vector stores

Dockerfile

@@ -31,8 +31,11 @@ RUN mkdir -p /app/.files && \
 # Copy the application code into the container
 COPY --chown=user . /app
 
+# Switch to the non-root user
+USER user
+
 # Run the application
 CMD /bin/bash -c "source env/bin/activate && \
     python3 downloadLLM.py && \
     python3 ingest.py && \
-    chainlit run main.py --host 0.0.0.0 --port 7680"
+    gunicorn -b 0.0.0.0:7860 main:app"

ingest.py

@@ -1,27 +1,19 @@
 from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain.document_loaders import PyPDFLoader, DirectoryLoader # could have done any unstructured text loader like ppt and xlsx
-
-
-from langchain.embeddings import HuggingFaceBgeEmbeddings # we can replace huggingface with facetransformers
-
+from langchain.document_loaders import PyPDFLoader, DirectoryLoader
+from langchain.embeddings import HuggingFaceBgeEmbeddings
 from langchain.vectorstores import FAISS
 
-DATA_PATH = "$HOME/data/"
-DB_FAISS_PATH = "$HOME/vectorstores/db_faiss"
+DATA_PATH = "/home/user/data"
+DB_FAISS_PATH = "/home/user/vectorstores/db_faiss"
 
-#create vector database
 def create_vector_db():
-                                            # WE can change .pdf with any other unstructured text format
-    loader = DirectoryLoader(DATA_PATH, glob="*.pdf", loader_cls = PyPDFLoader)
+    loader = DirectoryLoader(DATA_PATH, glob="*.pdf", loader_cls=PyPDFLoader)
     documents = loader.load()
 
     text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
-
     texts = text_splitter.split_documents(documents)
 
-    embeddings = HuggingFaceBgeEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2", model_kwargs={"device": "cpu"}) # change to GPU if you want
-
-    # cuda is not supported in my MAC M1! SADLY.
+    embeddings = HuggingFaceBgeEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2", model_kwargs={"device": "cpu"})
 
     db = FAISS.from_documents(texts, embeddings)
     db.save_local(DB_FAISS_PATH)