ai_chatbot 0.1.6.5 → 0.1.6.5.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 65a8e9d42a6f0a36cff9a13f7428975232912b4a2decd9509772b38d849f6340
-  data.tar.gz: f54c3642f29fb1f12f49af978f4ae34bd9dcdb85c7d22b48d07b195384354832
+  metadata.gz: fee6347bdac6070db1bfbc1711f039103c1237c149f42a7f0b848b85eba98314
+  data.tar.gz: c54c29b235f159921d4b33ac36bc56d505983eb03a25500829d72e9741628983
 SHA512:
-  metadata.gz: 6a7d4c388b24487a16a51dac935eb54d6dfc384f8d478dd80667f5de9a3dc2d8140e2785a0721db5d93f79b29285ad5deb3462042238536925c5b8e66b481939
-  data.tar.gz: e691cb235c3cae3c9b754c30a20cec05ca17bc684e0e7c727528ccf0b8f06e4a100e4473d050793a62029bf3352425f1b1c00540e709f04f868366bb2a0f5559
+  metadata.gz: f80cec458575b77b6be9879007e3f60830886b88bcfbde28974e9fe1e68b59d61424956a0aea0db62e69e5705e2c8d2b2b97d3e6700ee3b9cdd141530816325f
+  data.tar.gz: d2ac4f47ef9ce02255a60e84a6bff019c9036be5368f79e43748ca945a459c4459c5b53ee7a57a8345114018e03d0f5a1eeab70895ac78bafefed6980223dc59

data/lib/ai_chatbot/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module AiChatbot
-  VERSION = "0.1.6.5"
+  VERSION = "0.1.6.5.1"
 end

data/lib/ml_model.py

@@ -7,9 +7,12 @@ 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"),
+    dbname=os.getenv("DB_NAME"),
     user=os.getenv("DB_USERNAME"),
     password=os.getenv("DB_PASSWORD"),
     host=os.getenv("DB_HOST"), 
@@ -17,15 +20,20 @@ conn = psycopg2.connect(
 )
 cursor = conn.cursor()
 
-db_name = os.getenv("DB_NAME")
-
+# 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()
-question_vecs = vectorizer.fit_transform(questions) if questions else None
+model = MultinomialNB()
+pipeline = make_pipeline(vectorizer, model)
+
+# Train model if there is data
+if questions:
+    pipeline.fit(questions, answers)
 
 
 def get_prediction(query):
@@ -33,7 +41,7 @@ def get_prediction(query):
         return "No questions available in the database."
     
     query_vec = vectorizer.transform([query])
-    similarities = cosine_similarity(query_vec, question_vecs).flatten()
+    similarities = cosine_similarity(query_vec, vectorizer.transform(questions)).flatten()
 
     max_sim_index = similarities.argmax()
     max_similarity = similarities[max_sim_index]
@@ -44,58 +52,73 @@ def get_prediction(query):
     else:
         return answers[max_sim_index]
 
+
 # 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))
+    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)
-    model.fit(questions, answers)
+    pipeline.fit(questions, answers)  # Retrain model
 
     return f"Added: '{new_question}' -> '{new_answer}'"
 
+
 # Function to update an answer
 def update_answer(existing_question, new_answer):
-    cursor.execute("UPDATE qa_data SET answer = %s WHERE question = %s", (new_answer, existing_question))
+    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
-    model.fit(questions, answers)
+    pipeline.fit(questions, answers)
 
     return f"Updated: '{existing_question}' -> '{new_answer}'"
 
+
 # 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()
 
-    if existing_question in questions:
-        index = questions.index(existing_question)
-        del questions[index]
-        del answers[index]
-        model.fit(questions, answers)
+    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()]
 
+
 # Function to list answers
 def list_answers():
     cursor.execute("SELECT answer FROM qa_data")
     return [row[0] for row in cursor.fetchall()]
 
+
+# Command-line execution
 if __name__ == "__main__":
     action = sys.argv[1]
     question = sys.argv[2] if len(sys.argv) > 2 else None
@@ -116,4 +139,4 @@ if __name__ == "__main__":
 
 # Close DB connection
 cursor.close()
-conn.close()
+conn.close()

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: ai_chatbot
 version: !ruby/object:Gem::Version
-  version: 0.1.6.5
+  version: 0.1.6.5.1
 platform: ruby
 authors:
 - Sanket
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2025-03-04 00:00:00.000000000 Z
+date: 2025-03-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: open3
@@ -24,8 +24,8 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-description: Added caching to avoid redundant DB queries, improving chatbot response
-  time. Also updated unanswered question logging.
+description: Added PostgreSQL support, fixed model error. Version 0.1.6.5.1 Details
+  on Git.
 email:
 - sanket.tikhande@gmail.com
 executables: []