Upload 4 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+combined_chunks.json filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,17 @@
+FROM python:3.10-slim
+
+# Set working directory
+WORKDIR /app
+
+# Copy requirements and install dependencies
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy rest of the app
+COPY . .
+
+# Expose the port (default Flask)
+EXPOSE 7860
+
+# Start the app
+CMD ["python", "app.py"]

app.py

@@ -0,0 +1,48 @@
+import json
+import numpy as np
+from fastapi import FastAPI, Request
+from pydantic import BaseModel
+from sentence_transformers import SentenceTransformer
+from fastapi.middleware.cors import CORSMiddleware
+
+# === Setup ===
+app = FastAPI()
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# === Load chunks and their embeddings ===
+with open("combined_chunks.json", "r", encoding="utf-8") as f:
+    data = json.load(f)
+
+texts = [item["text"] for item in data]
+embeddings = np.array([item["embedding"] for item in data])
+
+# === Load Model ===
+model = SentenceTransformer("all-MiniLM-L6-v2")
+
+# === API Schema ===
+class Query(BaseModel):
+    query: str
+
+# === Similarity Function ===
+def cosine_similarity(query_vec, db_vecs):
+    query_norm = np.linalg.norm(query_vec)
+    db_norms = np.linalg.norm(db_vecs, axis=1)
+    return np.dot(db_vecs, query_vec) / (db_norms * query_norm + 1e-10)
+
+@app.post("/vector-api/search")
+async def search_vector(q: Query):
+    query_embedding = model.encode(q.query)
+    scores = cosine_similarity(query_embedding, embeddings)
+    top_indices = np.argsort(scores)[::-1][:5]
+    top_results = [texts[i] for i in top_indices]
+    return {"results": top_results}
+
+@app.get("/")
+def root():
+    return {"message": "Lightweight Vector API is running!"}

combined_chunks.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f3ee7f4a8e47c0114b419847657e2d89d7722efd3c24544f48b634f82601f7a
+size 129202002

requirements.txt

@@ -0,0 +1,5 @@
+flask
+sentence-transformers
+numpy
+chromadb
+faiss-cpu   # Optional if using FAISS