added streamlit app in the examples folder and modified .gitignore

.gitignore

@@ -159,3 +159,7 @@ cython_debug/
 #  and can be added to the global gitignore or merged into this file.  For a more nuclear
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 #.idea/
+
+# Streamlit
+.DS_Store
+uploaded_files/

CONTRIBUTING.md

@@ -5,7 +5,7 @@ helps, and credit will always be given.
 
 ## Get Started!
 
-Ready to contribute? Here's how to set up `genai_stack` for local development.
+Ready to contribute? Here's how to set up `beyondllm` for local development.
 
 1. Fork the `beyondllm` repo on GitHub.
 2. Clone your fork locally
@@ -71,8 +71,8 @@ and "help wanted" is open to whoever wants to implement it.
 
 **Write Documentation**
 
-GenAI Stack could always use more documentation, whether as part of the
-official GenAI Stack docs, in docstrings, or even on the web in blog posts,
+BeyondLLM could always use more documentation, whether as part of the
+official BeyondLLM docs, in docstrings, or even on the web in blog posts,
 articles, and such.
 
 **Submit Feedback**

examples/streamlit_app/app.py

@@ -0,0 +1,91 @@
+import os
+import streamlit as st
+from beyondllm import generator
+
+from beyondllm.llms import GeminiModel
+from beyondllm import generator
+from ingest import get_retriever
+
+st.title("Chat with CSV file")
+
+st.text("Enter Google API Key")
+google_api_key = st.text_input("Google API Key:", type="password")
+os.environ['GOOGLE_API_KEY'] = google_api_key
+
+vectordb_options = ['Chroma', 'Pinecone']
+with st.sidebar:
+    st.title("VectorDB Options")
+    vectordb_type = st.selectbox("Select VectorDB Type", 
+                                 vectordb_options, 
+                                 index=0)
+
+    if vectordb_type == 'Pinecone':
+        # get the pinecone api key and index name
+        pinecone_api_key = st.text_input("Pinecone API Key:", 
+                                         type="password")
+        pinecone_index_name = st.text_input("Pinecone Index Name:")
+
+        # choose whether to use an existing index or create a new one
+        st.subheader("Pinecone Options")
+        pinecone_option = st.radio("Choose Option", 
+                                   ('Existing', 'Create New'), 
+                                   index=0)
+
+        # choose whether you want to use the default embedding dimension or specify your own
+        pinecone_embedding_dim = st.number_input("Embedding Dimension", 
+                                                min_value=1, 
+                                                max_value=2048, 
+                                                value=768)
+
+        # choose whether you want to use the default metric or specify your own, choose between "cosine" and "euclidean"
+        pinecone_metric = st.selectbox("Metric", 
+                                      ["cosine", "euclidean"], 
+                                      index=0)
+
+        # choose whether you want to use the default cloud or specify your own
+        pinecone_cloud = st.selectbox("Cloud",
+                                      ["aws", "gcp", "azure"], 
+                                      index=0)
+
+        # put the name of the region you want to use
+        pinecone_region = st.text_input("Region:")
+
+if google_api_key:
+    st.success("Google API Key entered successfully!")
+    uploaded_file = st.file_uploader("Choose a CSV file", type=['csv'])
+    if uploaded_file is not None:
+        st.success("file uploaded successfully!")
+    question = st.text_input("Enter your question")
+
+    if uploaded_file is not None and question:
+        # Get the retriever
+        if vectordb_type == 'Pinecone':
+            retriever = get_retriever(uploaded_file, 
+                                      google_api_key, 
+                                      vector_db=vectordb_type.lower(), 
+                                      pinecone_api_key=pinecone_api_key, 
+                                      pinecone_index_name=pinecone_index_name, 
+                                      pinecone_option=pinecone_option,
+                                      pinecone_embedding_dim=pinecone_embedding_dim,
+                                      pinecone_metric=pinecone_metric,
+                                      pinecone_cloud=pinecone_cloud,
+                                      pinecone_region=pinecone_region)
+        elif vectordb_type == 'Chroma':
+            retriever = get_retriever(uploaded_file, 
+                                      google_api_key, 
+                                      vector_db=vectordb_type.lower())
+        # Initialize the LLM
+        llm = GeminiModel(model_name="gemini-pro",
+                          google_api_key = os.environ.get('GOOGLE_API_KEY'))
+        # Initialize the system prompt
+        system_prompt = "You are an AI assistant, who answers questions based on uploaded csv files. You can answer anything about the data."
+        # Initialize the generator
+        pipeline = generator.Generate(question=question,
+                                      retriever=retriever, 
+                                      llm=llm, 
+                                      system_prompt=system_prompt)
+        # Generate the response
+        response = pipeline.call()
+        # display the response
+        st.write(response)
+

examples/streamlit_app/ingest.py

@@ -0,0 +1,49 @@
+import os
+from beyondllm.retrieve import auto_retriever
+from beyondllm.vectordb import ChromaVectorDb, PineconeVectorDb
+from beyondllm.embeddings import GeminiEmbeddings
+from beyondllm import source
+
+def get_retriever(uploaded_file, google_api_key, vector_db='chroma', pinecone_api_key=None, pinecone_index_name=None, pinecone_option=None, pinecone_embedding_dim=None, pinecone_metric=None, pinecone_cloud=None, pinecone_region=None):
+    if google_api_key:
+        # Save the uploaded file
+        save_path = "./uploaded_files" # change this to your desired path or leave it as is
+        if not os.path.exists(save_path):
+            os.makedirs(save_path)
+        file_path = os.path.join(save_path, uploaded_file.name)
+        with open(file_path, "wb") as f:
+            f.write(uploaded_file.getbuffer())
+
+        # Fit the data
+        data = source.fit(file_path, dtype="csv", 
+                          chunk_size=512, 
+                          chunk_overlap=50)
+        # Initialize your embedding model
+        embed_model = GeminiEmbeddings(api_key=google_api_key, 
+                                       model_name="models/embedding-001")
+        # Initialize your vector store
+        if vector_db == 'chroma':
+            vector_store = ChromaVectorDb(collection_name='my_persistent_collection', # change this to your desired collection name
+                                          persist_directory='./db/chroma/')
+        elif vector_db == 'pinecone':
+            if pinecone_option == 'Existing':
+                # Initialize an existing Pinecone index
+                vector_store = PineconeVectorDb(api_key=pinecone_api_key, 
+                                                index_name=pinecone_index_name)
+            else:
+                # Create a new serverless Pinecone index
+                vector_store = PineconeVectorDb(
+                    create=True,
+                    api_key=pinecone_api_key,
+                    index_name=pinecone_index_name,
+                    embedding_dim=pinecone_embedding_dim,
+                    metric=pinecone_metric,
+                    cloud=pinecone_cloud,
+                    region=pinecone_region,
+                )
+        # Initialize the retriever
+        retriever = auto_retriever(data=data, embed_model=embed_model, type="normal", top_k=5, vectordb=vector_store)
+
+        return retriever
+
+    return None