feat: Add code for chatting with a website

.env.example

@@ -0,0 +1,3 @@
+OPENAI_API_KEY=your_api_key
+APIFY_API_TOKEN=your_api_key
+WEBSITE_URL="https://docs.apify.com/platform"

.gitignore

@@ -158,3 +158,6 @@ cython_debug/
 #  and can be added to the global gitignore or merged into this file.  For a more nuclear
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 #.idea/
+
+# Ignore the folder with the vector database's data
+db/

README.md

@@ -1,2 +1,25 @@
-# chat-with-a-website
-A simple app that lets you chat with a given website.
+# Chat with a website
+
+Chat with a website using Apify and ChatGPT.
+
+## Setup
+
+Before getting started, be sure to sign up for an [Apify](https://console.apify.com/sign-up) and [OpenAI](https://openai.com/) account and create API keys.
+
+To set up and run this project, follow these steps:
+
+1. Install the required packages with `pip`:
+   ```
+   pip install -r requirements.txt
+   ```
+2. Rename the `.env.example` file to `.env` and replace the variables. Here's an explanation of the variables in the .env file:
+
+`OPENAI_API_KEY`: Your OpenAI API key. You can obtain it from your OpenAI account dashboard.  
+`APIFY_API_TOKEN`: Your Apify API token. You can obtain it from [Apify settings](https://console.apify.com/account/integrations).  
+`WEBSITE_URL`: The full URL of the website you'd like to chat with.  
+
+3. Run the `scrape.py` script to scrape the website's data using Apify's [Website content crawler](https://apify.com/apify/website-content-crawler).
+4. Run the Streamlit chat app, which should default to `http://localhost:8501` and allow you to chat with the website:
+   ```
+   streamlit run chat.py
+   ```

chat.py

@@ -0,0 +1,61 @@
+import os
+
+import streamlit as st
+from dotenv import load_dotenv
+from langchain.callbacks.base import BaseCallbackHandler
+from langchain.chains import ConversationalRetrievalChain
+from langchain.chat_models import ChatOpenAI
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.memory import ConversationBufferMemory
+from langchain.memory.chat_message_histories import StreamlitChatMessageHistory
+from langchain.vectorstores import Chroma
+
+load_dotenv()
+
+website_url = os.environ.get('WEBSITE_URL', 'a website')
+
+st.set_page_config(page_title=f'Chat with {website_url}')
+st.title('Chat with a website')
+
+@st.cache_resource(ttl='1h')
+def get_retriever():
+    embeddings = OpenAIEmbeddings()
+    vectordb = Chroma(persist_directory='db', embedding_function=embeddings)
+
+    retriever = vectordb.as_retriever(search_type='mmr')
+
+    return retriever
+
+class StreamHandler(BaseCallbackHandler):
+    def __init__(self, container: st.delta_generator.DeltaGenerator, initial_text: str = ''):
+        self.container = container
+        self.text = initial_text
+
+    def on_llm_new_token(self, token: str, **kwargs) -> None:
+        self.text += token
+        self.container.markdown(self.text)
+
+retriever = get_retriever()
+
+msgs = StreamlitChatMessageHistory()
+memory = ConversationBufferMemory(memory_key='chat_history', chat_memory=msgs, return_messages=True)
+
+llm = ChatOpenAI(model_name='gpt-3.5-turbo', temperature=0, streaming=True)
+qa_chain = ConversationalRetrievalChain.from_llm(
+    llm, retriever=retriever, memory=memory, verbose=False
+)
+
+if st.sidebar.button('Clear message history') or len(msgs.messages) == 0:
+    msgs.clear()
+    msgs.add_ai_message(f'Ask me anything about {website_url}!')
+
+avatars = {'human': 'user', 'ai': 'assistant'}
+for msg in msgs.messages:
+    st.chat_message(avatars[msg.type]).write(msg.content)
+
+if user_query := st.chat_input(placeholder='Ask me anything!'):
+    st.chat_message('user').write(user_query)
+
+    with st.chat_message('assistant'):
+        stream_handler = StreamHandler(st.empty())
+        response = qa_chain.run(user_query, callbacks=[stream_handler])

requirements.txt

@@ -0,0 +1,7 @@
+apify-client
+chromadb
+langchain
+openai
+python-dotenv
+streamlit
+tiktoken

scrape.py

@@ -0,0 +1,40 @@
+import os
+
+from apify_client import ApifyClient
+from dotenv import load_dotenv
+from langchain.document_loaders import ApifyDatasetLoader
+from langchain.document_loaders.base import Document
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.vectorstores import Chroma
+
+# Load environment variables from a .env file
+load_dotenv()
+
+if __name__ == '__main__':
+    apify_client = ApifyClient(os.environ.get('APIFY_API_TOKEN'))
+    website_url = os.environ.get('WEBSITE_URL')
+    print(f'Extracting data from "{website_url}". Please wait...')
+    actor_run_info = apify_client.actor('apify/website-content-crawler').call(
+        run_input={'startUrls': [{'url': website_url}]}
+    )
+    print('Saving data into the vector database. Please wait...')
+    loader = ApifyDatasetLoader(
+        dataset_id=actor_run_info['defaultDatasetId'],
+        dataset_mapping_function=lambda item: Document(
+            page_content=item['text'] or '', metadata={'source': item['url']}
+        ),
+    )
+    documents = loader.load()
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1500, chunk_overlap=100)
+    docs = text_splitter.split_documents(documents)
+
+    embedding = OpenAIEmbeddings()
+
+    vectordb = Chroma.from_documents(
+        documents=docs,
+        embedding=embedding,
+        persist_directory='db2',
+    )
+    vectordb.persist()
+    print('All done!')