adding new files

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"]

README.md

@@ -1,11 +1,35 @@
 ---
-title: Airbnb New Space
-emoji: 🏆
+title: Ekonez
+emoji: 📉
 colorFrom: pink
 colorTo: yellow
 sdk: docker
 pinned: false
-license: openrail
+app_port: 7860
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+## 🤖 Appka pro snadný přístup k daňovým zákonům
+
+> Polož otázku o daních.
+
+<p align = "center" draggable=”false” ><img src="image.jpg" 
+     width="200px"
+     height="auto"/>
+</p>
+
+
+##  Odpovědi čerpají z webu:   "https://www.zakonyprolidi.cz/
+
+---
+
+<p align = "center" draggable=”false” ><img src="https://github.com/AI-Maker-Space/LLM-Dev-101/assets/37101144/d1343317-fa2f-41e1-8af1-1dbb18399719" 
+     width="200px"
+     height="auto"/>
+</p>
+
+
+## <h1 align="center" id="heading">:wave: Welcome to Beyond ChatGPT!!</h1>
+
+For a step-by-step YouTube video walkthrough, watch this! [Deploying Chainlit app on Hugging Face](https://www.youtube.com/live/pRbbZcL0NMI?si=NAYhMZ_suAY84f06&t=2119)
+
+![Beyond ChatGPT: Build Your First LLM Application](https://github.com/AI-Maker-Space/Beyond-ChatGPT/assets/48775140/cb7a74b8-28af-4d12-a008-8f5a51d47b4c)

app.py

@@ -0,0 +1,163 @@
+import os
+import chainlit as cl
+from dotenv import load_dotenv
+from operator import itemgetter
+from langchain_openai import ChatOpenAI
+from langchain.schema.runnable import RunnablePassthrough
+from langchain.schema.runnable.config import RunnableConfig
+from langchain_openai.embeddings import OpenAIEmbeddings
+from langchain.document_loaders import PyMuPDFLoader
+import tiktoken
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.vectorstores import Qdrant
+from langchain_openai.embeddings import OpenAIEmbeddings
+from langchain_core.prompts import ChatPromptTemplate
+from langchain.schema.output_parser import StrOutputParser
+from langchain.schema.runnable import RunnablePassthrough
+from dotenv import main
+import openai
+
+# GLOBAL SCOPE - ENTIRE APPLICATION HAS ACCESS TO VALUES SET IN THIS SCOPE #
+# ---- ENV VARIABLES ---- # 
+"""
+This function will load our environment file (.env) if it is present.
+
+NOTE: Make sure that .env is in your .gitignore file - it is by default, but please ensure it remains there.
+"""
+main.load_dotenv()
+
+"""
+We will load our environment variables here.
+"""
+openai.api_key = os.getenv("OPENAI_API_KEY")
+
+# Model
+openai_chat_model = ChatOpenAI(model="gpt-4o")
+
+# upload embedding model
+embedding_model = OpenAIEmbeddings(model="text-embedding-3-small")
+
+# ---- GLOBAL DECLARATIONS ---- #
+@cl.on_chat_start
+async def init():
+    # -- RETRIEVAL -- #
+    """
+    1. Load Documents from Text File
+    2. Split Documents into Chunks
+    3. Load HuggingFace Embeddings (remember to use the URL we set above)
+    4. Index Files if they do not exist, otherwise load the vectorstore
+    """
+    # upload file
+    #docs=TextLoader("./data/airbnb_10k_filings.txt").load()
+    docs = PyMuPDFLoader("airbnb_10k_filings.pdf").load()
+
+    import tiktoken
+    from langchain.text_splitter import RecursiveCharacterTextSplitter
+    def tiktoken_len(text):
+        tokens = tiktoken.encoding_for_model("gpt-4o").encode(
+            text,
+        )
+        return len(tokens)
+
+    text_splitter = RecursiveCharacterTextSplitter(
+        chunk_size = 200,
+        chunk_overlap = 0,
+        length_function = tiktoken_len,
+    )
+
+    split_chunks = text_splitter.split_documents(docs)
+
+    max_chunk_length = 0
+
+    for chunk in split_chunks:
+        max_chunk_length = max(max_chunk_length, tiktoken_len(chunk.page_content))
+
+    # Embeddings and Vector store
+    qdrant_vectorstore = Qdrant.from_documents(
+        split_chunks,
+        embedding_model,
+        location=":memory:",
+        collection_name="airbnb 10k filings",
+    )
+    print("Loaded Vectorstore")
+
+    # Ste up ur retriever using LangChain
+    qdrant_retriever = qdrant_vectorstore.as_retriever()
+
+    # -- AUGMENTED -- #
+    """
+    1. Define a String Template
+    2. Create a Prompt Template from the String Template
+    """
+    RAG_PROMPT = """
+    CONTEXT:
+    {context}
+
+    QUERY:
+    {question}
+    Use the provide context to answer the provided user question. Only use the provided context to answer the question. If you do not know the answer, response with "I don't know"
+    """
+
+    CONTEXT = """
+    This report on Airbnb 10k filings contains unstructured and structured tabular data, use both.
+    """
+
+    rag_prompt = ChatPromptTemplate.from_template(RAG_PROMPT)
+
+    # -- Our RAG Chain -- #
+
+    """
+    This function will be called at the start of every user session. 
+
+    We will build our LCEL RAG chain here, and store it in the user session. 
+
+    The user session is a dictionary that is unique to each user session, and is stored in the memory of the server.
+    """
+
+    lcel_rag_chain = (
+        # INVOKE CHAIN WITH: {"question" : "<<SOME USER QUESTION>>"}
+        # "question" : populated by getting the value of the "question" key
+        # "context"  : populated by getting the value of the "question" key and chaining it into the base_retriever
+        {"context": itemgetter("question") | qdrant_retriever, "question": itemgetter("question")}
+        # "context"  : is assigned to a RunnablePassthrough object (will not be called or considered in the next step)
+        #              by getting the value of the "context" key from the previous step
+        | RunnablePassthrough.assign(context=itemgetter("context"))
+        # "response" : the "context" and "question" values are used to format our prompt object and then piped
+        #              into the LLM and stored in a key called "response"
+        # "context"  : populated by getting the value of the "context" key from the previous step
+        | {"response": rag_prompt | openai_chat_model, "context": itemgetter("context")}
+    )
+    # cl.user_session.set("retrieval_augmented_qa_chain", retrieval_augmented_qa_chain)
+    
+    # lcel_rag_chain = (
+    #     {"context": itemgetter("question") | qdrant_retriever, "question": itemgetter("question")}
+    #     | rag_prompt | openai_chat_model
+    # )
+    cl.user_session.set("lcel_rag_chain", lcel_rag_chain)
+
+@cl.on_message  
+async def main(message: cl.Message):
+    """
+    This function will be called every time a message is recieved from a session.
+
+    We will use the LCEL RAG chain to generate a response to the user query.
+
+    The LCEL RAG chain is stored in the user session, and is unique to each user session - this is why we can access it here.
+    """
+    lcel_rag_chain = cl.user_session.get("lcel_rag_chain")
+
+    msg = cl.Message(content="")
+
+    # for chunk in await cl.make_async(lcel_rag_chain.stream)(
+    #     {"question": message.content},
+    #     config=RunnableConfig(callbacks=[cl.LangchainCallbackHandler()]),
+    # ):
+    #     await msg.stream_token(chunk)
+
+    # await msg.send()
+    print(msg)
+    response = lcel_rag_chain.invoke({"question" : message.content})
+    # lcel_rag_chain = cl.user_session.get("lcel_rag_chain")
+    # res = lcel_rag_chain.invoke({"question":message.content})
+    print(response["response"].content)
+    await cl.Message(content=response["response"].content).send()

chainlit.md

@@ -0,0 +1,6 @@
+
+## 🤖 Appka pro snadný přístup k daňovým zákonům
+![alt text](https://huggingface.co/spaces/KatGaw/Ekonez/blob/main/image.jpg)
+> Polož otázku o daních.
+
+## Odpovědi čerpají z webu:   "https://www.zakonyprolidi.cz/

requirements.txt

@@ -0,0 +1,10 @@
+chainlit==1.1.304
+langchain>0.2.0
+langchain_community==0.2.5
+langchain_core==0.2.9
+langchain_text_splitters==0.2.1
+python-dotenv==1.0.1
+langchain_openai==0.1.8
+qdrant-client==1.9.2
+tiktoken==0.7.0
+pymupdf==1.24.5