Upload 7 files

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.faiss filter=lfs diff=lfs merge=lfs -text
+data/ filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,11 @@
+FROM python:3.9
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+WORKDIR $HOME/app
+COPY --chown=user . $HOME/app
+COPY ./requirements.txt ~/app/requirements.txt
+RUN pip install -r requirements.txt
+COPY . .
+CMD ["chainlit", "run", "app.py", "--port", "7860"]

app.py

@@ -0,0 +1,154 @@
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.vectorstores import FAISS
+from langchain.chains import  RetrievalQA
+from langchain.chat_models import ChatOpenAI
+from langchain.document_loaders import PyMuPDFLoader
+import os
+from langchain.agents import initialize_agent, Tool
+from langchain.agents import AgentType
+import chainlit as cl
+
+@cl.on_chat_start
+async def start():
+    welcome_message1 = "Hey, Welcome to **10K-GPT**!"
+    welcome_message2 = "**10K-GPT** is designed to provide you with an interactive, user-friendly interface that lets you pose queries and fetch answers from Form 10-K documents of some of the world's leading tech giants:\n- **Meta**\n- **Amazon**\n- **Alphabet**\n- **Apple**\n- **Microsoft**,\n\nfor the years **2022, 2021, and 2020**.\n\nPlease ask a question to begin!"
+    
+    sample_questions="Some of the questions you can try:\n***"
+    elements = [
+        cl.Image(path="10KGPTLogo.png", name="10K-GPT", display="inline"),
+        # cl.Text(content=welcome_message1, name="10K-GPT", display="inline"),
+    ]
+    await cl.Message(content=welcome_message1, elements=elements).send()
+    await cl.Message(content=welcome_message2).send()
+
+@cl.langchain_factory(use_async=False)
+def load():
+    embeddings = OpenAIEmbeddings()
+    llm = ChatOpenAI(temperature=0, model="gpt-4", streaming=True)
+
+    apple_2022_docs_store = FAISS.load_local(r'data\datastores\apple_2022', embeddings)
+    apple_2021_docs_store = FAISS.load_local(r'data\datastores\apple_2021', embeddings)
+    apple_2020_docs_store = FAISS.load_local(r'data\datastores\apple_2020', embeddings)
+    
+    microsoft_2022_docs_store = FAISS.load_local(r'data\datastores\msft_2022', embeddings)
+    microsoft_2021_docs_store = FAISS.load_local(r'data\datastores\msft_2021', embeddings)
+    microsoft_2020_docs_store = FAISS.load_local(r'data\datastores\msft_2020', embeddings)
+
+    amazon_2022_docs_store = FAISS.load_local(r'data\datastores\amzn_2022', embeddings)
+    amazon_2021_docs_store = FAISS.load_local(r'data\datastores\amzn_2021', embeddings)
+    amazon_2020_docs_store = FAISS.load_local(r'data\datastores\amzn_2020', embeddings)
+
+    alphabet_2022_docs_store = FAISS.load_local(r'data\datastores\alphbt_2022', embeddings)
+    alphabet_2021_docs_store = FAISS.load_local(r'data\datastores\alphbt_2021', embeddings)
+    alphabet_2020_docs_store = FAISS.load_local(r'data\datastores\alphbt_2020', embeddings)
+
+    meta_2022_docs_store = FAISS.load_local(r'data\datastores\meta_2022', embeddings)
+    meta_2021_docs_store = FAISS.load_local(r'data\datastores\meta_2021', embeddings)
+    meta_2020_docs_store = FAISS.load_local(r'data\datastores\meta_2020', embeddings)
+
+
+    apple_2022_qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=apple_2022_docs_store.as_retriever(search_kwargs={'k':5}))
+    apple_2021_qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=apple_2021_docs_store.as_retriever(search_kwargs={'k':5}))
+    apple_2020_qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=apple_2020_docs_store.as_retriever(search_kwargs={'k':5}))
+
+    microsoft_2022_qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=microsoft_2022_docs_store.as_retriever(search_kwargs={'k':5}))
+    microsoft_2021_qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=microsoft_2021_docs_store.as_retriever(search_kwargs={'k':5}))
+    microsoft_2020_qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=microsoft_2020_docs_store.as_retriever(search_kwargs={'k':5}))
+
+    amazon_2022_qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=amazon_2022_docs_store.as_retriever(search_kwargs={'k':5}))
+    amazon_2021_qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=amazon_2021_docs_store.as_retriever(search_kwargs={'k':5}))
+    amazon_2020_qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=amazon_2020_docs_store.as_retriever(search_kwargs={'k':5}))
+
+    meta_2022_qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=meta_2022_docs_store.as_retriever(search_kwargs={'k':5}))
+    meta_2021_qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=meta_2021_docs_store.as_retriever(search_kwargs={'k':5}))
+    meta_2020_qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=meta_2020_docs_store.as_retriever(search_kwargs={'k':5}))
+
+    alphabet_2022_qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=alphabet_2022_docs_store.as_retriever(search_kwargs={'k':5}))
+    alphabet_2021_qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=alphabet_2021_docs_store.as_retriever(search_kwargs={'k':5}))
+    alphabet_2020_qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=alphabet_2020_docs_store.as_retriever(search_kwargs={'k':5}))
+
+
+
+    tools = [
+        Tool(
+            name="Apple Form 10K 2022",
+            func=apple_2022_qa.run,
+            description="useful when you need to answer from Apple 2022",
+        ),
+        Tool(
+            name="Apple Form 10K 2021",
+            func=apple_2021_qa.run,
+            description="useful when you need to answer from Apple 2021",
+        ),
+        Tool(
+            name="Apple Form 10K 2020",
+            func=apple_2020_qa.run,
+            description="useful when you need to answer from Apple 2020",
+        ),
+        Tool(
+            name="Microsoft Form 10K 2022",
+            func=microsoft_2022_qa.run,
+            description="useful when you need to answer from Microsoft 2022",
+        ),
+        Tool(
+            name="Microsoft Form 10K 2021",
+            func=microsoft_2021_qa.run,
+            description="useful when you need to answer from Microsoft 2021",
+        ),
+        Tool(
+            name="Microsoft Form 10K 2020",
+            func=microsoft_2020_qa.run,
+            description="useful when you need to answer from Microsoft 2020",
+        ),
+        Tool(
+            name="Meta Form 10K 2022",
+            func=meta_2022_qa.run,
+            description="useful when you need to answer from Meta 2022",
+        ),
+        Tool(
+            name="Meta Form 10K 2021",
+            func=meta_2021_qa.run,
+            description="useful when you need to answer from Meta 2021",
+        ),
+        Tool(
+            name="Meta Form 10K 2020",
+            func=meta_2020_qa.run,
+            description="useful when you need to answer from Meta 2020",
+        ),
+        Tool(
+            name="Alphabet Form 10K 2022",
+            func=alphabet_2022_qa.run,
+            description="useful when you need to answer from Alphabet or Google 2022",
+        ),
+        Tool(
+            name="Alphabet Form 10K 2021",
+            func=alphabet_2021_qa.run,
+            description="useful when you need to answer from Alphabet or Google 2021",
+        ),
+        Tool(
+            name="Alphabet Form 10K 2020",
+            func=alphabet_2020_qa.run,
+            description="useful when you need to answer from Alphabet or Google 2020",
+        ),
+        Tool(
+            name="Amazon Form 10K 2022",
+            func=amazon_2022_qa.run,
+            description="useful when you need to answer from Amazon 2022",
+        ),
+        Tool(
+            name="Amazon Form 10K 2021",
+            func=amazon_2021_qa.run,
+            description="useful when you need to answer from Amazon 2021",
+        ),
+        Tool(
+            name="Amazon Form 10K 2020",
+            func=amazon_2020_qa.run,
+            description="useful when you need to answer from Amazon 2020",
+        ),
+    ]
+
+    # Construct the agent. We will use the default agent type here.
+    # See documentation for a full list of options.
+    return initialize_agent(
+        tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True
+    )

requirements.txt

@@ -0,0 +1,6 @@
+langchain
+openai
+chromadb
+pypdf
+tiktoken
+chainlit