Add application file

app.py

@@ -0,0 +1,57 @@
+
+import os
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.document_loaders import TextLoader, DirectoryLoader
+from langchain.embeddings import CohereEmbeddings
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.vectorstores import Chroma
+from langchain.llms import OpenAI
+from langchain.llms import Cohere
+from langchain.chains import RetrievalQA
+from langchain import PromptTemplate
+
+import streamlit as st
+
+def ingest(file_path,embeddings):
+    loader = TextLoader(file_path)
+    documents = loader.load()
+    text_splitter = CharacterTextSplitter(chunk_size=1000) #Splitting the text and creating chunks
+    docs = text_splitter.split_documents(documents)
+
+    persist_directory = file_path[:-4]
+    print('persist dict: ')
+    print(persist_directory)
+
+    vectordb = Chroma.from_documents(documents=docs,
+                                 embedding=embeddings,
+                                 persist_directory=persist_directory)
+    # persiste the db to disk
+    vectordb.persist()
+    vectordb = None
+
+with st.sidebar:
+    with st.form('Cohere/OpenAI'):
+        mod = st.radio('Choose OpenAI/Cohere', ('OpenAI', 'Cohere'))
+        api_key = st.text_input('Enter API key', type="password")
+        # model = st.radio('Choose Company', ('ArtisanAppetite foods', 'BMW','Titan Watches'))
+        submitted = st.form_submit_button("Submit")
+
+if api_key:
+    if(mod=='OpenAI'):
+        os.environ["OPENAI_API_KEY"] = api_key
+        llm = OpenAI(temperature=0.7, verbose=True)
+        embeddings = OpenAIEmbeddings()
+    elif(mod=='Cohere'):
+        os.environ["COHERE_API_KEY"] = api_key
+        llm = Cohere(temperature=0.7, verbose=True)
+        embeddings = CohereEmbeddings()
+
+uploaded_file = st.file_uploader("Upload a file to ingest", type=["txt"])
+
+if uploaded_file is not None:
+        file_contents = uploaded_file.read()
+        file_path = uploaded_file.name
+      #  with open(save_path, "wb") as f:
+      #      f.write(file_contents)
+        print(file_path)
+        ingest(file_path,embeddings)