Upload 2 files

app.py

@@ -7,7 +7,7 @@ from langchain.chains.combine_documents import create_stuff_documents_chain
 from langchain_core.prompts import ChatPromptTemplate
 from langchain_openai import ChatOpenAI
 from langchain_community.document_loaders import PyPDFLoader
-from langchain_core.vectorstores import InMemoryVectorStore
+from langchain.vectorstores import FAISS
 from langchain_openai import OpenAIEmbeddings
 from langchain_text_splitters import RecursiveCharacterTextSplitter
 
@@ -26,12 +26,12 @@ def process_pdf(api_key, uploaded_file, questions_path, prompt_path, display_pla
     docs = loader.load()
 
     # Split the document into smaller chunks for embedding
-    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=3000, chunk_overlap=500)
     splits = text_splitter.split_documents(docs)
 
     # Create vector store and retriever
-    vectorstore = InMemoryVectorStore.from_documents(
-        documents=splits, embedding=OpenAIEmbeddings()
+    vectorstore = FAISS.from_documents(
+        documents=splits, embedding=OpenAIEmbeddings(model="text-embedding-3-large")
     )
     retriever = vectorstore.as_retriever(search_kwargs={"k": 10})
 

summary_tool_questions.md

@@ -1,4 +1,4 @@
-Provide a summary of information available from the plan including the city name, population, geography, major industries, per capita income, or similar summary information.
+Provide a summary of information available from the plan regarding the planning jurisdiction, including its name, location, population, geography, major industries, per capita income, and similar information.
 
 To what extent does the plan address resilience, mitigation, and adaptation?