sample

README.md

@@ -4,9 +4,9 @@ emoji: 📉
 colorFrom: gray
 colorTo: gray
 sdk: gradio
-sdk_version: 4.42.0
+sdk_version: 4.2.0
 app_file: app.py
 pinned: false
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,34 +1,40 @@
 import gradio as gr
-import random
-import time
 import boto3
 from botocore import UNSIGNED
 from botocore.client import Config
-import zipfile
+
+from langchain.document_loaders import WebBaseLoader
+
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+text_splitter = RecursiveCharacterTextSplitter(chunk_size=350, chunk_overlap=10)
 
 from langchain.llms import HuggingFaceHub
-model_id = HuggingFaceHub(repo_id="tiiuae/falcon-7b-instruct", model_kwargs={"temperature":0.1, "max_new_tokens":1024})
+model_id = HuggingFaceHub(repo_id="HuggingFaceH4/zephyr-7b-beta", model_kwargs={"temperature":0.1, "max_new_tokens":300})
 
 from langchain.embeddings import HuggingFaceHubEmbeddings
 embeddings = HuggingFaceHubEmbeddings()
 
-from langchain.vectorstores import FAISS
+from langchain.vectorstores import Chroma
 
 from langchain.chains import RetrievalQA
 
-s3 = boto3.client('s3', config=Config(signature_version=UNSIGNED))
-s3.download_file('rad-rag-demos', 'vectorstores/faiss_db_ray.zip', './chroma_db/faiss_db_ray.zip')
-with zipfile.ZipFile('./chroma_db/faiss_db_ray.zip', 'r') as zip_ref:
-    zip_ref.extractall('./chroma_db/')
+from langchain.prompts import ChatPromptTemplate
 
-FAISS_INDEX_PATH='./chroma_db/faiss_db_ray'
-#embeddings = HuggingFaceHubEmbeddings("multi-qa-mpnet-base-dot-v1")
-embeddings = HuggingFaceHubEmbeddings()
-db = FAISS.load_local(FAISS_INDEX_PATH, embeddings)
-retriever = db.as_retriever(search_type = "mmr")
+#web_links = ["https://www.databricks.com/","https://help.databricks.com","https://docs.databricks.com","https://kb.databricks.com/","http://docs.databricks.com/getting-started/index.html","http://docs.databricks.com/introduction/index.html","http://docs.databricks.com/getting-started/tutorials/index.html","http://docs.databricks.com/machine-learning/index.html","http://docs.databricks.com/sql/index.html"]
+#loader = WebBaseLoader(web_links)
+#documents = loader.load()
+
+s3 = boto3.client('s3', config=Config(signature_version=UNSIGNED))
+s3.download_file('rad-rag-demos', 'vectorstores/chroma.sqlite3', './chroma_db/chroma.sqlite3')
+     
+db = Chroma(persist_directory="./chroma_db", embedding_function=embeddings)
+db.get()
+#texts = text_splitter.split_documents(documents)
+#db = Chroma.from_documents(texts, embedding_function=embeddings)
+retriever = db.as_retriever()
 
 global qa 
-qa = RetrievalQA.from_chain_type(llm=model_id, chain_type="stuff", retriever=retriever)
+qa = RetrievalQA.from_chain_type(llm=model_id, chain_type="stuff", retriever=retriever, return_source_documents=True)
 
 
 def add_text(history, text):
@@ -40,7 +46,8 @@ def bot(history):
     history[-1][1] = response['result']
     return history
 
-def infer(question):  
+def infer(question):
+    
     query = question
     result = qa({"query": query})
     return result
@@ -51,9 +58,9 @@ css="""
 
 title = """
 <div style="text-align: center;max-width: 700px;">
-    <h1>Chat with the RAY Docs</h1>
-    <p style="text-align: center;">The AI bot is here to help you with the RAY Documentation, <br />
-    start asking questions about the open-source software </p>
+    <h1>Chat with PDF</h1>
+    <p style="text-align: center;">Upload a .PDF from your computer, click the "Load PDF to LangChain" button, <br />
+    when everything is ready, you can start asking questions about the pdf ;)</p>
 </div>
 """
 

requirements.txt

@@ -1,5 +1,5 @@
 huggingface_hub
-faiss-cpu
+chromadb
 langchain
 boto3
 unstructured