add files

app.py

@@ -0,0 +1,54 @@
+import os
+import gradio as gr
+import openai
+from langchain import hub
+from langchain_community.document_loaders import PyPDFLoader
+from langchain_community.vectorstores import Chroma
+from langchain_core.output_parsers import StrOutputParser
+from langchain_core.runnables import RunnablePassthrough
+from langchain_openai import ChatOpenAI, OpenAIEmbeddings
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+
+
+data_root = './data/pdf/'
+pdf_paths = [data_root+path for path in os.listdir(data_root)]
+
+loaders = [PyPDFLoader(path) for path in pdf_paths]
+
+docs = []
+for loader in loaders:
+    docs.extend(
+        loader.load()[0:] # skip first page
+    )
+
+chunk_size = 500
+chunk_overlap = 100
+
+text_splitter = RecursiveCharacterTextSplitter(chunk_size=chunk_size, 
+                                               chunk_overlap=chunk_overlap)
+
+splits = text_splitter.split_documents(docs)
+
+vectorstore = Chroma.from_documents(documents=splits, embedding=OpenAIEmbeddings())
+retriever = vectorstore.as_retriever()
+prompt = hub.pull("rlm/rag-prompt")
+# model_name = 'gpt-3.5-turbo-0125'
+model_name = 'gpt-4-1106-preview'
+llm = ChatOpenAI(model_name=model_name, temperature=0)
+
+def format_docs(docs):
+    return '\n\n'.join(doc.page_content for doc in docs)
+
+rag_chain = (
+    {"context": retriever | format_docs, "question": RunnablePassthrough()}
+    | prompt
+    | llm
+    | StrOutputParser()
+)
+
+def predict(query):
+    return rag_chain.invoke(query)
+
+textbox = gr.Textbox(label="اكتب سؤالك هنا", placeholder="", lines=4)
+iface = gr.Interface(fn=predict, inputs=textbox, outputs="text")
+iface.launch()

requirements.txt

@@ -0,0 +1,7 @@
+langchain 
+langchain-community 
+langchainhub 
+langchain-openai 
+chromadb 
+bs4
+pypdf