Update app_utils.py

app_utils.py

@@ -14,6 +14,21 @@ from langchain.vectorstores import Chroma # Chroma is a class in the langchain.v
 from langchain.document_loaders import DirectoryLoader #       
 from langchain.embeddings.openai import OpenAIEmbeddings # OpenAIGPTEmbeddings
 from langchain.text_splitter import CharacterTextSplitter #     CharacterTextSplitter is a class in the langchain.text_splitter module that can be used to split text into chunks.
+from tenacity import (
+    retry,
+    stop_after_attempt,
+    wait_random_exponential,
+)
+
+# FUNCTIONS
+
+# get embeddings
+@retry(wait=wait_random_exponential(min=1, max=60), stop=stop_after_attempt(6))
+@st.cache_data
+def embedding_from_string(input: str, model: str) -> list:
+    response = openai.Embedding.create(input=input, model=model)
+    embedding = response["data"][0]["embedding"]
+    return embedding
 
 
 OPENAI_API_KEY = os.getenv('OPENAI_API_KEY')
@@ -47,7 +62,9 @@ def initialize_knowledge_base():
     openAI_embeddings = OpenAIEmbeddings()
     for doc in doc_texts:
         text = str(doc)
-        embedding = openAI_embeddings.embed_documents(text)
+        #embedding = openAI_embeddings.embed_documents(text)
+        #embeddings.append(embedding)
+        embedding = embedding_from_string(text, "text-embedding-ada-002")
         embeddings.append(embedding)
     
     vStore = np.concatenate(embeddings, axis=0)