ai_chatbot 0.1.6.5.1 → 0.1.6.5.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: fee6347bdac6070db1bfbc1711f039103c1237c149f42a7f0b848b85eba98314
-  data.tar.gz: c54c29b235f159921d4b33ac36bc56d505983eb03a25500829d72e9741628983
+  metadata.gz: 751a6f2a9c762af2c03f9f14842ccafaefee38e2d0d2e9fb7f6595cfd1fc9a6c
+  data.tar.gz: 5030f83ae39a359a498bbbb2956bb5cffb79e7071b9b22c9f87c3bf67775a2dd
 SHA512:
-  metadata.gz: f80cec458575b77b6be9879007e3f60830886b88bcfbde28974e9fe1e68b59d61424956a0aea0db62e69e5705e2c8d2b2b97d3e6700ee3b9cdd141530816325f
-  data.tar.gz: d2ac4f47ef9ce02255a60e84a6bff019c9036be5368f79e43748ca945a459c4459c5b53ee7a57a8345114018e03d0f5a1eeab70895ac78bafefed6980223dc59
+  metadata.gz: ba1346f5b15c8c08af48bfcd72490c060c34acb07112a63f6c2cc5589574195bc5dcf0b83c5471ef8d149a26b42a3ffbf7e6838aa3b28a42a12684bf4946fe5f
+  data.tar.gz: e652e1c7aa1cc2d80550832892b62a3d7018a13684f9c734f75b9ef73947c56e711569e3c99176dd71f3d65965ff10cd801d92b5c62010dfc8547279987b58b8

data/lib/ai_chatbot/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module AiChatbot
-  VERSION = "0.1.6.5.1"
+  VERSION = "0.1.6.5.2"
 end

data/lib/ml_model.py

@@ -1,142 +1,125 @@
 import sys
-import psycopg2
+import pickle
 import os
-from dotenv import load_dotenv
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.naive_bayes import MultinomialNB
 from sklearn.pipeline import make_pipeline
 from sklearn.metrics.pairwise import cosine_similarity
 
-# Load environment variables
-load_dotenv()
-
-# Connect to PostgreSQL
-conn = psycopg2.connect(
-    dbname=os.getenv("DB_NAME"),
-    user=os.getenv("DB_USERNAME"),
-    password=os.getenv("DB_PASSWORD"),
-    host=os.getenv("DB_HOST"), 
-    port=os.getenv("DB_PORT"),
-)
-cursor = conn.cursor()
-
-# Fetch data from DB
-cursor.execute("SELECT question, answer FROM qa_data")
-rows = cursor.fetchall()
-questions = [row[0] for row in rows]
-answers = [row[1] for row in rows]
-
-# Define the vectorizer and Naive Bayes model
-vectorizer = TfidfVectorizer()
-model = MultinomialNB()
-pipeline = make_pipeline(vectorizer, model)
-
-# Train model if there is data
-if questions:
-    pipeline.fit(questions, answers)
+DATA_FILE = "qa_model.pkl"
 
+# Globals
+questions = []
+answers = []
+model = make_pipeline(TfidfVectorizer(), MultinomialNB())
 
+# ------------------- Load or Initialize ------------------- #
+def load_data():
+    global questions, answers
+    if os.path.exists(DATA_FILE):
+        with open(DATA_FILE, "rb") as f:
+            model_data = pickle.load(f)
+            questions = model_data.get('questions', [])
+            answers = model_data.get('answers', [])
+            print(f"Loaded {len(questions)} Q&A pairs.")
+    else:
+        # Default seed data
+        questions.extend([
+            "How to create a new model in Rails?",
+            "What is migration?",
+            "How to add a route?"
+        ])
+        answers.extend([
+            "You can create a model using 'rails generate model'.",
+            "Migration is a database schema change.",
+            "You can add a route in the config/routes.rb file."
+        ])
+        print("No existing model found, using default seed data.")
+
+    retrain_model()
+
+def save_data():
+    with open(DATA_FILE, "wb") as f:
+        pickle.dump({'questions': questions, 'answers': answers}, f)
+
+def retrain_model():
+    if questions and answers:
+        model.fit(questions, answers)
+
+# ------------------- Core Actions ------------------- #
 def get_prediction(query):
-    if not questions:
-        return "No questions available in the database."
-    
-    query_vec = vectorizer.transform([query])
-    similarities = cosine_similarity(query_vec, vectorizer.transform(questions)).flatten()
+    query_vec = model.named_steps['tfidfvectorizer'].transform([query])
+    question_vecs = model.named_steps['tfidfvectorizer'].transform(questions)
+    similarities = cosine_similarity(query_vec, question_vecs)
+    max_similarity = similarities.max()
 
-    max_sim_index = similarities.argmax()
-    max_similarity = similarities[max_sim_index]
+    print(f"🔍 Similarity Score: {max_similarity:.2f}")
 
     threshold = 0.65
     if max_similarity < threshold:
-        return "No good match found. Please provide the correct answer."
+        return "No good match found. You may need to train the model with this question."
     else:
-        return answers[max_sim_index]
+        prediction = model.predict([query])
+        return prediction[0]
 
-
-# Function to train the model with new data
 def train_model(new_question, new_answer):
-    global questions, answers
-
-    # Store in database
-    cursor.execute(
-        "INSERT INTO qa_data (question, answer, created_at, updated_at) VALUES (%s, %s, NOW(), NOW()) ON CONFLICT (question) DO NOTHING",
-        (new_question, new_answer),
-    )
-    conn.commit()
-
-    # Update lists and retrain model
     questions.append(new_question)
     answers.append(new_answer)
-    pipeline.fit(questions, answers)  # Retrain model
-
-    return f"Added: '{new_question}' -> '{new_answer}'"
-
+    retrain_model()
+    save_data()
+    return f"Model updated with: '{new_question}'"
 
-# Function to update an answer
 def update_answer(existing_question, new_answer):
-    if existing_question not in questions:
-        return f"Question '{existing_question}' not found."
-
-    cursor.execute(
-        "UPDATE qa_data SET answer = %s WHERE question = %s", (new_answer, existing_question)
-    )
-    conn.commit()
-
-    # Update lists and retrain model
-    index = questions.index(existing_question)
-    answers[index] = new_answer
-    pipeline.fit(questions, answers)
-
-    return f"Updated: '{existing_question}' -> '{new_answer}'"
+    if existing_question in questions:
+        idx = questions.index(existing_question)
+        answers[idx] = new_answer
+        retrain_model()
+        save_data()
+        return f"Answer updated for: '{existing_question}'"
+    return "Question not found."
+
+def update_or_delete_question(existing_question, new_question=None):
+    if existing_question in questions:
+        idx = questions.index(existing_question)
+        if new_question:
+            questions[idx] = new_question
+            action = f"Question updated to: '{new_question}'"
+        else:
+            questions.pop(idx)
+            answers.pop(idx)
+            action = f"🗑️ Question '{existing_question}' deleted."
+        retrain_model()
+        save_data()
+        return action
+    return "Question not found."
 
-
-# Function to delete a question
-def delete_question(existing_question):
-    if existing_question not in questions:
-        return f"Question '{existing_question}' not found."
-
-    cursor.execute("DELETE FROM qa_data WHERE question = %s", (existing_question,))
-    conn.commit()
-
-    index = questions.index(existing_question)
-    del questions[index]
-    del answers[index]
-    pipeline.fit(questions, answers)
-
-    return f"Deleted: '{existing_question}'"
-
-
-# Function to list questions
 def list_questions():
-    cursor.execute("SELECT question FROM qa_data")
-    return [row[0] for row in cursor.fetchall()]
+    return "\n".join([f"{i+1}. {q}" for i, q in enumerate(questions)])
 
-
-# Function to list answers
 def list_answers():
-    cursor.execute("SELECT answer FROM qa_data")
-    return [row[0] for row in cursor.fetchall()]
+    return "\n".join([f"{i+1}. {a}" for i, a in enumerate(answers)])
 
-
-# Command-line execution
-if __name__ == "__main__":
-    action = sys.argv[1]
-    question = sys.argv[2] if len(sys.argv) > 2 else None
-    answer = sys.argv[3] if len(sys.argv) > 3 else None
+# ------------------- CLI Entry ------------------- #
+def main(action, query=None, answer=None):
+    load_data()
 
     if action == "predict":
-        print(get_prediction(question))
+        return get_prediction(query)
     elif action == "train_model":
-        print(train_model(question, answer))
+        return train_model(query, answer)
     elif action == "update_answer":
-        print(update_answer(question, answer))
-    elif action == "delete_question":
-        print(delete_question(question))
+        return update_answer(query, answer)
+    elif action == "update_or_delete_question":
+        return update_or_delete_question(query, answer)
     elif action == "list_questions":
-        print(list_questions())
+        return list_questions()
     elif action == "list_answers":
-        print(list_answers())
+        return list_answers()
+    else:
+        return "Unknown action. Try: predict, train_model, update_answer, list_questions, list_answers"
 
-# Close DB connection
-cursor.close()
-conn.close()
+if __name__ == "__main__":
+    action = sys.argv[1] if len(sys.argv) > 1 else None
+    question = sys.argv[2] if len(sys.argv) > 2 else None
+    answer = sys.argv[3] if len(sys.argv) > 3 else None
+    print(main(action, question, answer))

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: ai_chatbot
 version: !ruby/object:Gem::Version
-  version: 0.1.6.5.1
+  version: 0.1.6.5.2
 platform: ruby
 authors:
 - Sanket
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2025-03-05 00:00:00.000000000 Z
+date: 2025-06-13 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: open3
@@ -24,8 +24,7 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-description: Added PostgreSQL support, fixed model error. Version 0.1.6.5.1 Details
-  on Git.
+description: fixed model error. Version 0.1.6.5.1 Details on Git.
 email:
 - sanket.tikhande@gmail.com
 executables: []
@@ -58,5 +57,5 @@ requirements: []
 rubygems_version: 3.3.7
 signing_key: 
 specification_version: 4
-summary: 'Fix: Added postgres integration'
+summary: 'Fix: Added high accuracy'
 test_files: []