Fastapi impl (#25)

* -product pitch presentation

* -llama-deploy implementation, -implemented fastapi for all templates, -partial implementation of docker for templates

* implemented the llama-deploy and workflows with simplemq and rabbitmq

* - modified the docs

* - implemented kafaka queue mechanism

* - modified the docs and version

* - implemented fastapi for simple rag

* - refactoring the code

* -implemented fastapi for simple rag

* -implemented fastapi for self correcting rag

* -modified docs for fastapi impl

---------

Co-authored-by: pavanmantha <pavan.mantha@thevaslabs.io>

Author: pavanjava

bootstraprag/templates/llamaindex/llama_deploy_with_kafka/readme.md

@@ -11,4 +11,3 @@
 - `python deploy_code.py`
 - `python deploy_workflow.py`
 - `python main.py`
-

bootstraprag/templates/llamaindex/rag_with_self_correction/api_core/__init__.py

@@ -0,0 +1,5 @@
+class Settings:
+    PROJECT_NAME: str = "Simple RAG as FastAPI Application"
+
+
+settings = Settings()

bootstraprag/templates/llamaindex/rag_with_self_correction/api_core/config.py

@@ -0,0 +1,14 @@
+from fastapi import APIRouter, Depends
+from models.payload import Payload
+from self_correction_core import SelfCorrectingRAG
+
+
+self_correcting_rag = SelfCorrectingRAG(input_dir='data', show_progress=True, no_of_retries=3)
+
+router = APIRouter(prefix="/api/v1/rag", tags=["rag"])
+
+
+@router.post(path='/query')
+def fetch_response(payload: Payload):
+    response = self_correcting_rag.query_with_source_query_engine(query=payload.query)
+    return response

bootstraprag/templates/llamaindex/rag_with_self_correction/api_routes/__init__.py

@@ -0,0 +1,110 @@
+from fastapi import FastAPI, Request
+from fastapi.openapi.utils import get_openapi
+from api_routes.apis import router
+from fastapi.middleware.cors import CORSMiddleware
+import uvicorn
+import logging
+import time
+
+logging.basicConfig(level=logging.DEBUG)
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s [%(levelname)s] %(name)s: %(message)s",
+)
+logger = logging.getLogger(__name__)
+allowed_origins = [
+    "*"
+]
+
+app = FastAPI(
+    title="My FastAPI Application",
+    description="This is a FastAPI implementation for RAG application with Swagger UI configurations.",
+    version="1.0.0",
+    docs_url="/documentation",
+    redoc_url="/redoc",
+    openapi_url="/openapi.json",
+    contact={
+        "name": "M K Pavan Kumar",
+        "linkedin": "https://www.linkedin.com",
+    },
+    license_info={
+        "name": "MIT License",
+        "url": "https://opensource.org/licenses/MIT",
+    },
+    terms_of_service="https://www.yourwebsite.com/terms/",
+)
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=allowed_origins,
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+app.include_router(router)
+
+
+# Custom OpenAPI schema generation (optional)
+def custom_openapi():
+    if app.openapi_schema:
+        return app.openapi_schema
+    openapi_schema = get_openapi(
+        title="RAG APIs",
+        version="1.0.0",
+        description="This is a custom OpenAPI schema with additional metadata.",
+        routes=app.routes,
+        tags=[
+            {
+                "name": "rag",
+                "description": "Operations for RAG query.",
+            }
+        ],
+    )
+    # Modify openapi_schema as needed
+    app.openapi_schema = openapi_schema
+    return app.openapi_schema
+
+
+app.openapi = custom_openapi
+
+
+@app.middleware("http")
+async def log_requests(request: Request, call_next):
+    try:
+        logger.info(f"Incoming request: {request.method} {request.url}")
+        response = await call_next(request)
+        logger.info(f"Response status: {response.status_code}")
+        return response
+    except Exception as e:
+        logger.exception(f"Error processing request: {e}")
+        raise e
+
+
+# Request Timing Middleware
+@app.middleware("http")
+async def add_process_time_header(request: Request, call_next):
+    start_time = time.time()
+    response = await call_next(request)
+    process_time = time.time() - start_time
+    response.headers["X-Process-Time"] = str(process_time)
+    logger.info(f"Processed in {process_time:.4f} seconds")
+    return response
+
+
+# Logging Middleware
+@app.middleware("http")
+async def log_requests(request: Request, call_next):
+    logger.info(f"Incoming request: {request.method} {request.url}")
+    response = await call_next(request)
+    logger.info(f"Response status: {response.status_code}")
+    return response
+
+
+if __name__ == "__main__":
+    uvicorn.run(
+        "apis:app",
+        host="127.0.0.1",
+        port=8000,
+        reload=True,
+        log_level="info",
+        workers=1,
+    )

bootstraprag/templates/llamaindex/rag_with_self_correction/api_routes/apis.py

@@ -0,0 +1,5 @@
+from pydantic import BaseModel
+
+
+class Payload(BaseModel):
+    query: str

bootstraprag/templates/llamaindex/rag_with_self_correction/apis.py

@@ -13,3 +13,9 @@
   - query_with_retry_query_engine(query=user_query)
   - query_with_source_query_engine(query=user_query)
   - query_with_guideline_query_engine(query=user_query)
+
+### How to expose RAG as API
+- run `python apis.py`
+- verify the swagger redoc and documentation as below
+- open browser and hit `http://localhost:8000/redoc`
+- open browser and hit `http://localhost:8000/documentation`