Upload 3 files

app.py

@@ -0,0 +1,65 @@
+# Import statements
+from langchain.chat_models import ChatOpenAI
+from langchain.chains import ConversationChain
+from langchain.chains.conversation.memory import ConversationBufferWindowMemory
+from langchain.prompts import (
+    SystemMessagePromptTemplate,
+    HumanMessagePromptTemplate,
+    ChatPromptTemplate,
+    MessagesPlaceholder
+)
+import streamlit as st
+from streamlit_chat import message
+from utils import *
+
+# Streamlit setup
+st.subheader("Legal Guardian")
+
+# Session state initialization
+if 'responses' not in st.session_state:
+    st.session_state['responses'] = ["How can I assist you?"]
+
+if 'requests' not in st.session_state:
+    st.session_state['requests'] = []
+
+if 'buffer_memory' not in st.session_state:
+    st.session_state.buffer_memory = ConversationBufferWindowMemory(k=3, return_messages=True)
+
+# Initialize ChatOpenAI and conversation
+llm = ChatOpenAI(model_name="gpt-3.5-turbo", openai_api_key="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")
+
+system_msg_template = SystemMessagePromptTemplate.from_template("""
+    Legal Guardian' is a GPT designed to assist with a broad range of legal questions related to children's issues, focusing on laws in India...
+    ...It asks for clarification on vague questions to ensure accurate and relevant responses, and treats each query independently for focused assistance.'
+""")
+
+human_msg_template = HumanMessagePromptTemplate.from_template("{input}")
+prompt_template = ChatPromptTemplate.from_messages([system_msg_template, MessagesPlaceholder(variable_name="history"), human_msg_template])
+conversation = ConversationChain(memory=st.session_state.buffer_memory, prompt=prompt_template, llm=llm, verbose=True)
+
+# Streamlit UI components
+response_container = st.container()
+textcontainer = st.container()
+
+# Handle user input and display conversation
+with textcontainer:
+    query = st.text_input("Query: ", key="input")
+    if st.button("Submit"):
+        with st.spinner("typing..."):
+            conversation_string = get_conversation_string()
+            refined_query = query_refiner(conversation_string, query)
+            st.subheader("Refined Query:")
+            st.write(refined_query)
+            context = find_match(refined_query)
+            response = conversation.predict(input=f"Context:\n {context} \n\n Query:\n{query}")
+        st.session_state.requests.append(query)
+        st.session_state.responses.append(response)
+
+# Display conversation history
+with response_container:
+    if st.session_state['responses']:
+        st.subheader("Chat History:")
+        for i in range(len(st.session_state['responses'])):
+            message(st.session_state['responses'][i], key=str(i))
+            if i < len(st.session_state['requests']):
+                message(st.session_state["requests"][i], is_user=True, key=str(i) + '_user')

requirements.txt

@@ -0,0 +1,107 @@
+aiohttp==3.8.6
+aiosignal==1.3.1
+altair==5.1.2
+annotated-types==0.6.0
+anyio==3.7.1
+async-timeout==4.0.3
+attrs==23.1.0
+blinker==1.6.3
+cachetools==5.3.2
+certifi==2023.7.22
+charset-normalizer==3.3.1
+click==8.1.7
+dataclasses-json==0.6.1
+dnspython==2.4.2
+exceptiongroup==1.1.3
+filelock==3.13.0
+frozenlist==1.4.0
+fsspec==2023.10.0
+gitdb==4.0.11
+GitPython==3.1.40
+greenlet==3.0.1
+huggingface-hub==0.17.3
+idna==3.4
+importlib-metadata==6.8.0
+Jinja2==3.1.2
+joblib==1.3.2
+jsonpatch==1.33
+jsonpointer==2.4
+jsonschema==4.19.1
+jsonschema-specifications==2023.7.1
+langchain==0.0.325
+langsmith==0.0.53
+loguru==0.7.2
+markdown-it-py==3.0.0
+MarkupSafe==2.1.3
+marshmallow==3.20.1
+mdurl==0.1.2
+mpmath==1.3.0
+multidict==6.0.4
+mypy-extensions==1.0.0
+networkx==3.2.1
+nltk==3.8.1
+numpy==1.26.1
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==8.9.2.26
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-nccl-cu12==2.18.1
+nvidia-nvjitlink-cu12==12.3.52
+nvidia-nvtx-cu12==12.1.105
+openai==0.28.1
+packaging==23.2
+pandas==2.1.2
+Pillow==10.1.0
+pinecone-client==2.2.4
+protobuf==4.24.4
+pyarrow==13.0.0
+pydantic==2.4.2
+pydantic_core==2.10.1
+pydeck==0.8.1b0
+Pygments==2.16.1
+python-dateutil==2.8.2
+python-dotenv==1.0.0
+pytz==2023.3.post1
+PyYAML==6.0.1
+referencing==0.30.2
+regex==2023.10.3
+requests==2.31.0
+rich==13.6.0
+rpds-py==0.10.6
+safetensors==0.4.0
+scikit-learn==1.3.2
+scipy==1.11.3
+sentence-transformers==2.2.2
+sentencepiece==0.1.99
+six==1.16.0
+smmap==5.0.1
+sniffio==1.3.0
+SQLAlchemy==2.0.22
+streamlit==1.28.0
+streamlit-chat==0.1.1
+sympy==1.12
+tenacity==8.2.3
+threadpoolctl==3.2.0
+tokenizers==0.14.1
+toml==0.10.2
+toolz==0.12.0
+torch==2.1.0
+torchvision==0.16.0
+tornado==6.3.3
+tqdm==4.66.1
+transformers==4.34.1
+triton==2.1.0
+typing-inspect==0.9.0
+typing_extensions==4.8.0
+tzdata==2023.3
+tzlocal==5.2
+urllib3==2.0.7
+validators==0.22.0
+watchdog==3.0.0
+yarl==1.9.2
+zipp==3.17.0

utils.py

@@ -0,0 +1,96 @@
+from sentence_transformers import SentenceTransformer
+import pinecone
+import openai
+import streamlit as st
+from indic_transliteration import sanscript
+from indic_transliteration.sanscript import transliterate
+
+# Set OpenAI API key
+openai.api_key = "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"
+
+# Initialize SentenceTransformer model
+model = SentenceTransformer('all-MiniLM-L6-v2')
+
+# Initialize Pinecone index
+pinecone.init(api_key='14b2909a-c00c-4ff8-9b79-87eb51b9d891', environment='gcp-starter')
+index = pinecone.Index('langchain-chatbot')
+
+# Function to find the most relevant match in Pinecone index
+def find_match(input):
+    input_em = model.encode(input).tolist()
+    result = index.query(input_em, top_k=2, includeMetadata=True)
+    return result['matches'][0]['metadata']['text'] + "\n" + result['matches'][1]['metadata']['text']
+
+# Function to refine a user query using OpenAI's Completion API
+def query_refiner(conversation, query):
+    response = openai.Completion.create(
+        model="text-davinci-003",
+        prompt=f"Given the following user query and conversation log, formulate a question that would be the most relevant to provide the user with an answer from a knowledge base.\n\nCONVERSATION LOG: \n{conversation}\n\nQuery: {query}\n\nRefined Query:",
+        temperature=0.7,
+        max_tokens=256,
+        top_p=1,
+        frequency_penalty=0,
+        presence_penalty=0
+    )
+    return response['choices'][0]['text']
+
+# Function to get the conversation string for display
+def get_conversation_string():
+    conversation_string = ""
+    for i in range(len(st.session_state['responses']) - 1):
+        conversation_string += "Human: " + st.session_state['requests'][i] + "\n"
+        conversation_string += "Bot: " + st.session_state['responses'][i + 1] + "\n"
+    return conversation_string
+
+def transliterate_tamil_to_english(text):
+    return transliterate(text, sanscript.TAMIL, sanscript.ITRANS)
+
+# Function to find the most relevant match in Pinecone index
+def find_match(input):
+    input_em = model.encode(input).tolist()
+    result = index.query(input_em, top_k=2, includeMetadata=True)
+    return result['matches'][0]['metadata']['text'] + "\n" + result['matches'][1]['metadata']['text']
+
+# ... (your existing functions)
+
+# Streamlit app
+def main():
+    st.title("LangChain Chatbot")
+
+    # User input for the conversation in Tamil
+    user_input_tamil = st.text_input("User Input (Tamil):", "")
+
+    # Transliterate Tamil input to English for processing
+    user_input_english = transliterate_tamil_to_english(user_input_tamil)
+
+    # Retrieve refined query using OpenAI
+    refined_query = query_refiner(get_conversation_string(), user_input_english)
+
+    # Find the most relevant match using Sentence Transformers and Pinecone
+    match_result = find_match(refined_query)
+
+    # Display results
+    st.text("User Input (Tamil): " + user_input_tamil)
+    st.text("User Input (English): " + user_input_english)
+    st.text("Refined Query: " + refined_query)
+    st.text("Top Matches:")
+    st.text(match_result)
+    st.title("LangChain Chatbot")
+
+    # User input for the conversation
+    user_input = st.text_input("User Input:", "")
+
+    # Retrieve refined query using OpenAI
+    refined_query = query_refiner(get_conversation_string(), user_input)
+
+    # Find the most relevant match using Sentence Transformers and Pinecone
+    match_result = find_match(refined_query)
+
+    # Display results
+    st.text("Refined Query: " + refined_query)
+    st.text("Top Matches:")
+    st.text(match_result)
+
+# Run the Streamlit app
+if __name__ == "__main__":
+    main()