Rename app.py to chromedb_service.py

app.py

@@ -1,78 +0,0 @@
-#!/usr/bin/env python
-
-from __future__ import annotations
-
-import cv2
-import gradio as gr
-import huggingface_hub
-import insightface
-import numpy as np
-import onnxruntime as ort
-from PIL import Image
-
-TITLE = "insightface Person Detection"
-DESCRIPTION = "https://github.com/deepinsight/insightface/tree/master/examples/person_detection"
-
-def load_model():
-    path = huggingface_hub.hf_hub_download("public-data/insightface", "models/scrfd_person_2.5g.onnx")
-    options = ort.SessionOptions()
-    options.intra_op_num_threads = 8
-    options.inter_op_num_threads = 8
-    session = ort.InferenceSession(
-        path, sess_options=options, providers=["CPUExecutionProvider", "CUDAExecutionProvider"]
-    )
-    model = insightface.model_zoo.retinaface.RetinaFace(model_file=path, session=session)
-    return model
-
-def detect_person(
-    img: np.ndarray, detector: insightface.model_zoo.retinaface.RetinaFace
-) -> tuple[np.ndarray, np.ndarray]:
-    bboxes, kpss = detector.detect(img)
-    bboxes = np.round(bboxes[:, :4]).astype(int)
-    kpss = np.round(kpss).astype(int)
-    kpss[:, :, 0] = np.clip(kpss[:, :, 0], 0, img.shape[1])
-    kpss[:, :, 1] = np.clip(kpss[:, :, 1], 0, img.shape[0])
-    vbboxes = bboxes.copy()
-    vbboxes[:, 0] = kpss[:, 0, 0]
-    vbboxes[:, 1] = kpss[:, 0, 1]
-    vbboxes[:, 2] = kpss[:, 4, 0]
-    vbboxes[:, 3] = kpss[:, 4, 1]
-    return bboxes, vbboxes
-
-def visualize(image: np.ndarray, bboxes: np.ndarray, vbboxes: np.ndarray) -> list[np.ndarray]:
-    person_images = []
-    for i in range(bboxes.shape[0]):
-        bbox = bboxes[i]
-        x1, y1, x2, y2 = bbox
-        person_img = image[y1:y2, x1:x2]
-        
-        # Convert numpy array to PIL Image and append
-        pil_img = Image.fromarray(person_img)
-        person_images.append(pil_img)
-
-    return person_images
-
-detector = load_model()
-detector.prepare(-1, nms_thresh=0.5, input_size=(640, 640))
-
-def detect(image: np.ndarray) -> list[np.ndarray]:
-    if image is None:
-        return []
-
-    image = image[:, :, ::-1]  # RGB -> BGR
-    bboxes, vbboxes = detect_person(image, detector)
-    person_images = visualize(image, bboxes, vbboxes)
-    
-    # Convert PIL images to numpy arrays and return
-    return [np.array(img) for img in person_images]
-
-demo = gr.Interface(
-    fn=detect,
-    inputs=gr.Image(label="Input", type="numpy"),
-    outputs=gr.Gallery(label="Detected Persons"),
-    title=TITLE,
-    description=DESCRIPTION,
-)
-
-if __name__ == "__main__":
-    demo.queue(max_size=10).launch()

chromedb_service.py

@@ -0,0 +1,87 @@
+import requests
+from PIL import Image
+import numpy as np
+import tensorflow as tf
+import chromadb
+from chromadb.config import Settings
+
+# Fonction pour télécharger une image depuis une URL
+def download_image(url):
+    response = requests.get(url)
+    if response.status_code != 200:
+        raise Exception(f"Erreur lors du téléchargement de l'image : {response.status_code}")
+    return Image.open(io.BytesIO(response.content))
+
+# Fonction pour encoder une image en vecteurs à partir d'une URL
+def encode_image_from_url(image_url):
+    image = download_image(image_url)
+    image = image.resize((224, 224))  # Redimensionner à 224x224
+    image_array = np.array(image) / 255.0  # Normaliser les valeurs des pixels
+    image_tensor = tf.convert_to_tensor(image_array, dtype=tf.float32)
+    image_tensor = tf.expand_dims(image_tensor, axis=0)  # Ajouter une dimension pour le batch
+
+    # Charger le modèle MobileNet
+    model = tf.keras.applications.MobileNetV2(weights='imagenet', include_top=False, pooling='avg')
+    embeddings = model(image_tensor)
+    return embeddings.numpy()[0]  # Retourner les vecteurs sous forme de tableau
+
+# Ajouter une image dans ChromaDB
+def add_image_to_chroma(collection_name, id, image_url, metadata):
+    vector = encode_image_from_url(image_url)
+    chroma_client = chromadb.Client(Settings(path="https://stable-diffusion-engine.oneiro-lego.com"))
+    collection = chroma_client.get_or_create_collection(
+        name=collection_name, dimension=len(vector)
+    )
+    collection.add(
+        ids=[id],
+        embeddings=[vector],
+        metadatas=[metadata]
+    )
+    print(f"Image {image_url} ajoutée avec succès !")
+
+# Ajouter un document dans ChromaDB
+def add_document(collection_name, id, text, metadata):
+    chroma_client = chromadb.Client(Settings(path="https://stable-diffusion-engine.oneiro-lego.com"))
+    collection = chroma_client.get_or_create_collection(name=collection_name)
+    collection.upsert(
+        documents=[text],
+        ids=[id],
+        metadatas=[metadata]
+    )
+    print(f"Document {id} ajouté avec succès !")
+
+# Supprimer un document dans ChromaDB
+def delete_document(collection_name, id):
+    chroma_client = chromadb.Client(Settings(path="https://stable-diffusion-engine.oneiro-lego.com"))
+    collection = chroma_client.get_or_create_collection(name=collection_name)
+    collection.delete(ids=[id])
+    print(f"Document {id} supprimé avec succès !")
+
+# Supprimer une collection dans ChromaDB
+def delete_collection(collection_name):
+    chroma_client = chromadb.Client(Settings(path="https://stable-diffusion-engine.oneiro-lego.com"))
+    chroma_client.delete_collection(name=collection_name)
+    print(f"Collection {collection_name} supprimée avec succès !")
+
+# Recherche dans une collection
+def search(collection_name, query, n_results):
+    chroma_client = chromadb.Client(Settings(path="https://stable-diffusion-engine.oneiro-lego.com"))
+    collection = chroma_client.get_or_create_collection(name=collection_name)
+    results = collection.query(
+        query_texts=[query],
+        n_results=n_results
+    )
+    return parse_chromadb_response(results)
+
+# Analyse des réponses de ChromaDB
+def parse_chromadb_response(response):
+    results = [
+        {
+            "id": response["ids"][0][i],
+            "distance": response["distances"][0][i],
+            "document": response["documents"][0][i],
+            "metadata": response["metadatas"][0].get(i)
+        }
+        for i in range(len(response["ids"][0]))
+    ]
+    return results