Feature image search

.env

@@ -1,4 +1,6 @@
 DEFAULT_MODEL="qwen3:0.6b"
+DEFAULT_IMAGE_MODEL="qwen2.5vl:3b"
+
 OLLAMA_URL="http://ollama:11434"
 DB_PATH="/data/enmemoryalpha_db"
 COLLECTION_NAME="memoryalpha"

.github/workflows/ci-build.yml

@@ -52,22 +52,6 @@ jobs:
           exit 1
         fi
 
-    - name: Test streaming endpoint
-      run: |
-        # Test the streaming endpoint
-        response=$(timeout 30 curl -s -N -H "Accept: text/event-stream" \
-          "http://localhost:8000/memoryalpha/rag/stream?question=What%20is%20a%20Transporter?&thinkingmode=DISABLED&max_tokens=50&top_k=3" \
-          | head -10)
-
-        # Check if streaming response contains data events
-        if echo "$response" | grep -q "data:"; then
-          echo "✅ Streaming endpoint test passed"
-        else
-          echo "❌ Streaming endpoint test failed - no streaming data found"
-          echo "Response: $response"
-          exit 1
-        fi
-
     - name: Generate OpenAPI spec
       run: |
         # Download OpenAPI spec

Dockerfile

@@ -3,14 +3,16 @@ FROM python:3.12-slim-bullseye AS devcontainer
 ARG DEBIAN_FRONTEND=noninteractive
 
 RUN apt-get update &&\
-    apt-get -y install curl wget git
+    apt-get -y install jq curl wget git
 
 COPY ./requirements.txt /tmp/pip-tmp/
 RUN pip install --no-cache-dir -r /tmp/pip-tmp/requirements.txt \
     && rm -rf /tmp/pip-tmp
 
 WORKDIR /data
-RUN wget https://github.com/aniongithub/memoryalpha-vectordb/releases/latest/download/enmemoryalpha_db.tar.gz &&\
+
+ARG MEMORYALPHA_DB_RELEASE=v0.5.0
+RUN wget https://github.com/aniongithub/memoryalpha-vectordb/releases/download/${MEMORYALPHA_DB_RELEASE}/enmemoryalpha_db.tar.gz &&\
     tar -xzf enmemoryalpha_db.tar.gz &&\
     rm enmemoryalpha_db.tar.gz &&\
     chmod -R 0777 /data

README.md

@@ -6,7 +6,7 @@ A REST API for Retrieval-Augmented Generation (RAG) over Star Trek's MemoryAlpha
 
 ## Overview
 
-This project provides a streaming REST API that enables natural language queries over the comprehensive Star Trek MemoryAlpha database. It uses the vectorized database from [memoryalpha-vectordb](https://github.com/aniongithub/memoryalpha-vectordb) and combines it with local LLMs via Ollama to provide accurate, context-aware responses about Star Trek lore.
+This project provides a REST API that enables natural language queries over the comprehensive Star Trek MemoryAlpha database. It uses the vectorized database from [memoryalpha-vectordb](https://github.com/aniongithub/memoryalpha-vectordb) and combines it with local LLMs via Ollama to provide accurate, context-aware responses about Star Trek lore.
 
 The system implements:
 
@@ -169,7 +169,7 @@ graph TD
 
 ### Components
 
-- **FastAPI**: REST API framework with streaming support
+- **FastAPI**: REST API framework and OpenAPI spec generation
 - **ChromaDB**: Vector database for document storage and retrieval
 - **Ollama**: Local LLM inference server
 - **Cross-Encoder**: Document reranking for improved relevance

api/main.py

@@ -2,8 +2,8 @@
 from contextlib import asynccontextmanager
 from fastapi import FastAPI
 from .memoryalpha.health import router as health_router
-from .memoryalpha.stream import router as stream_router
 from .memoryalpha.ask import router as ask_router
+from .memoryalpha.identify import router as identify_router
 
 # Configure logging
 logging.basicConfig(level=logging.INFO)
@@ -21,5 +21,5 @@ async def lifespan(app: FastAPI):
 app = FastAPI(lifespan=lifespan)
 
 app.include_router(health_router)
-app.include_router(stream_router)
-app.include_router(ask_router)
+app.include_router(ask_router)
+app.include_router(identify_router)

api/memoryalpha/identify.py

@@ -0,0 +1,31 @@
+from fastapi import APIRouter, File, UploadFile, Query
+from fastapi.responses import JSONResponse
+import tempfile
+import os
+from .rag import MemoryAlphaRAG
+
+router = APIRouter()
+
+# Singleton or global instance for demo; in production, manage lifecycle properly
+rag_instance = MemoryAlphaRAG()
+
+@router.post("/memoryalpha/rag/identify", summary="Multimodal Image Search")
+def identify_endpoint(
+    file: UploadFile = File(...),
+    top_k: int = Query(5, description="Number of results to return")
+):
+    """
+    Accepts an image file upload, performs multimodal image search, and returns results.
+    """
+    try:
+        # Save uploaded file to a temp location
+        with tempfile.NamedTemporaryFile(delete=False, suffix=os.path.splitext(file.filename)[-1]) as tmp:
+            tmp.write(file.file.read())
+            image_path = tmp.name
+        # Perform image search
+        results = rag_instance.search_image(image_path, top_k=top_k)
+        # Clean up temp file
+        os.remove(image_path)
+        return JSONResponse(content=results)
+    except Exception as e:
+        return JSONResponse(status_code=500, content={"error": str(e)})