():
                     outputs=[qa_model_name]
                 )
                 
-                # Update QA prompt content
+                # Update QA Prompt 
                 qa_prompt_template.change(
                     fn=update_qa_prompt_content,
                     inputs=[qa_prompt_template],
@@ -563,7 +709,7 @@ def create_interface():
                 # QA submit button event
                 qa_submit_btn.click(
                     fn=submit_qa_request,
-                    inputs=[qa_model_series, qa_model_name, qa_custom_model_name, qa_type, qa_prompt_template, qa_prompt_content, geological_text, question_or_statement],
+                    inputs=[qa_model_series, qa_model_name, qa_type, qa_prompt_template, qa_prompt_content, geological_text, question_or_statement],
                     outputs=[qa_output]
                 )
                 
@@ -573,16 +719,15 @@ def create_interface():
                     outputs=[geological_text, question_or_statement, qa_output]
                 )
                 
-                # QA enter key submission
+                # QA回车键提交
                 question_or_statement.submit(
                     fn=submit_qa_request,
-                    inputs=[qa_model_series, qa_model_name, qa_custom_model_name, qa_type, qa_prompt_template, qa_prompt_content, geological_text, question_or_statement],
+                    inputs=[qa_model_series, qa_model_name, qa_type, qa_prompt_template, qa_prompt_content, geological_text, question_or_statement],
                     outputs=[qa_output]
                 )
     
     return demo
 
-
 if __name__ == "__main__":
     # Launch interface with password protection
     demo = create_interface()
@@ -590,6 +735,6 @@ if __name__ == "__main__":
         server_port=7860,
         share=True,
         debug=True,
-        auth=("geollm", "research2025"), 
-        auth_message="Please enter credentials to access GeoLLM Geological Intelligence Platform"
+        # auth=("geollm", "research2025"), 
+        # auth_message="Please enter credentials to access GeoLLM Geological Intelligence Platform"
     )