Usando o FastAPI para DB vetorial

main.py

@@ -2,17 +2,64 @@
 """
 Data Scientist.: Dr. Eddy Giusepe Chirinos Isidro
 
+Link de estudo ---> https://levelup.gitconnected.com/building-vector-databases-with-fastapi-and-chromadb-0a1cd96fab08
+
 Executar este Script
 ====================
 O seguinte comando iniciará o servidor:
 
 $ fastapi dev main.py
 """
-from fastapi import FastAPI
+from fastapi import FastAPI, HTTPException
+from langchain_chroma import Chroma
+from langchain_community.embeddings.sentence_transformer import (
+                                                                 SentenceTransformerEmbeddings,
+                                                                )
+
+from models import Query
+from functions import create_db, delete_persisted_db
 
-app = FastAPI()
+
+app = FastAPI(title='🤗 Usando FastAPI e Chroma para construir um DB Vetorial 🤗',
+              version='1.0',
+              description="""Data Scientist.: PhD. Eddy Giusepe Chirinos Isidro\n
+              Projeto end-to-end para DBVector""")
 
 
 @app.get("/")
 async def root():
-    return {"message": "Whatchamacallit"}
+    return {"message": "Bem-vindo ao DB vetorial com FastAPI e ChromaDB!"}
+
+# Criar o Database:
+@app.get("/create/")
+async def create_database():
+    create_db()
+    return {"message": "Database criado."}
+
+#Delete database
+@app.delete("/delete/")
+async def delete_database():
+    try:
+        delete_persisted_db()
+        return {"message": "Database excluído."}
+    except FileNotFoundError as e:
+        raise HTTPException(status_code=404, detail=str(e))
+    
+#Fetch Chunks
+@app.post("/neighbours/")
+async def fetch_item(query: Query):
+    embedding_function = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2",
+                                                       model_kwargs = {'device': 'cpu'}
+                                                      )
+    
+    db = Chroma(persist_directory="./chroma_db",
+                embedding_function=embedding_function
+               )
+    
+    #print(db.get().keys())
+    #print(sorted(db.get()["ids"], key=int))
+
+    results = db.similarity_search(query.query, k=query.neighbours)
+
+    return {"message": "Vizinhos mais próximos encontrados.", "results": results}
+