debug

README.md

@@ -4,17 +4,16 @@ emoji: 😻
 colorFrom: red
 colorTo: indigo
 sdk: docker
-sdk_version: 3.40.1
-app_port: 7860
-suggested_storage: large
+#sdk_version: 3.40.1
+#app_port: 7860
+#suggested_storage: large
 app_file: app.py
-pinned: false
+#pinned: false
 startup_duration_timeout: 3 hours
 ---
 
 # Retrieval Augmented Generation with Large Language Models
 
-
 This project serves as a Proof-of-Concept for implementing Retrieval Augmented Generation (RAG) when prompting Large Language Models (LLMs). It is a learning exercise aimed at enabling future LLM-based applications by leveraging the power of RAG techniques.
 
 ## Components
@@ -35,26 +34,33 @@ The project incorporates the following key components:
 ## Application Notes
 
 As part of the initialization process, the application executes a Bash script asynchronously. The script follows these steps:
+- It starts the text2vec-transformers Weaviate module first.
+- Then, it starts the Weaviate database server itself.
+- Both programs run as subprocesses to the script.
+- Finally, the script waits to ensure that its subprocesses continue to execute so that app.py
+  can use the database for RAG functions.
 
-1. It starts the text2vec-transformers Weaviate module first.
-2. Then, it starts the Weaviate database server itself.
-3. Both programs run as subprocesses to the script.
-4. Finally, the script waits to ensure that its subprocesses continue to execute.
+Also, the vector database is only loaded with two collections/schemas based on one webpage each
+from Wikipedia. One page has content related to artifical intelligence and the other content
+about Norwegian literature.
 
 ## Usage
 
 To use the application, follow these steps:
 
-1. Type in a prompt and an optional system prompt (e.g., "You are a helpful AI assistant.") in the provided input fields.
-2. Click the "Run LLM Prompt" button to initiate the processing of the prompt by the llama-2 LLM.
-3. Once the processing is complete, the generated completion will be displayed along with the user's prompt and system prompt.
+- Type in a prompt and an optional system prompt (e.g., "You are a helpful AI assistant.") in the provided input fields.
+- Click the "Run LLM Prompt" button to initiate the processing of the prompt by the llama-2 LLM.
+- Once the processing is complete, the generated completion will be displayed along with the user's prompt and system prompt.
+- Click the "Get All Rag Data" button to view information on the two documents in the database including chunks.
 
 ## Future Improvements
 
 The following areas have been identified for future improvements:
 
-- Ensure that Retrieval Augmented Generation (RAG) is functioning correctly and efficiently.
-- Explore additional techniques to enhance the quality and relevance of the generated completions.
-- Optimize the performance and scalability of the application to handle larger datasets and more complex queries.
-- Incorporate user feedback and iterate on the user interface to improve the overall user experience.
+- Ensure that Retrieval Augmented Generation (RAG) is functioning correctly. When a prompt is created
+  with RAG data, it appears to llama-2 is considering the information along with information it has
+  been trained with. But more testing is needed.
+- Also to this end, add web pages with details on a topic that the LLM won't have been trained with. Compare prompts with
+  and without RAG.
+- Experiment with different database settings on queries such as the distance parameter on the collection query.near_vector() call.