added logo and changed the embeddings

.chainlit/config.toml

@@ -64,7 +64,7 @@ default_expand_messages = false
 hide_cot = false
 
 # Link to your github repo. This will add a github button in the UI's header.
-# github = ""
+github = "https://github.com/souravmighty"
 
 # Specify a CSS file that can be used to customize the user interface.
 # The CSS file can be served from the public directory or via an external link.

app.py

@@ -1,5 +1,5 @@
 import PyPDF2
-from langchain_community.embeddings import OllamaEmbeddings
+from langchain_community.embeddings import SentenceTransformerEmbeddings
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_community.vectorstores import Chroma
 from langchain.chains import ConversationalRetrievalChain
@@ -41,25 +41,6 @@ async def on_chat_start():
         ]
     ).send()
 
-    
-    await setup_agent(settings)
-    
-
-@cl.on_settings_update
-async def setup_agent(settings):
-    print("Setup agent with settings:", settings)
-
-    user_env = cl.user_session.get("env")
-    os.environ["GROQ_API_KEY"] = user_env.get("GROQ_API_KEY")
-
-    # embeddings = OllamaEmbeddings(model="nomic-embed-text")
-    # memory=get_memory()
-    
-    # docsearch = await cl.make_async(Chroma)(
-    #     persist_directory="./chroma_db",
-    #     embedding_function=embeddings
-    # )
-
     files = None #Initialize variable to store uploaded files
 
     # Wait for the user to upload a file
@@ -92,17 +73,36 @@ async def setup_agent(settings):
     metadatas = [{"source": f"{i}-pl"} for i in range(len(texts))]
 
     # Create a Chroma vector store
-    embeddings = OllamaEmbeddings(model="nomic-embed-text")
+    # embeddings = OllamaEmbeddings(model="nomic-embed-text")
+    embeddings = SentenceTransformerEmbeddings(model_name = "sentence-transformers/all-MiniLM-L6-v2")
     #embeddings = OllamaEmbeddings(model="llama2:7b")
     docsearch = await cl.make_async(Chroma.from_texts)(
-        texts, embeddings, metadatas=metadatas
+        texts, embeddings, metadatas=metadatas, persist_directory='./chroma_db'
     )
-    
+    docsearch.persist()
+
     # Let the user know that the system is ready
     msg.content = f"Processing `{file.name}` done. You can now ask questions!"
     await msg.update()
 
+    await setup_agent(settings)
+    
+
+@cl.on_settings_update
+async def setup_agent(settings):
+    print("Setup agent with settings:", settings)
+
+    user_env = cl.user_session.get("env")
+    os.environ["GROQ_API_KEY"] = user_env.get("GROQ_API_KEY")
+
+    # embeddings = OllamaEmbeddings(model="nomic-embed-text")
+    embeddings = SentenceTransformerEmbeddings(model_name = "sentence-transformers/all-MiniLM-L6-v2")
     memory=get_memory()
+    
+    docsearch = await cl.make_async(Chroma)(
+        persist_directory="./chroma_db",
+        embedding_function=embeddings
+    )
 
 
     # Create a chain that uses the Chroma vector store

chroma_db/71a07f1e-d833-4c9a-a157-bfc7ef8305f1/data_level0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3c9fd302f000d7790aa403c2d0d8fec363fe46f30b07d53020b6e33b22435a9
+size 1676000

chroma_db/71a07f1e-d833-4c9a-a157-bfc7ef8305f1/header.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e87a1dc8bcae6f2c4bea6d5dd5005454d4dace8637dae29bff3c037ea771411e
+size 100

chroma_db/71a07f1e-d833-4c9a-a157-bfc7ef8305f1/length.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:756bb44282bd5346e3ab0f955749756f1f378b655ccd3c2ee9f8ae7cc5f92a9e
+size 4000