Update app.py

app.py

@@ -1,101 +1,73 @@
-import re
-import time
 import random
-import gradio as gr
+import re
 from huggingface_hub import InferenceClient
 
-# Optional: Enable scraping if your site is deployed.
-ENABLE_SCRAPING = False
-SITE_URL = "https://your-agri-future-site.com"
-
-# Global variable to hold scraped content
-knowledge_base = ""
-
-# --- Optional: Scraping Functionality ---
-if ENABLE_SCRAPING:
-    try:
-        from selenium import webdriver
-        from selenium.webdriver.chrome.options import Options
-        from selenium.webdriver.common.by import By
+# Initialize the InferenceClient with your Hugging Face API token
+client = InferenceClient(
+    model="HuggingFaceH4/zephyr-7b-beta",  # Specify your model here
+    token="your_huggingface_api_token"     # Replace with your actual token
+)
 
-        def scrape_site(url):
-            options = Options()
-            options.headless = True  # Run browser in headless mode.
-            driver = webdriver.Chrome(options=options)
-            driver.get(url)
-            # Use explicit waits in production; here we use a basic sleep.
-            time.sleep(5)
-            try:
-                # Customize the selector based on your site's HTML structure.
-                content_element = driver.find_element(By.ID, "content")
-                page_text = content_element.text
-            except Exception as e:
-                page_text = "Error encountered during scraping: " + str(e)
-            driver.quit()
-            return page_text
-
-        knowledge_base = scrape_site(SITE_URL)
-        print("Scraped knowledge base successfully.")
-    except Exception as e:
-        print("Scraping failed or Selenium is not configured:", e)
-else:
-    print("Scraping is disabled; proceeding without scraped site content.")
-
-# --- Multilingual Helpers ---
+# Multilingual greetings dictionary
+greetings = {
+    "en": ["hello", "hi", "hey", "good morning", "good afternoon", "good evening"],
+    "fr": ["bonjour", "salut", "coucou", "bonsoir"],
+    "am": ["ሰላም", "ሰላም እንደምን", "እንዴት"]
+}
 
 def is_greeting(query: str, lang: str) -> bool:
-    greetings = {
-        "en": ["hello", "hi", "hey", "good morning", "good afternoon", "good evening"],
-        "fr": ["bonjour", "salut", "coucou", "bonsoir"],
-        "am": ["ሰላም", "ሰላም እንደምን", "እንዴት"]
-    }
+    """
+    Check if the user's query is a greeting in the specified language.
+    """
     greet_list = greetings.get(lang, greetings["en"])
-    # For languages using Latin script, convert to lower case.
+    # Convert to lowercase for non-Amharic languages
     if lang != "am":
         query = query.lower()
     return any(query.startswith(greet) for greet in greet_list)
 
-# Rather than using fixed out-of-scope messages, use the model via Hugging Face to generate them.
 def generate_dynamic_out_of_scope_message(language: str) -> str:
-    # Define language-specific system prompts for generating a dynamic out-of-scope message.
+    """
+    Generate a dynamic out-of-scope message using the Hugging Face Inference API.
+    """
+    # Define language-specific system prompts
     system_prompts = {
         "en": (
             "You are a helpful chatbot specializing in agriculture and agro-investment. "
-            "A user just asked a question that is not related to these topics. "
-            "Generate a friendly, varied, and intelligent out-of-scope response in English that kindly encourages the user to ask about agriculture or agro-investment."
+            "A user has asked a question unrelated to these topics. "
+            "Generate a friendly and intelligent out-of-scope response in English, encouraging the user to ask about agriculture or agro-investment."
         ),
         "fr": (
             "Vous êtes un chatbot utile spécialisé dans l'agriculture et les investissements agroalimentaires. "
-            "Un utilisateur vient de poser une question qui ne concerne pas ces sujets. "
-            "Générez une réponse élégante, variée et intelligente en français pour indiquer que la question est hors de portée, en invitant l'utilisateur à poser une question sur l'agriculture ou les investissements agroalimentaires."
+            "Un utilisateur a posé une question sans rapport avec ces sujets. "
+            "Générez une réponse amicale et intelligente en français, encourageant l'utilisateur à poser des questions sur l'agriculture ou les investissements agroalimentaires."
         ),
         "am": (
-            "እርስዎ በግብርናና በአገልግሎት ስርዓተ-ቢዝነስ ውስጥ በተለይ የተሞሉ ቻትቦት ናቸው። "
-            "ተጠቃሚው ለግብርና ወይም ለአገልግሎት ስርዓተ-ቢዝነስ ተያይዞ ያልሆነ ጥያቄ አስቀድመዋል። "
-            "በአማርኛ በተለያዩ መልኩ የውጭ ክፍል መልእክት ፍጥረት ያድርጉ፤ እባኮትን ተጠቃሚውን ለግብርና ወይም ለአገልግሎት ጥያቄዎች ለመጠየቅ ያነጋግሩ።"
+            "እርስዎ በግብርናና በአገልግሎት ስርዓተ-ቢዝነስ ውስጥ የሚሰራ እገዛ የሚሰጥ ቻትቦት ነው። "
+            "ተጠቃሚው ከእነዚህ ጉዳዮች ውጪ ጥያቄ አቀርቧል። "
+            "በአማርኛ የተሰጠ የውጭ ክፍል ምላሽ ይፍጠሩ፣ ተጠቃሚውን ለግብርና ወይም ለአገልግሎት ስርዓተ-ቢዝነስ ጥያቄዎች ለመጠየቅ ያበረታታ።"
         )
     }
     prompt = system_prompts.get(language, system_prompts["en"])
     messages = [{"role": "system", "content": prompt}]
 
-    # Call the model without streaming to generate the complete message.
+    # Call the model to generate the response
     response = client.chat_completion(
         messages,
         max_tokens=80,
-        stream=False,
         temperature=0.7,
         top_p=0.95,
     )
-    # Depending on the client structure, adjust the extraction of the generated text.
+    # Extract the generated message content
     try:
         out_message = response.choices[0].message.content
     except AttributeError:
-        # If the response structure differs, do a fallback conversion.
         out_message = str(response)
     return out_message.strip()
 
-# A helper to determine domain relevance (basic implementation; can be expanded).
 def is_domain_query(query: str) -> bool:
+    """
+    Determine if the query is related to agriculture or agro-investment.
+    """
     domain_keywords = [
         "agriculture", "farming", "crop", "agro", "investment", "soil",
         "irrigation", "harvest", "organic", "sustainable", "agribusiness",
@@ -103,6 +75,19 @@ def is_domain_query(query: str) -> bool:
     ]
     return any(re.search(r"\b" + keyword + r"\b", query, re.IGNORECASE) for keyword in domain_keywords)
 
-def retrieve_relevant_snippet(query: str, text: str, max_length: int = 300) -> str:
-    sentences = re.split(r'[.?!]', text)
-    for sentence in sentences
+def handle_user_query(query: str, lang: str = "en") -> str:
+    """
+    Process the user's query and provide an appropriate response.
+    """
+    if is_greeting(query, lang):
+        return random.choice(greetings.get(lang, greetings["en"])).capitalize() + "!"
+    elif is_domain_query(query):
+        # Here you would integrate your domain-specific response generation
+        return "This is a domain-specific question. Processing accordingly..."
+    else:
+        return generate_dynamic_out_of_scope_message(lang)
+
+# Example usage
+user_query = "Tell me about space travel."
+response = handle_user_query(user_query, lang="en")
+print(response)