remove unused files, imports

.github/workflows/run_server.sh

@@ -1,48 +0,0 @@
-#!/bin/bash
-
-# Get the directory of the script
-SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-
-# Navigate to the project root (2 levels up from .github/workflows)
-PROJECT_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
-
-# Move to the project root
-cd "$PROJECT_ROOT"
-
-# Start Flask server in the background
-python -m src.api.controller &
-SERVER_PID=$!
-
-# Function to check if server is up
-wait_for_server() {
-    echo "Waiting for Flask server to start..."
-    local max_attempts=100
-    local attempt=0
-    
-    while [ $attempt -lt $max_attempts ]; do
-        if curl -s http://localhost:9998/ > /dev/null 2>&1; then
-            echo "Server is up!"
-            return 0
-        fi
-        
-        attempt=$((attempt + 1))
-        echo "Attempt $attempt/$max_attempts - Server not ready yet, waiting..."
-        sleep 1
-    done
-    
-    echo "Server failed to start after $max_attempts attempts"
-    kill $SERVER_PID
-    return 1
-}
-
-# Wait for server to be ready
-wait_for_server || exit 1
-
-# Make the actual request once server is ready
-echo "Making API request..."
-curl -X POST -i http://localhost:9998/api/conversations \
-    -d '{ "prompt": "describe a random planet in our solar system in 10 words or less" }' \
-    -H "Content-Type: application/json" || exit 1
-echo
-
-exit 0

src/api/controller.flask.py

@@ -1,26 +0,0 @@
-import logging
-from flask import Flask, jsonify, request
-from waitress import serve
-from src.llm.llm import Phi3LanguageModel
-from src.llm.llm_rag import Phi3LanguageModelWithRag
-
-app = Flask(__name__)
-
-@app.route('/', methods=['GET'])
-def health_check():
-    return f"Server is running\n", 200
-
-@app.route('/api/conversations', methods=['POST'])
-def get_llm_response():
-    prompt = request.json['prompt']
-    service = Phi3LanguageModel()
-    response = service.invoke(user_input=prompt)
-    return jsonify({'response': response}), 201
-
-if __name__ == '__main__':
-    logger = logging.Logger(name='Flask API', level=logging.DEBUG)
-    print('test')
-    logger.debug('running...')
-
-    # TODO set up port # as env var
-    serve(app, host='0.0.0.0', port=9999)

src/api/controller.py

@@ -1,5 +1,4 @@
 import json
-import time
 import traceback
 
 

src/api/http_api.py

@@ -1,35 +1,35 @@
-"""
-    Usage:
-        $ uvicorn src.api.http_api:app --host 0.0.0.0 --port 9999
-"""
+# """
+#     Usage:
+#         $ uvicorn src.api.http_api:app --host 0.0.0.0 --port 9999
+# """
 
-from fastapi import FastAPI
-from pathlib import Path
-from pydantic import BaseModel
-from src.llm.llm import Phi3LanguageModel
+# from fastapi import FastAPI
+# from pathlib import Path
+# from pydantic import BaseModel
+# from src.llm.llm import Phi3LanguageModel
 
 
-STATIC_PATH = Path(__file__).parent.absolute() / 'static'
+# STATIC_PATH = Path(__file__).parent.absolute() / 'static'
 
-app = FastAPI(
-    title='Phi-3 Language Model API',
-    description='HTTP API for interacting with Phi-3 Mini 4K language model'
-)
+# app = FastAPI(
+#     title='Phi-3 Language Model API',
+#     description='HTTP API for interacting with Phi-3 Mini 4K language model'
+# )
 
-class LanguageModelPrompt(BaseModel):
-    prompt: str
+# class LanguageModelPrompt(BaseModel):
+#     prompt: str
 
-class LanguageModelResponse(BaseModel):
-    response: str
+# class LanguageModelResponse(BaseModel):
+#     response: str
 
 
-@app.get('/', response_model=str)
-async def health_check():
-    return 'success'
+# @app.get('/', response_model=str)
+# async def health_check():
+#     return 'success'
 
 
-@app.post('/api/conversations', response_model=LanguageModelResponse)
-async def get_llm_conversation_response(request: LanguageModelPrompt):
-    service = Phi3LanguageModel()
-    response = service.invoke(user_input=request.prompt)
-    return LanguageModelResponse(response=response)
+# @app.post('/api/conversations', response_model=LanguageModelResponse)
+# async def get_llm_conversation_response(request: LanguageModelPrompt):
+#     service = Phi3LanguageModel()
+#     response = service.invoke(user_input=request.prompt)
+#     return LanguageModelResponse(response=response)

src/llm/llm.py

@@ -5,16 +5,10 @@ RAG implementation with local Phi-3-mini-4k-instruct-onnx and embeddings
 import logging
 import os
 import sys
-from typing import List
 
 # LangChain imports
 from langchain_huggingface import HuggingFacePipeline
-from langchain_huggingface import HuggingFaceEmbeddings
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain_community.vectorstores import FAISS
-from langchain.chains import LLMChain
 from langchain.prompts import PromptTemplate
-from langchain.schema import Document
 from langchain_core.output_parsers import StrOutputParser
 from langchain_core.runnables import RunnablePassthrough