Upload 6 files

.gitattributes

@@ -34,3 +34,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 faiss_index_sysml/index.faiss filter=lfs diff=lfs merge=lfs -text
+Dataset/Lenny[[:space:]]Delligatti[[:space:]]-[[:space:]]SysML[[:space:]]Distilled[[:space:]][[:space:]]A[[:space:]]Brief[[:space:]]Guide[[:space:]]to[[:space:]]the[[:space:]]Systems[[:space:]]Modeling[[:space:]]Language-Addison-Wesley[[:space:]]Professional[[:space:]](2013).pdf filter=lfs diff=lfs merge=lfs -text
+Dataset/OMG[[:space:]]Systems[[:space:]]Modeling[[:space:]]Language[[:space:]](OMG[[:space:]]SysML).pdf filter=lfs diff=lfs merge=lfs -text
+Dataset/The_SysML_Modelling_Language.pdf filter=lfs diff=lfs merge=lfs -text

Dataset/Lenny Delligatti - SysML Distilled A Brief Guide to the Systems Modeling Language-Addison-Wesley Professional (2013).pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adad4affd9427f87a0ec9217abf30bab0cef7c2cc438023665e66c90d5ed6f9d
+size 6350490

Dataset/OMG Systems Modeling Language (OMG SysML).pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:633007f2b5e8257f40b0315732d5c0720c1e025cd6bf78dfd9c0aa43eaff23fe
+size 3613524

Dataset/The_SysML_Modelling_Language.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:406089eb1d4f67ca35cfa42cce377ad7435b30e5baa435cdd00847afdec635dd
+size 233280

vdb_script/faiss_vdb_script.py

@@ -0,0 +1,50 @@
+import os
+from langchain.document_loaders import PyPDFLoader, DirectoryLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain_community.vectorstores import FAISS
+from langchain.chains import RetrievalQA
+from langchain.llms import OpenAI
+from dotenv import load_dotenv
+
+# Load environment variable for OpenAI key
+load_dotenv()
+
+OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
+if not OPENAI_API_KEY:
+    raise ValueError("Missing OPENAI_API_KEY in environment variables.")
+
+# Extract Data from the PDFs
+def load_pdf_file(data_path):
+    loader = DirectoryLoader(data_path, glob="*.pdf", loader_cls=PyPDFLoader)
+    documents = loader.load()
+    return documents
+
+# Split the data into chunks
+def text_split(docs):
+    splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=20)
+    return splitter.split_documents(docs)
+
+# Set up LLM and Embedding
+llm = OpenAI(model_name="gpt-4o-mini", temperature=0.5, openai_api_key=OPENAI_API_KEY)
+embeddings = OpenAIEmbeddings(openai_api_key=OPENAI_API_KEY)
+
+# Load PDF, chunk it, embed it, and store in FAISS
+pdf_docs = load_pdf_file("/kaggle/input/rag-test")  # Update this to your PDF folder
+chunks = text_split(pdf_docs)
+
+vectorstore = FAISS.from_documents(chunks, embeddings)
+vectorstore.save_local("faiss_index_sysml")
+
+# Load FAISS and create retriever QA chain
+# new_vectorstore = FAISS.load_local("faiss_index_sysml", embeddings, allow_dangerous_deserialization=True)
+# qa = RetrievalQA.from_chain_type(
+#     llm=llm,
+#     chain_type="stuff",
+#     retriever=new_vectorstore.as_retriever()
+# )
+
+# # Run a sample query
+# query = "What is SysML used for?"
+# print("User:", query)
+# print("Bot:", qa.run(query))

vdb_script/requirements.txt

@@ -0,0 +1,10 @@
+langchain==0.3.25
+langchain-community==0.3.24
+langchain-core==0.3.60
+langchain-openai==0.3.17
+openai==1.79.0
+faiss-cpu==1.11.0
+python-dotenv==1.1.0
+gradio==4.15.0
+gradio_client==0.8.1
+huggingface_hub >= 0.19.3