updated lc imports

app.py

@@ -36,6 +36,12 @@ def create_gradio_interface(qa:RetrievalQAWithSourcesChain):
         result = qa({"query": query, "history": history, "question": question})
         return result
 
+    def vote(data: gr.LikeData):
+        if data.liked:
+            print("You upvoted this response: ")
+        else:
+            print("You downvoted this response: ")
+
     css="""
     #col-container {max-width: 700px; margin-left: auto; margin-right: auto;}
     """
@@ -43,19 +49,28 @@ def create_gradio_interface(qa:RetrievalQAWithSourcesChain):
     title = """
     <div style="text-align: center;max-width: 1920px;">
         <h1>Chat with your Documentation</h1>
-        <p style="text-align: center;">This is a privately hosten Docs AI Buddy, <br />
-        It will help you with any question regarding the documentation of Ray ;)</p>
+        <p style="text-align: center;">This is a privately hosten Docs AI Buddy ;)</p>
     </div>
     """
 
+    head_style = """
+    <style>
+    @media (min-width: 1536px)
+    {
+        .gradio-container {
+            min-width: var(--size-full) !important;
+        }
+    }
+    </style>
+    """
 
-
-    with gr.Blocks(css=css) as demo:
+    with gr.Blocks(title="DocsBuddy AI 🤵🏻‍♂️", head=head_style) as demo:
         with gr.Column(min_width=900, elem_id="col-container"):
             gr.HTML(title)      
-            chatbot = gr.Chatbot([], elem_id="chatbot")
+            chatbot = gr.Chatbot([], elem_id="chatbot", label="DocuBuddy 🤵🏻‍♂️")
             #with gr.Row():
             #    clear = gr.Button("Clear")
+            chatbot.like(vote, None, None)
 
             with gr.Row():
                 question = gr.Textbox(label="Question", placeholder="Type your question and hit Enter ")

qa.py

@@ -6,7 +6,7 @@ import logging
 import os
 from dotenv import load_dotenv
 
-import time
+#import time
 
 #boto3 for S3 access
 import boto3
@@ -14,10 +14,10 @@ from botocore import UNSIGNED
 from botocore.client import Config
 
 # HF libraries
-from langchain_community.llms import HuggingFaceHub
-from langchain_community.embeddings import HuggingFaceHubEmbeddings
+from langchain_huggingface import HuggingFaceEndpoint
+from langchain_huggingface.embeddings import HuggingFaceEmbeddings
 # vectorestore
-from langchain_community.vectorstores import Chroma
+#from langchain_community.vectorstores import Chroma
 from langchain_community.vectorstores import FAISS
 import zipfile
 
@@ -34,7 +34,7 @@ from langchain.globals import set_verbose
 # caching
 from langchain.globals import set_llm_cache
 # We can do the same thing with a SQLite cache
-from langchain.cache import SQLiteCache
+from langchain_community.cache import SQLiteCache
 
 
 # template for prompt
@@ -70,17 +70,17 @@ if os.path.exists('.langchain.sqlite'):
 llm_model_name = "mistralai/Mistral-7B-Instruct-v0.1"
 
 # changed named to model_id to llm as is common
-llm = HuggingFaceHub(repo_id=llm_model_name, model_kwargs={
-    # "temperature":0.1, 
-    "max_new_tokens":1024, 
-    "repetition_penalty":1.2, 
-#    "streaming": True, 
-    "return_full_text":False
-    })
+llm = HuggingFaceEndpoint(
+repo_id=llm_model_name, 
+temperature=0.1, 
+max_new_tokens=1024,
+repetition_penalty=1.2,
+return_full_text=False,
+) 
 
 # initialize Embedding config
 embedding_model_name = "sentence-transformers/multi-qa-mpnet-base-dot-v1"
-embeddings = HuggingFaceHubEmbeddings(repo_id=embedding_model_name)
+embeddings = HuggingFaceEmbeddings(model_name=embedding_model_name)
 
 set_llm_cache(SQLiteCache(database_path=".langchain.sqlite"))
 
@@ -93,7 +93,7 @@ with zipfile.ZipFile(VS_DESTINATION, 'r') as zip_ref:
     zip_ref.extractall('./vectorstore/')
 
 FAISS_INDEX_PATH='./vectorstore/lc-faiss-multi-qa-mpnet'
-db = FAISS.load_local(FAISS_INDEX_PATH, embeddings)
+db = FAISS.load_local(FAISS_INDEX_PATH, embeddings, allow_dangerous_deserialization=True)
 
 # use the cached embeddings instead of embeddings to speed up re-retrival
 # db = Chroma(persist_directory="./vectorstore", embedding_function=embeddings)

requirements.txt

@@ -3,6 +3,7 @@ chromadb
 faiss-cpu
 langchain
 langchain-community
+langchain-huggingface
 python-dotenv
 bs4
 gradio