Dockerfile and minor changes

Dockerfile

@@ -0,0 +1,31 @@
+FROM python:3.11
+
+# Change permissions to allow writing to the directory
+RUN chmod -R 777 /apps/ai_tutor
+
+WORKDIR /apps/ai_tutor
+
+RUN pip install --upgrade pip
+RUN pip install edubotics-core
+
+# Create a logs directory and set permissions
+RUN mkdir logs && chmod 777 logs
+
+# Create a cache directory within the application's working directory
+RUN mkdir /.cache && chmod -R 777 /.cache
+
+# Expose the port the app runs on
+EXPOSE 7860
+
+RUN --mount=type=secret,id=HUGGINGFACEHUB_API_TOKEN,mode=0444,required=true 
+RUN --mount=type=secret,id=OPENAI_API_KEY,mode=0444,required=true 
+RUN --mount=type=secret,id=CHAINLIT_URL,mode=0444,required=true 
+RUN --mount=type=secret,id=LITERAL_API_URL,mode=0444,required=true 
+RUN --mount=type=secret,id=LLAMA_CLOUD_API_KEY,mode=0444,required=true 
+RUN --mount=type=secret,id=OAUTH_GOOGLE_CLIENT_ID,mode=0444,required=true 
+RUN --mount=type=secret,id=OAUTH_GOOGLE_CLIENT_SECRET,mode=0444,required=true 
+RUN --mount=type=secret,id=LITERAL_API_KEY_LOGGING,mode=0444,required=true 
+RUN --mount=type=secret,id=CHAINLIT_AUTH_SECRET,mode=0444,required=true 
+
+# Default command to run the application
+CMD vectorstore_creator --config_file config/config.yml --project_config_file config/project_config.yml && python app.py

README.md

@@ -4,7 +4,7 @@
 
 This repository contains an LLM-based chatbot designed for the [DS701: Tools for Data Science](https://tools4ds.github.io/fa2024/) course at Boston University. The chatbot serves as an interactive learning assistant, helping students with course-related queries, explanations of concepts, and guidance on data science tools. It is powered by [edubotics-core](https://github.com/edubotics-ai/edubotics-core) a package of modules for data loading, vector store creation and management.
 
-The chatbot will be available on HuggingFace Spaces soon. Lecture slides are available [here].
+The chatbot will be available on HuggingFace Spaces soon. Lecture slides are available [here](https://tools4ds.github.io/DS701-Course-Notes/).
 
 ## Features
 
@@ -46,7 +46,9 @@ Note: Make sure to use Python 3.9 or later.
 
    `pip install edubotics-core`
 
-4. Run the chatbot
+4. Set up environment variables. See `apps/ai_tutor/.env.example` for reference.
+
+5. Run the chatbot
 
    ```python
     cd apps/ai-tutor

apps/ai_tutor/app.py

@@ -387,4 +387,4 @@ mount_chainlit(app=app, target="chainlit_app.py", path=CHAINLIT_PATH)
 if __name__ == "__main__":
     import uvicorn
 
-    uvicorn.run(app, host="127.0.0.1", port=8000)
+    uvicorn.run(app, host="0.0.0.0", port=7860)

apps/ai_tutor/config/config.yml

@@ -3,12 +3,12 @@ log_chunk_dir: 'storage/logs/chunks' # str
 device: 'cpu' # str [cuda, cpu]
 
 vectorstore:
-  load_from_HF: True # bool
+  load_from_HF: False # bool
   reparse_files: True # bool
   data_path: 'storage/data' # str
   url_file_path: 'storage/data/urls.txt' # str
   expand_urls: True # bool
-  db_option : 'RAGatouille' # str [FAISS, Chroma, RAGatouille, RAPTOR]
+  db_option : 'FAISS' # str [FAISS, Chroma, RAGatouille, RAPTOR]
   db_path : 'vectorstores' # str
   model : 'sentence-transformers/all-MiniLM-L6-v2' # str [sentence-transformers/all-MiniLM-L6-v2, text-embedding-ada-002']
   search_top_k : 3 # int
@@ -39,7 +39,7 @@ llm_params:
     filename: 'tinyllama-1.1b-chat-v1.0.Q5_0.gguf' # Specific name of gguf file in the repo
     model_path: 'storage/models/tinyllama-1.1b-chat-v1.0.Q5_0.gguf' # Path to the model file
   stream: False # bool
-  pdf_reader: 'gpt' # str [llama, pymupdf, gpt]
+  pdf_reader: 'pymupdf' # str [llama, pymupdf, gpt]
 
 chat_logging:
   log_chat: True # bool