second commit

Dockerfile

@@ -8,4 +8,4 @@ COPY --chown=user . $HOME/app
 COPY ./requirements.txt ~/app/requirements.txt
 RUN pip install -r requirements.txt
 COPY . .
-CMD ["chainlit", "run", "app.py", "--port", "7860"]
+CMD ["chainlit", "run", "talking_app.py", "--port", "7860"]

app.py

@@ -1,13 +1,19 @@
-
-import chainlet as cl
+import chainlit as cl
 import sys
 
 sys.path.append(".")
 
 from earnings_app import extract_information
 
+@cl.author_rename
+def rename(orig_author: str):
+    diamond_char = u'\U0001F537'
+    phrase = diamond_char + " Diamond Hands " + diamond_char
+    rename_dict = {"RetrievalQA": phrase}
+    return rename_dict.get(orig_author, orig_author)
+
 @cl.on_chat_start
-async def start():
+async def init():
     cl.user_session.set("chain", extract_information())
     await cl.Message(content="Welcome to Earnings chat!").send()
 

roaringkitty.py

@@ -0,0 +1,31 @@
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.document_loaders.csv_loader import CSVLoader
+from langchain.embeddings import CacheBackedEmbeddings
+from langchain.vectorstores import FAISS
+from langchain.chains import RetrievalQA
+from langchain.chat_models import ChatOpenAI
+from langchain.storage import LocalFileStore
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+
+text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
+
+def roaringkiity_chain():
+    # build FAISS index from csv
+    loader = CSVLoader(file_path="./data/roaringkitty.csv", source_column="Link")
+    data = loader.load()
+    documents = text_splitter.transform_documents(data)
+    store = LocalFileStore("./cache/")
+    core_embeddings_model = OpenAIEmbeddings()
+    embedder = CacheBackedEmbeddings.from_bytes_store(
+        core_embeddings_model, store, namespace=core_embeddings_model.model
+    )
+    # make async docsearch
+    docsearch = await cl.make_async(FAISS.from_documents)(documents, embedder)
+
+    chain = RetrievalQA.from_chain_type(
+        ChatOpenAI(model="gpt-4", temperature=0, streaming=True),
+        chain_type="stuff",
+        return_source_documents=True,
+        retriever=docsearch.as_retriever(),
+        chain_type_kwargs = {"prompt": prompt}
+    )

talking_app.py

@@ -1,20 +1,18 @@
+import sys
+
+sys.path.append(".")
+
 import chainlit as cl
-from langchain.embeddings.openai import OpenAIEmbeddings
-from langchain.document_loaders.csv_loader import CSVLoader
-from langchain.embeddings import CacheBackedEmbeddings
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain.vectorstores import FAISS
-from langchain.chains import RetrievalQA
-from langchain.chat_models import ChatOpenAI
-from langchain.storage import LocalFileStore
+
+
 from langchain.prompts.chat import (
     ChatPromptTemplate,
     SystemMessagePromptTemplate,
     HumanMessagePromptTemplate,
 )
-import chainlit as cl
+from roaringkitty import roaringkiity_chain
+
 
-text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
 
 # Please respond as if you were Ken from the movie Barbie. Ken is a well-meaning but naive character who loves to Beach. He talks like a typical Californian Beach Bro, but he doesn't use the word "Dude" so much.
 # If you don't know the answer, just say that you don't know, don't try to make up an answer.
@@ -54,25 +52,7 @@ async def init():
     msg = cl.Message(content=f"Building Index...")
     await msg.send()
 
-    # build FAISS index from csv
-    loader = CSVLoader(file_path="./data/roaringkitty.csv", source_column="Link")
-    data = loader.load()
-    documents = text_splitter.transform_documents(data)
-    store = LocalFileStore("./cache/")
-    core_embeddings_model = OpenAIEmbeddings()
-    embedder = CacheBackedEmbeddings.from_bytes_store(
-        core_embeddings_model, store, namespace=core_embeddings_model.model
-    )
-    # make async docsearch
-    docsearch = await cl.make_async(FAISS.from_documents)(documents, embedder)
-
-    chain = RetrievalQA.from_chain_type(
-        ChatOpenAI(model="gpt-4", temperature=0, streaming=True),
-        chain_type="stuff",
-        return_source_documents=True,
-        retriever=docsearch.as_retriever(),
-        chain_type_kwargs = {"prompt": prompt}
-    )
+    chain = roaringkiity_chain()
 
     msg.content = f"Index built!"
     await msg.send()