Update app.py

app.py

@@ -1,63 +1,78 @@
+import os
+from getpass import getpass
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
 
+pinecone_api_key = os.getenv("PINECONE_API_KEY") or getpass("Enter your Pinecone API Key: ")
+openai_api_key = os.getenv("OPENAI_API_KEY") or getpass("Enter your OpenAI API Key: ")
+
+from llama_index.node_parser import SemanticSplitterNodeParser
+from llama_index.embeddings import OpenAIEmbedding
+from llama_index.ingestion import IngestionPipeline
+
+# This will be the model we use both for Node parsing and for vectorization
+embed_model = OpenAIEmbedding(api_key=openai_api_key)
+
+# Define the initial pipeline
+pipeline = IngestionPipeline(
+    transformations=[
+        SemanticSplitterNodeParser(
+            buffer_size=1,
+            breakpoint_percentile_threshold=95,
+            embed_model=embed_model,
+            ),
+        embed_model,
+        ],
+    )
+
+from pinecone.grpc import PineconeGRPC
+from pinecone import ServerlessSpec
+
+from llama_index.vector_stores import PineconeVectorStore
+
+# Initialize connection to Pinecone
+pc = PineconeGRPC(api_key=pinecone_api_key)
+index_name = "anualreport"
+
+# Initialize your index
+pinecone_index = pc.Index(index_name)
+
+# Initialize VectorStore
+vector_store = PineconeVectorStore(pinecone_index=pinecone_index)
+
+pinecone_index.describe_index_stats()
+
+from llama_index import VectorStoreIndex
+from llama_index.retrievers import VectorIndexRetriever
+
+# Due to how LlamaIndex works here, if your Open AI API key was
+# not set to an environment variable before, you have to set it at this point
+if not os.getenv('OPENAI_API_KEY'):
+    os.environ['OPENAI_API_KEY'] = openai_api_key
+
+# Instantiate VectorStoreIndex object from our vector_store object
+vector_index = VectorStoreIndex.from_vector_store(vector_store=vector_store)
+
+# Grab 5 search results
+retriever = VectorIndexRetriever(index=vector_index, similarity_top_k=5)
+
+from llama_index.query_engine import RetrieverQueryEngine
+
+# Pass in your retriever from above, which is configured to return the top 5 results
+query_engine = RetrieverQueryEngine(retriever=retriever)
+
+# Define the function to handle user input and return the query response
+def query_annual_report(summary_request):
+    llm_query = query_engine.query(summary_request)
+    return llm_query.response
+
+# Create the Gradio interface
+iface = gr.Interface(
+    fn=query_annual_report,
+    inputs="text",
+    outputs="text",
+    title="Annual Report Summary Query",
+    description="Enter your query to get the summary of the annual report."
+)
 
-if __name__ == "__main__":
-    demo.launch()
+# Launch the Gradio app
+iface.launch()