Add Docker support

.dockerignore

@@ -0,0 +1,9 @@
+.venv
+node_modules
+frontend/node_modules
+data/
+logs/
+.git
+__pycache__
+*.pyc
+.env

docker/Dockerfile.backend

@@ -0,0 +1,6 @@
+FROM python:3.11-slim
+WORKDIR /app
+COPY requirements.txt .
+RUN pip install -r requirements.txt
+COPY . .
+CMD ["uvicorn", "src.api.main:app", "--host", "0.0.0.0", "--port", "8000"]

docker/Dockerfile.frontend

@@ -0,0 +1,10 @@
+FROM node:20-alpine AS build
+WORKDIR /app
+COPY frontend/package*.json ./
+RUN npm install
+COPY frontend/ .
+RUN npm run build
+
+FROM nginx:alpine
+COPY --from=build /app/build /usr/share/nginx/html
+EXPOSE 80

docker/docker-compose.yml

@@ -0,0 +1,30 @@
+services:
+  backend:
+    build:
+      context: ..
+      dockerfile: docker/Dockerfile.backend
+    ports:
+      - "8000:8000"
+    env_file:
+      - ../.env
+    environment:
+      - MLFLOW_TRACKING_URI=http://mlflow:5000
+    depends_on:
+      - mlflow
+
+  mlflow:
+    image: ghcr.io/mlflow/mlflow
+    ports:
+      - "5001:5000"
+    volumes:
+      - ../logs/mlflow:/mlflow
+    command: mlflow server --host 0.0.0.0 --port 5000 --allowed-hosts "mlflow,mlflow:5000,localhost:5001,127.0.0.1" --cors-allowed-origins "http://localhost:3000,http://localhost:8000,http://frontend:80"
+
+  frontend:
+    build:
+      context: ..
+      dockerfile: docker/Dockerfile.frontend
+    ports:
+      - "3000:80"
+    depends_on:
+      - backend

src/agent/nodes.py

@@ -1,7 +1,6 @@
 import numpy as np
 import torch
 from src.agent.state import AgentState
-from src.retrieval.cache import get_cache, set_cache
 from src.retrieval.vector_store import add_abstracts, query_abstracts
 from src.retrieval.pubmed import search_pubmed
 from src.monitoring.mlflow_logger import log_query_run
@@ -19,19 +18,6 @@ def extract_clean_text(response) -> str:
         return next((block["text"] for block in response.content if block.get("type") == "text"), "")
     return str(response.content)
 
-def check_cache(state: AgentState):
-    cached_result = get_cache(state["query"])
-    if cached_result:
-        return {"cache_hit": True, "abstracts": cached_result}
-    else:
-        return {"cache_hit": False}
-
-def route_after_cache(state: AgentState) -> str:
-    if state["cache_hit"]:
-        return "llm_generation"
-    return "pubmed_retrieval"
-
-
 def preprocess_query(state: AgentState):
     prompt = f"""You are an expert medical librarian. Convert the clinical question into a professional PubMed search string.
 
@@ -48,17 +34,14 @@ def preprocess_query(state: AgentState):
         Search string:"""
 
     response = _search_llm.invoke(prompt)
-    print(response.content)
     search_query = response.content.strip().replace('"', '')  # Clean quotes for API
     return {"search_query": search_query}
 
 def pubmed_retrieval(state: AgentState):
-    if not state["cache_hit"]:
-        results = search_pubmed(state["search_query"])
-        add_abstracts(results)
-        abstracts = query_abstracts(state["query"])
-        set_cache(state["query"], abstracts)
-        return {"abstracts": abstracts}
+    results = search_pubmed(state["search_query"])
+    add_abstracts(results)
+    abstracts = query_abstracts(state["query"])
+    return {"abstracts": abstracts}
 
 def llm_generation(state: AgentState):
     context = "\n\n".join([f"Title: {a['title']}\nAbstract: {a['abstract']}"

src/agent/state.py

@@ -2,7 +2,6 @@
 
 class AgentState(TypedDict):
     query: str
-    cache_hit: bool
     search_query: Optional[str]
     abstracts: list[dict]
     llm_response: Optional[str]

src/api/main.py

@@ -26,7 +26,6 @@ async def query(request: QueryRequest):
         result = agent.invoke({
             "query": request.query,
             "search_query": None,
-            "cache_hit": False,
             "abstracts": [],
             "llm_response": None,
             "claims": None,

src/retrieval/vector_store.py

@@ -37,7 +37,7 @@ def add_abstracts(abstracts: list[dict]):
     if data_list:
         get_collection().upsert(vectors=data_list)
 
-def query_abstracts(query: str, n_results: int = 5) -> list[dict]:
+def query_abstracts(query: str, n_results: int = 3) -> list[dict]:
     embedding = _embed_text(query)
     results = get_collection().query(
         vector=embedding,