using chainlit v1.0.0 in requirements txt to get rid of errors. complete code in app.py. works locally in localhost 8000

.chainlit/config.toml

@@ -0,0 +1,84 @@
+[project]
+# Whether to enable telemetry (default: true). No personal data is collected.
+enable_telemetry = true
+
+# List of environment variables to be provided by each user to use the app.
+user_env = []
+
+# Duration (in seconds) during which the session is saved when the connection is lost
+session_timeout = 3600
+
+# Enable third parties caching (e.g LangChain cache)
+cache = false
+
+# Follow symlink for asset mount (see https://github.com/Chainlit/chainlit/issues/317)
+# follow_symlink = false
+
+[features]
+# Show the prompt playground
+prompt_playground = true
+
+# Process and display HTML in messages. This can be a security risk (see https://stackoverflow.com/questions/19603097/why-is-it-dangerous-to-render-user-generated-html-or-javascript)
+unsafe_allow_html = false
+
+# Process and display mathematical expressions. This can clash with "$" characters in messages.
+latex = false
+
+# Authorize users to upload files with messages
+multi_modal = true
+
+# Allows user to use speech to text
+[features.speech_to_text]
+    enabled = false
+    # See all languages here https://github.com/JamesBrill/react-speech-recognition/blob/HEAD/docs/API.md#language-string
+    # language = "en-US"
+
+[UI]
+# Name of the app and chatbot.
+name = "Chatbot"
+
+# Show the readme while the thread is empty.
+show_readme_as_default = true
+
+# Description of the app and chatbot. This is used for HTML tags.
+# description = ""
+
+# Large size content are by default collapsed for a cleaner ui
+default_collapse_content = true
+
+# The default value for the expand messages settings.
+default_expand_messages = false
+
+# Hide the chain of thought details from the user in the UI.
+hide_cot = false
+
+# Link to your github repo. This will add a github button in the UI's header.
+# github = ""
+
+# Specify a CSS file that can be used to customize the user interface.
+# The CSS file can be served from the public directory or via an external link.
+# custom_css = "/public/test.css"
+
+# Override default MUI light theme. (Check theme.ts)
+[UI.theme.light]
+    #background = "#FAFAFA"
+    #paper = "#FFFFFF"
+
+    [UI.theme.light.primary]
+        #main = "#F80061"
+        #dark = "#980039"
+        #light = "#FFE7EB"
+
+# Override default MUI dark theme. (Check theme.ts)
+[UI.theme.dark]
+    #background = "#FAFAFA"
+    #paper = "#FFFFFF"
+
+    [UI.theme.dark.primary]
+        #main = "#F80061"
+        #dark = "#980039"
+        #light = "#FFE7EB"
+
+
+[meta]
+generated_by = "1.0.0"

app.py

@@ -11,25 +11,20 @@ from langchain_core.prompts import PromptTemplate
 from langchain.schema.output_parser import StrOutputParser
 from langchain.schema.runnable import RunnablePassthrough
 from langchain.schema.runnable.config import RunnableConfig
-
 # 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.
 """
 load_dotenv()
-
 """
 We will load our environment variables here.
 """
 HF_LLM_ENDPOINT = os.environ["HF_LLM_ENDPOINT"]
 HF_EMBED_ENDPOINT = os.environ["HF_EMBED_ENDPOINT"]
-HF_TOKEN = os.environ["HF_TOKEN"]
-
+HF_TOKEN = os.environ.get("HF_TOKEN")
 # ---- GLOBAL DECLARATIONS ---- #
-
 # -- RETRIEVAL -- #
 """
 1. Load Documents from Text File
@@ -39,16 +34,17 @@ HF_TOKEN = os.environ["HF_TOKEN"]
 """
 ### 1. CREATE TEXT LOADER AND LOAD DOCUMENTS
 ### NOTE: PAY ATTENTION TO THE PATH THEY ARE IN. 
-text_loader = 
-documents = 
-
+text_loader = TextLoader("./data/paul_graham_essays.txt")
+documents = text_loader.load()  # Load the documents
 ### 2. CREATE TEXT SPLITTER AND SPLIT DOCUMENTS
-text_splitter = 
-split_documents = 
-
+text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=30)
+split_documents = text_splitter.split_documents(documents)
 ### 3. LOAD HUGGINGFACE EMBEDDINGS
-hf_embeddings = 
-
+hf_embeddings = HuggingFaceEndpointEmbeddings(
+    model=HF_EMBED_ENDPOINT,
+    task="feature-extraction",
+    huggingfacehub_api_token=HF_TOKEN,
+)
 if os.path.exists("./data/vectorstore"):
     vectorstore = FAISS.load_local(
         "./data/vectorstore", 
@@ -62,71 +58,79 @@ else:
     os.makedirs("./data/vectorstore", exist_ok=True)
     ### 4. INDEX FILES
     ### NOTE: REMEMBER TO BATCH THE DOCUMENTS WITH MAXIMUM BATCH SIZE = 32
-
+    for i in range(0, len(split_documents), 32):
+        if i == 0:
+            vectorstore = FAISS.from_documents(split_documents[i:i+32], hf_embeddings)
+            continue
+        vectorstore.add_documents(split_documents[i:i+32])
+    vectorstore.save_local("./data/vectorstore")
 hf_retriever = vectorstore.as_retriever()
-
 # -- AUGMENTED -- #
 """
 1. Define a String Template
 2. Create a Prompt Template from the String Template
 """
 ### 1. DEFINE STRING TEMPLATE
-RAG_PROMPT_TEMPLATE = 
-
+RAG_PROMPT_TEMPLATE = """\
+<|start_header_id|>system<|end_header_id|>
+You are a helpful assistant. You answer user questions based on provided context. If you can't answer the question with the provided context, say you don't know.<|eot_id|>
+<|start_header_id|>user<|end_header_id|>
+User Query:
+{query}
+Context:
+{context}<|eot_id|>
+<|start_header_id|>assistant<|end_header_id|>
+"""
 ### 2. CREATE PROMPT TEMPLATE
-rag_prompt =
-
+rag_prompt = PromptTemplate.from_template(RAG_PROMPT_TEMPLATE)
 # -- GENERATION -- #
 """
 1. Create a HuggingFaceEndpoint for the LLM
 """
 ### 1. CREATE HUGGINGFACE ENDPOINT FOR LLM
-hf_llm = 
-
+hf_llm = HuggingFaceEndpoint(
+    endpoint_url=HF_LLM_ENDPOINT,
+    max_new_tokens=512,
+    top_k=10,
+    top_p=0.95,
+    typical_p=0.95,
+    temperature=0.01,
+    repetition_penalty=1.03,
+    huggingfacehub_api_token=HF_TOKEN
+)
 @cl.author_rename
 def rename(original_author: str):
     """
     This function can be used to rename the 'author' of a message. 
-
     In this case, we're overriding the 'Assistant' author to be 'Paul Graham Essay Bot'.
     """
     rename_dict = {
         "Assistant" : "Paul Graham Essay Bot"
     }
     return rename_dict.get(original_author, original_author)
-
 @cl.on_chat_start
 async def start_chat():
     """
     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.
     """
-
     ### BUILD LCEL RAG CHAIN THAT ONLY RETURNS TEXT
-    lcel_rag_chain = 
-
+    # Diagram https://docs.google.com/presentation/d/1P9ohPhMdDr9VdXT7qgROZNY93B4jw1xaAvNH6g0AIIQ/edit?usp=sharing 
+    lcel_rag_chain = {"context": itemgetter("query") | hf_retriever, "query": itemgetter("query")}| rag_prompt | hf_llm
     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="")
-
     async for chunk in lcel_rag_chain.astream(
         {"query": message.content},
         config=RunnableConfig(callbacks=[cl.LangchainCallbackHandler()]),
     ):
         await msg.stream_token(chunk)
-
     await msg.send()

chainlit.md

@@ -1 +1 @@
-# FILL OUT YOUR CHAINLIT MD HERE WITH A DESCRIPTION OF YOUR APPLICATION
+# Paul Graham Essay LangChain RAG

data/vectorstore/index.faiss

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a86a7e679d047cd8971a596286526815f93065a9856f197b7312146545ab323
+size 13102125

data/vectorstore/index.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b75430ec8999b62a93a194efec725ae6440be0a344d89f1196b0f5eab8ff716
+size 3470911

requirements.txt

@@ -1,4 +1,4 @@
-chainlit==0.7.700
+chainlit==1.0.0
 langchain==0.2.5
 langchain_community==0.2.5
 langchain_core==0.2.9

solution_app.py

@@ -1,155 +0,0 @@
-import os
-import chainlit as cl
-from dotenv import load_dotenv
-from operator import itemgetter
-from langchain_huggingface import HuggingFaceEndpoint
-from langchain_community.document_loaders import TextLoader
-from langchain_text_splitters import RecursiveCharacterTextSplitter
-from langchain_community.vectorstores import FAISS
-from langchain_huggingface import HuggingFaceEndpointEmbeddings
-from langchain_core.prompts import PromptTemplate
-from langchain.schema.output_parser import StrOutputParser
-from langchain.schema.runnable import RunnablePassthrough
-from langchain.schema.runnable.config import RunnableConfig
-
-# 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.
-"""
-load_dotenv()
-
-"""
-We will load our environment variables here.
-"""
-HF_LLM_ENDPOINT = os.environ["HF_LLM_ENDPOINT"]
-HF_EMBED_ENDPOINT = os.environ["HF_EMBED_ENDPOINT"]
-HF_TOKEN = os.environ["HF_TOKEN"]
-
-# ---- GLOBAL DECLARATIONS ---- #
-
-# -- 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
-"""
-document_loader = TextLoader("./data/paul_graham_essays.txt")
-documents = document_loader.load()
-
-text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=30)
-split_documents = text_splitter.split_documents(documents)
-
-hf_embeddings = HuggingFaceEndpointEmbeddings(
-    model=HF_EMBED_ENDPOINT,
-    task="feature-extraction",
-    huggingfacehub_api_token=HF_TOKEN,
-)
-
-if os.path.exists("./data/vectorstore"):
-    vectorstore = FAISS.load_local(
-        "./data/vectorstore", 
-        hf_embeddings, 
-        allow_dangerous_deserialization=True # this is necessary to load the vectorstore from disk as it's stored as a `.pkl` file.
-    )
-    hf_retriever = vectorstore.as_retriever()
-    print("Loaded Vectorstore")
-else:
-    print("Indexing Files")
-    os.makedirs("./data/vectorstore", exist_ok=True)
-    for i in range(0, len(split_documents), 32):
-        if i == 0:
-            vectorstore = FAISS.from_documents(split_documents[i:i+32], hf_embeddings)
-            continue
-        vectorstore.add_documents(split_documents[i:i+32])
-    vectorstore.save_local("./data/vectorstore")
-
-hf_retriever = vectorstore.as_retriever()
-
-# -- AUGMENTED -- #
-"""
-1. Define a String Template
-2. Create a Prompt Template from the String Template
-"""
-RAG_PROMPT_TEMPLATE = """\
-<|start_header_id|>system<|end_header_id|>
-You are a helpful assistant. You answer user questions based on provided context. If you can't answer the question with the provided context, say you don't know.<|eot_id|>
-
-<|start_header_id|>user<|end_header_id|>
-User Query:
-{query}
-
-Context:
-{context}<|eot_id|>
-
-<|start_header_id|>assistant<|end_header_id|>
-"""
-
-rag_prompt = PromptTemplate.from_template(RAG_PROMPT_TEMPLATE)
-
-# -- GENERATION -- #
-"""
-1. Create a HuggingFaceEndpoint for the LLM
-"""
-hf_llm = HuggingFaceEndpoint(
-    endpoint_url=HF_LLM_ENDPOINT,
-    max_new_tokens=512,
-    top_k=10,
-    top_p=0.95,
-    temperature=0.3,
-    repetition_penalty=1.15,
-    huggingfacehub_api_token=HF_TOKEN,
-)
-
-@cl.author_rename
-def rename(original_author: str):
-    """
-    This function can be used to rename the 'author' of a message. 
-
-    In this case, we're overriding the 'Assistant' author to be 'Paul Graham Essay Bot'.
-    """
-    rename_dict = {
-        "Assistant" : "Paul Graham Essay Bot"
-    }
-    return rename_dict.get(original_author, original_author)
-
-@cl.on_chat_start
-async def start_chat():
-    """
-    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 = (
-        {"context": itemgetter("query") | hf_retriever, "query": itemgetter("query")}
-        | rag_prompt | hf_llm
-    )
-
-    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)(
-        {"query": message.content},
-        config=RunnableConfig(callbacks=[cl.LangchainCallbackHandler()]),
-    ):
-        await msg.stream_token(chunk)
-
-    await msg.send()