paste

RAG_PDF_WEB.py

@@ -50,17 +50,17 @@ def get_doc_chunks(docs):
     return docs
 
 def get_vectorstore_from_docs(doc_chunks):
-    embedding = OpenAIEmbeddings(model="text-embedding-3-large")
+    embedding = OpenAIEmbeddings(model="text-embedding-3-small")
     vectorstore = FAISS.from_documents(documents=doc_chunks, embedding=embedding)
     return vectorstore
 
 def get_vectorstore(text_chunks):
-    embedding = OpenAIEmbeddings(model="text-embedding-3-large")
+    embedding = OpenAIEmbeddings(model="text-embedding-3-small")
     vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embedding)
     return vectorstore
 
 def get_conversation_chain(vectorstore):
-    llm = ChatOpenAI(model="gpt-4",temperature=0.5, max_tokens=2048)
+    llm = ChatOpenAI(model="gpt-3.5-turbo",temperature=0.5, max_tokens=2048)
     retriever=vectorstore.as_retriever()
     prompt = hub.pull("rlm/rag-prompt")
     

chat_te.py

@@ -20,12 +20,12 @@ def get_docs_from_pdf(file):
     return docs
 
 def get_doc_chunks(docs):
-    text_splitter = SemanticChunker(OpenAIEmbeddings(model="text-embedding-3-large"))
+    text_splitter = SemanticChunker(OpenAIEmbeddings(model="text-embedding-3-small"))
     chunks = text_splitter.split_documents(docs)
     return chunks 
 
 def get_vectorstore_from_docs(doc_chunks):
-    embedding = OpenAIEmbeddings(model="text-embedding-3-large")
+    embedding = OpenAIEmbeddings(model="text-embedding-3-small")
     vectorstore = FAISS.from_documents(documents=doc_chunks, embedding=embedding)
     return vectorstore
 
@@ -47,7 +47,7 @@ def create_db(file):
     # docs = get_docs_from_pdf(file)
     # doc_chunks = get_doc_chunks(docs)
     # vectorstore = get_vectorstore_from_docs(doc_chunks)
-    vectorstore = FAISS.load_local(file, OpenAIEmbeddings(model="text-embedding-3-large"),allow_dangerous_deserialization= True)
+    vectorstore = FAISS.load_local(file, OpenAIEmbeddings(model="text-embedding-3-small"),allow_dangerous_deserialization= True)
     return vectorstore
 
 def get_response(chain,user_query, chat_history):