first files

.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
+gehoert2022-11[[:space:]]November.pdf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,12 +1 @@
----
-title: Chatwithfiles
-emoji: 🌖
-colorFrom: gray
-colorTo: green
-sdk: streamlit
-sdk_version: 1.25.0
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# streamlit_chatwithfiles

app.py

@@ -0,0 +1,51 @@
+import os
+
+import streamlit as st
+
+from gui.history import ChatHistory
+from gui.layout import Layout
+from gui.sidebar import Sidebar, Utilities
+
+if __name__ == '__main__':
+    st.set_page_config(layout="wide", page_icon="💬", page_title="ChatPDF")
+    layout, sidebar, utils = Layout(), Sidebar(), Utilities()
+
+    layout.show_header()
+    user_api_key = utils.load_api_key()
+
+    if not user_api_key:
+        layout.show_api_key_missing()
+    else:
+        os.environ["OPENAI_API_KEY"] = user_api_key
+        pdf = utils.handle_upload()
+
+        if pdf:
+            sidebar.show_options()
+
+            try:
+                history = ChatHistory()
+                chatbot = utils.setup_chatbot(
+                    pdf, st.session_state["model"], st.session_state["temperature"]
+                )
+                st.session_state["chatbot"] = chatbot
+                if st.session_state["ready"]:
+                    history.initialize(pdf.name)
+
+                    response_container, prompt_container = st.container(), st.container()
+
+                    with prompt_container:
+                        is_ready, user_input = layout.prompt_form()
+
+                        if st.session_state["reset_chat"]:
+                            history.reset()
+
+                        if is_ready:
+                            output = st.session_state["chatbot"].conversational_chat(user_input)
+
+                    history.generate_messages(response_container)
+
+            except Exception as e:
+                st.error(f"{e}")
+                st.stop()
+
+    sidebar.about()

chatbot.py

@@ -0,0 +1,24 @@
+import streamlit as st
+from langchain.chains import ConversationalRetrievalChain
+from langchain.chat_models import ChatOpenAI
+
+
+class Chatbot:
+
+    def __init__(self, model_name, temperature, vectors):
+        self.model_name = model_name
+        self.temperature = temperature
+        self.vectors = vectors
+
+    def conversational_chat(self, query):
+        """
+        Starts a conversational chat with a model via Langchain
+        """
+        chain = ConversationalRetrievalChain.from_llm(
+            llm=ChatOpenAI(model_name=self.model_name, temperature=self.temperature),
+            memory=st.session_state["history"],
+            retriever=self.vectors.as_retriever(),
+        )
+        result = chain({"question": query})
+
+        return result["answer"]

config.toml

@@ -0,0 +1,18 @@
+[theme]
+
+# Primary accent for interactive elements
+primaryColor = '#548eff'
+
+# Background color for the main content area
+backgroundColor = '#f5f7fb'
+
+# Background color for sidebar and most interactive widgets
+secondaryBackgroundColor = '#FFFFFF'
+
+# Color used for almost all text
+textColor = '#2d3643'
+
+# Font family for all text in the app, except code blocks
+# Accepted values (serif | sans serif | monospace) 
+# Default: "sans serif"
+font = "sans serif"

embedding.py

@@ -0,0 +1,61 @@
+import os
+import pickle
+import tempfile
+
+from langchain.document_loaders import PyPDFLoader
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.vectorstores import FAISS
+
+
+class Embedder:
+    def __init__(self):
+        self.PATH = "embeddings"
+        self.createEmbeddingsDir()
+
+    def createEmbeddingsDir(self):
+        """
+        Creates a directory to store the embeddings vectors
+        """
+        if not os.path.exists(self.PATH):
+            os.mkdir(self.PATH)
+
+    def storeDocEmbeds(self, file, filename):
+        """
+        Stores document embeddings using Langchain and FAISS
+        """
+        # Write the uploaded file to a temporary file
+        with tempfile.NamedTemporaryFile(mode="wb", delete=False) as tmp_file:
+            tmp_file.write(file)
+            tmp_file_path = tmp_file.name
+
+        # Load the data from the file using Langchain
+        loader = PyPDFLoader(file_path=tmp_file_path)
+        data = loader.load_and_split()
+        print(f"Loaded {len(data)} documents from {tmp_file_path}")
+
+        # Create an embeddings object using Langchain
+        embeddings = OpenAIEmbeddings(allowed_special={'<|endofprompt|>'})
+
+        # Store the embeddings vectors using FAISS
+        vectors = FAISS.from_documents(data, embeddings)
+        os.remove(tmp_file_path)
+
+        # Save the vectors to a pickle file
+        with open(f"{self.PATH}/{filename}.pkl", "wb") as f:
+            pickle.dump(vectors, f)
+
+    def getDocEmbeds(self, file, filename):
+        """
+        Retrieves document embeddings
+        """
+        # Check if embeddings vectors have already been stored in a pickle file
+        pkl_file = f"{self.PATH}/{filename}.pkl"
+        if not os.path.isfile(pkl_file):
+            # If not, store the vectors using the storeDocEmbeds function
+            self.storeDocEmbeds(file, filename)
+
+        # Load the vectors from the pickle file
+        with open(pkl_file, "rb") as f:
+            vectors = pickle.load(f)
+
+        return vectors

gehoert2022-11 November.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:973eed315c62e02dda711577266d4199fc6ab923ebbfdad7d7b51d316f9c1701
+size 8963614

requirements.txt

@@ -0,0 +1,22 @@
+# Automatically generated by https://github.com/damnever/pigar.
+
+# ChatPDF/chatbot.py: 2,3,4
+# ChatPDF/embedding.py: 5,6,7
+# ChatPDF/gui/history.py: 4
+# ChatPDF/notebook/pdf_chat.ipynb: 1,3,10,11,19,20,21,22
+langchain==0.0.153
+
+# ChatPDF/app.py: 3
+# ChatPDF/chatbot.py: 1
+# ChatPDF/gui/history.py: 1
+# ChatPDF/gui/layout.py: 1
+# ChatPDF/gui/sidebar.py: 3
+streamlit==1.22.0
+
+# ChatPDF/gui/history.py: 5
+streamlit_chat_media==0.0.4
+
+pypdf==3.8.1
+openai==0.27.5
+tiktoken==0.3.3
+faiss-cpu==1.7.4