Adding sentence transformers and some logs

indexer.py

@@ -11,12 +11,15 @@ loader = DirectoryLoader('.', glob="./source/*.html", loader_cls=BSHTMLLoader)
 docs=loader.load()
 
 #splitting the text into chunks, trying with 1000 size 
+print("splitting to chunks")
 text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
 texts = text_splitter.split_documents(docs)
 
 #init db and embeddings
+print("Creating embeddings")
 persist_directory="./index/chroma"
 embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2") 
+print("Storing in db")
 vectordb = Chroma.from_documents(documents=texts, 
                                  embedding=embeddings,
                                  persist_directory=persist_directory)
@@ -29,6 +32,7 @@ meta=[{"n":1},{"z":2},{},{},{"n":3},{"n":4}]
 
 #docsearch=FAISS.from_texts(sentences,embeddings,meta,id)   
 #m=docsearch.similarity_search_with_score(query2,filter={"n":2}) 
+print("Querying db")
 query="How to Increase Flexibility Without Losing Productivity"
 docs = vectordb.similarity_search(query)
 for i in range(0,len(docs)):

requirements.txt

@@ -6,5 +6,6 @@ fastapi
 loguru
 chromadb
 langchain
+sentence_transformers
 sse_starlette
 dropbox