Merge pull request #14 from hannguyen2880/develop

Complete homework module1/week4 (complete all weeks in module1)

.sonarlint/connectedMode.json

@@ -0,0 +1,4 @@
+{
+    "sonarCloudOrganization": "hannguyen2880",
+    "projectKey": "hannguyen2880_AIO-Exercise"
+}

.vscode/settings.json

@@ -0,0 +1,6 @@
+{
+    "sonarlint.connectedMode.project": {
+        "connectionId": "hannguyen2880",
+        "projectKey": "hannguyen2880_AIO-Exercise"
+    }
+}

Module1/Week4-Streamlit/chatbot.py

@@ -0,0 +1,49 @@
+import streamlit as st
+from hugchat import hugchat
+from hugchat.login import Login
+
+#Generating LLM response
+def generate_response(prompt_input, email, password):
+    sign = Login(email, password)
+    cookies = sign.login()
+    chatbot = hugchat.ChatBot(cookies=cookies.get_dict())
+    return chatbot.chat(prompt_input)
+
+# MAIN PROGRAM
+# ChatBot Title
+st.title('Simple ChatBot')
+with st.sidebar:
+    st.title('Login HugChat')
+    email = st.text_input('Enter email:')
+    password = st.text_input('Enter password:', type='password')
+    if email and password:
+        st.success('Proceed to entering your prompt message!')
+    else:
+        st.warning('Please enter your account!')
+
+# Store LLM generated responses and display first message
+if "messages" not in st.session_state.keys():
+    st.session_state.messages = [{"role": "assistant", "content": "How may I help you?"}]
+
+for message in st.session_state.messages:
+    with st.chat_message("assistant"):
+        st.write(message["content"])
+
+# User-provided prompt
+if prompt := st.chat_input(disabled=not (email and password)):
+    st.session_state.messages.append({"role": "user", "content": prompt})
+    with st.chat_message("user"):
+        st.write(prompt)
+
+# Generate other responses
+if st.session_state.messages[-1]["role"] != "assistant":
+    with st.chat_message("assistant"):
+        with st.spinner("Thinking..."):
+            response = generate_response(prompt, email, password)
+            st.write(response)
+    st.session_state.messages.append({"role": "assistant", "content": response})
+
+
+
+
+

Module1/Week4-Streamlit/levelshtein_distance.py

@@ -0,0 +1,53 @@
+import streamlit as st
+
+
+def levenshtein_distance(token1, token2):
+    dist = [[0] * (len(token2) + 1) for _ in range(len(token1) + 1)]
+    for i in range(len(token1) + 1):
+        dist[i][0] = i
+    for i in range(len(token2) + 1):
+        dist[0][i] = i
+
+    for i in range(1, len(token1) + 1):
+        for j in range(1, len(token2) + 1):
+            if (token1[i - 1] == token2[j - 1]):
+                dist[i][j] = dist[i - 1][j - 1]
+            else:
+                dist[i][j] = min([dist[i][j - 1], dist[i - 1]
+                                 [j], dist[i - 1][j - 1]]) + 1
+
+    return dist[len(token1)][len(token2)]
+
+
+def load_vocab_file(file_path):
+    with open(file_path, 'r') as f:
+        data = f.readlines()
+    vocab = sorted(set(line.strip().lower() for line in data))
+    return vocab
+
+
+def main():
+    vocabs = load_vocab_file(file_path='Module1/Week4-Streamlit/vocab.txt')
+    # print(vocabs)
+    st.title('Word Correction using Levenshtein Distance')
+    word = st.text_input('Word:')
+
+    if st.button('Compute'):
+        leven_dist = dict()
+
+        for vocab in vocabs:
+            leven_dist[vocab] = levenshtein_distance(word, vocab)
+
+        sorted_dists = dict(
+            sorted(leven_dist.items(), key=lambda item: item[1]))
+        correct_word = list(sorted_dists.keys())[0]
+        st.write('Correct Word: ', correct_word)
+        col1, col2 = st.columns(2)
+        col1.write('Vocabulary:')
+        col1.write(vocabs)
+        col2.write('Distances')
+        col2.write(sorted_dists)
+
+
+if __name__ == "__main__":
+    main()