innitial commit

.chainlit/config.toml

@@ -0,0 +1,42 @@
+[project]
+# If true (default), the app will be available to anonymous users.
+# If false, users will need to authenticate and be part of the project to use the app.
+public = true
+
+# The project ID (found on https://cloud.chainlit.io).
+# The project ID is required when public is set to false or when using the cloud database.
+#id = ""
+
+# Uncomment if you want to persist the chats.
+# local will create a database in your .chainlit directory (requires node.js installed).
+# cloud will use the Chainlit cloud database.
+# custom will load use your custom client.
+#database = "local"
+
+# Whether to enable telemetry (default: true). No personal data is collected.
+enable_telemetry = false
+
+# 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
+
+[UI]
+# Name of the app and chatbot.
+name = "Broomva Book Chat"
+
+# Description of the app and chatbot. This is used for HTML tags.
+# description = ""
+
+# 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 = ""
+
+[meta]
+generated_by = "0.6.2"

.gitattributes

@@ -33,3 +33,4 @@ 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

.gitignore

@@ -0,0 +1 @@
+.env

Dockerfile.txt

@@ -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 +1,45 @@
+import os
+
+import chainlit as cl
+from langchain.chains import RetrievalQAWithSourcesChain
+from langchain.chat_models import ChatOpenAI
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.prompts.chat import (AIMessagePromptTemplate,
+                                    ChatPromptTemplate,
+                                    HumanMessagePromptTemplate)
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.vectorstores import FAISS
+
+text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
+embeddings = OpenAIEmbeddings()
+
+@cl.on_chat_start
+async def init():
+    vector_store = FAISS.load_local("docs.faiss", embeddings)
+
+    chain = RetrievalQAWithSourcesChain.from_chain_type(
+        ChatOpenAI(temperature=0, streaming=True, model="gpt-4-1106-preview"),
+        chain_type="stuff",
+        retriever=vector_store.as_retriever(search_kwargs={"k": 7}),
+    )
+
+    cl.user_session.set("chain", chain)
+
+
+@cl.on_message
+async def main(message):
+    chain = cl.user_session.get("chain")  # type: RetrievalQAWithSourcesChain
+    cb = cl.AsyncLangchainCallbackHandler(
+        stream_final_answer=True, answer_prefix_tokens=["FINAL", "ANSWER"]
+    )
+    cb.answer_reached = True
+    
+    res = await chain.acall(message.content, callbacks=[cb])
+
+    if cb.has_streamed_final_answer:
+        await cb.final_stream.update()
+    else:
+        answer = res["answer"]
+        await cl.Message(
+            content=answer,
+        ).send()

chainlit.md

@@ -0,0 +1,2 @@
+# Welcome to the Broomva Book Chat
+

index_creation.py

@@ -0,0 +1,26 @@
+# %%
+from langchain.document_loaders import DirectoryLoader, TextLoader
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.vectorstores import FAISS
+
+# %%
+loader = DirectoryLoader(
+    "../../../docs", glob="./*.md", loader_cls=TextLoader, recursive=True
+)
+
+documents = loader.load()
+# %%
+
+text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
+texts = text_splitter.split_documents(documents)
+
+# %%
+embedding = OpenAIEmbeddings()
+
+vectordb = FAISS.from_documents(documents=texts, embedding=embedding)
+
+# %%
+vectordb.save_local("docs.faiss")
+
+# %%

requirements.txt

@@ -0,0 +1,7 @@
+langchain
+chainlit
+openai
+faiss-cpu
+chromadb
+tiktoken
+pymupdf