0.1

app.py

@@ -0,0 +1,109 @@
+import os
+import tempfile
+import time
+
+import streamlit as st
+from dotenv import load_dotenv
+from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
+from langchain.chat_models import ChatOpenAI
+from langchain.prompts import PromptTemplate
+from langchain.schema import StrOutputParser
+from langchain.vectorstores import Vectara
+
+# Load environment variables from .env file
+load_dotenv()
+
+# Sidebar for PDF upload and API keys
+with st.sidebar:
+    st.header("Configuration")
+    uploaded_file = st.file_uploader("Choose a PDF file", type=["pdf"])
+    customer_id = st.text_input("Vectara Customer ID", value=os.getenv("CUSTOMER_ID", ""))
+    api_key = st.text_input("Vectara API Key", value=os.getenv("API_KEY", ""))
+    corpus_id = st.text_input("Vectara Corpus ID", value=str(os.getenv("CORPUS_ID", "")))
+    openai_api_key = st.text_input("OpenAI API Key", value=os.getenv("OPENAI_API_KEY", ""))
+    submit_button = st.button("Submit")
+
+# Constants
+CUSTOMER_ID = customer_id if customer_id else os.getenv("CUSTOMER_ID")
+API_KEY = api_key if api_key else os.getenv("API_KEY")
+CORPUS_ID = int(corpus_id) if corpus_id else int(os.getenv("CORPUS_ID", 0))  # Assuming CORPUS_ID should be an integer
+OPENAI_API_KEY = openai_api_key if openai_api_key else os.getenv("OPENAI_API_KEY")
+
+# Initialize Vectara
+def initialize_vectara():
+    vectara = Vectara(
+        vectara_customer_id=CUSTOMER_ID,
+        vectara_corpus_id=CORPUS_ID,
+        vectara_api_key=API_KEY
+    )
+    return vectara
+
+vectara_client = initialize_vectara()
+
+# Function to get knowledge content from Vectara
+def get_knowledge_content(vectara, query, threshold=0.5):
+    found_docs = vectara.similarity_search_with_score(
+        query,
+        score_threshold=threshold,
+    )
+    knowledge_content = ""
+    for number, (score, doc) in enumerate(found_docs):
+        knowledge_content += f"Document {number}: {found_docs[number][0].page_content}\n"
+    return knowledge_content
+
+# Prompt and response setup
+prompt = PromptTemplate.from_template(
+    """You are a professional and friendly Legal Consultant and you are helping a client with a legal issue. The client is asking you for advice on a legal issue. Just explain him in detail the answer and nothing else. This is the issue: {issue} 
+    To assist him with his issue, you need to know the following information: {knowledge} 
+    """
+)
+runnable = prompt | ChatOpenAI(streaming=True, callbacks=[StreamingStdOutCallbackHandler()], openai_api_key=OPENAI_API_KEY) | StrOutputParser()
+
+# Main Streamlit App
+st.title("Legal Consultation Chat")
+
+# Initialize chat history
+if "messages" not in st.session_state:
+    st.session_state.messages = []
+
+# Display chat messages from history on app rerun
+for message in st.session_state.messages:
+    with st.chat_message(message["role"]):
+        st.markdown(message["content"])
+
+# Accept user input and run the main chat interaction
+if user_input := st.chat_input("Enter your issue:"):
+    st.session_state.messages.append({"role": "user", "content": user_input})
+    with st.chat_message("user"):
+        st.markdown(user_input)
+
+    knowledge_content = get_knowledge_content(vectara_client, user_input)
+    print("__________________ Start of knowledge content __________________")
+    print(knowledge_content)
+    response = runnable.invoke({"knowledge": knowledge_content, "issue": user_input})
+
+    response_words = response.split()
+    with st.chat_message("assistant"):
+        message_placeholder = st.empty()
+        full_response = ""
+        for word in response_words:
+            full_response += word + " "
+            time.sleep(0.05)
+            message_placeholder.markdown(full_response + "▌")
+        message_placeholder.markdown(full_response)
+
+    st.session_state.messages.append({"role": "assistant", "content": full_response})
+
+# Run when the submit button is pressed
+if submit_button and uploaded_file:
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmpfile:
+        tmpfile.write(uploaded_file.getvalue())
+        tmp_filename = tmpfile.name
+
+    try:
+        vectara_client.add_files([tmp_filename])
+        st.sidebar.success("PDF file successfully uploaded to Vectara!")
+    except Exception as e:
+        st.sidebar.error(f"An error occurred: {str(e)}")
+    finally:
+        os.remove(tmp_filename)  # Clean up temporary file

requirements.txt

@@ -0,0 +1,113 @@
+aiohttp==3.8.6
+aiosignal==1.3.1
+altair==5.1.2
+annotated-types==0.6.0
+anyio==3.7.1
+appnope==0.1.3
+asttokens==2.4.1
+async-timeout==4.0.3
+attrs==23.1.0
+backoff==2.2.1
+beautifulsoup4==4.12.2
+blinker==1.7.0
+cachetools==5.3.2
+certifi==2023.7.22
+chardet==5.2.0
+charset-normalizer==3.3.2
+click==8.1.7
+comm==0.1.4
+dataclasses-json==0.6.1
+debugpy==1.8.0
+decorator==5.1.1
+emoji==2.8.0
+exceptiongroup==1.1.3
+executing==2.0.1
+filetype==1.2.0
+frozenlist==1.4.0
+gitdb==4.0.11
+GitPython==3.1.40
+idna==3.4
+importlib-metadata==6.8.0
+ipykernel==6.26.0
+ipython==8.17.2
+jedi==0.19.1
+Jinja2==3.1.2
+joblib==1.3.2
+jq==1.6.0
+jsonpatch==1.33
+jsonpointer==2.4
+jsonschema==4.19.2
+jsonschema-specifications==2023.7.1
+jupyter_client==8.5.0
+jupyter_core==5.5.0
+langchain==0.0.327
+langdetect==1.0.9
+langsmith==0.0.56
+lxml==4.9.3
+markdown-it-py==3.0.0
+MarkupSafe==2.1.3
+marshmallow==3.20.1
+matplotlib-inline==0.1.6
+mdurl==0.1.2
+multidict==6.0.4
+mypy-extensions==1.0.0
+nest-asyncio==1.5.8
+nltk==3.8.1
+numpy==1.26.1
+openai==0.28.1
+packaging==23.2
+pandas==2.1.2
+parso==0.8.3
+pexpect==4.8.0
+Pillow==10.1.0
+platformdirs==3.11.0
+prompt-toolkit==3.0.39
+protobuf==4.25.0
+psutil==5.9.6
+ptyprocess==0.7.0
+pure-eval==0.2.2
+pyarrow==14.0.0
+pydantic==2.4.2
+pydantic_core==2.10.1
+pydeck==0.8.1b0
+Pygments==2.16.1
+pypdf==3.17.0
+python-dateutil==2.8.2
+python-docx==1.0.1
+python-dotenv==1.0.0
+python-iso639==2023.6.15
+python-magic==0.4.27
+pytz==2023.3.post1
+PyYAML==6.0.1
+pyzmq==25.1.1
+rapidfuzz==3.5.1
+referencing==0.30.2
+regex==2023.10.3
+requests==2.31.0
+rich==13.6.0
+rpds-py==0.10.6
+six==1.16.0
+smmap==5.0.1
+sniffio==1.3.0
+soupsieve==2.5
+SQLAlchemy==2.0.22
+stack-data==0.6.3
+streamlit==1.28.0
+tabulate==0.9.0
+tenacity==8.2.3
+toml==0.10.2
+toolz==0.12.0
+tornado==6.3.3
+tqdm==4.66.1
+traitlets==5.13.0
+typing-inspect==0.9.0
+typing_extensions==4.8.0
+tzdata==2023.3
+tzlocal==5.2
+unstructured==0.10.28
+urllib3==2.0.7
+validators==0.22.0
+watchdog==3.0.0
+wcwidth==0.2.9
+yarl==1.9.2
+zipp==3.17.0