ahnlich-client-py 0.2.0__tar.gz → 0.3.0__tar.gz

{ahnlich_client_py-0.2.0 → ahnlich_client_py-0.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ahnlich-client-py
-Version: 0.2.0
+Version: 0.3.0
 Summary: A python client for interacting with Ahnlich DB and AI
 Author: David Onuh
 Author-email: davidonuh1@gmail.com
@@ -790,6 +790,105 @@ async with Channel(host="127.0.0.1", port=1370) as channel:
     )
 ```
 
+### Convert Store Input To Embeddings
+
+Converts raw inputs (text, images, audio) into embeddings without storing them.
+
+**Basic Example:**
+```python
+from grpclib.client import Channel
+from ahnlich_client_py.grpc.services.ai_service import AiServiceStub
+from ahnlich_client_py.grpc.ai import query as ai_query
+from ahnlich_client_py.grpc.ai.models import AiModel
+from ahnlich_client_py.grpc.ai import preprocess
+from ahnlich_client_py.grpc import keyval
+
+async with Channel(host="127.0.0.1", port=1370) as channel:
+    client = AiServiceStub(channel)
+    
+    inputs = [keyval.StoreInput(raw_string="Hello world")]
+    
+    response = await client.convert_store_input_to_embeddings(
+        ai_query.ConvertStoreInputToEmbeddings(
+            store_inputs=inputs,
+            preprocess_action=preprocess.PreprocessAction.NoPreprocessing,
+            model=AiModel.ALL_MINI_LM_L6_V2,
+        )
+    )
+    
+    # Access embeddings
+    for item in response.values:
+        if item.single and item.single.embedding:
+            print(f"Embedding size: {len(item.single.embedding.key)}")
+```
+
+**Face Detection with Bounding Box Metadata (v0.2.1+):**
+
+Buffalo-L and SFace models return normalized bounding boxes (0-1 range) and confidence scores:
+
+```python
+from grpclib.client import Channel
+from ahnlich_client_py.grpc.services.ai_service import AiServiceStub
+from ahnlich_client_py.grpc.ai import query as ai_query
+from ahnlich_client_py.grpc.ai.models import AiModel
+from ahnlich_client_py.grpc.ai import preprocess
+from ahnlich_client_py.grpc import keyval
+
+async with Channel(host="127.0.0.1", port=1370) as channel:
+    client = AiServiceStub(channel)
+    
+    # Load image
+    with open("group_photo.jpg", "rb") as f:
+        image_bytes = f.read()
+    
+    inputs = [keyval.StoreInput(image=image_bytes)]
+    
+    response = await client.convert_store_input_to_embeddings(
+        ai_query.ConvertStoreInputToEmbeddings(
+            store_inputs=inputs,
+            preprocess_action=preprocess.PreprocessAction.ModelPreprocessing,
+            model=AiModel.BUFFALO_L,
+        )
+    )
+    
+    # Process detected faces with metadata
+    for item in response.values:
+        if item.multiple:
+            print(f"Detected {len(item.multiple.embeddings)} faces")
+            
+            for i, face_data in enumerate(item.multiple.embeddings):
+                # Access embedding
+                embedding = face_data.embedding.key  # 512-dim for Buffalo_L
+                print(f"Face {i}: {len(embedding)}-dim embedding")
+                
+                # Access bounding box metadata
+                if face_data.metadata:
+                    metadata = face_data.metadata.value
+                    
+                    bbox_x1 = float(metadata["bbox_x1"].value)
+                    bbox_y1 = float(metadata["bbox_y1"].value)
+                    bbox_x2 = float(metadata["bbox_x2"].value)
+                    bbox_y2 = float(metadata["bbox_y2"].value)
+                    confidence = float(metadata["confidence"].value)
+                    
+                    print(f"  BBox: ({bbox_x1:.3f}, {bbox_y1:.3f}) "
+                          f"to ({bbox_x2:.3f}, {bbox_y2:.3f})")
+                    print(f"  Confidence: {confidence:.3f}")
+```
+
+**Metadata Fields:**
+- `bbox_x1`, `bbox_y1`, `bbox_x2`, `bbox_y2`: Normalized coordinates (0.0-1.0)
+- `confidence`: Detection confidence score (0.0-1.0)
+
+To convert to pixel coordinates:
+```python
+from PIL import Image
+img = Image.open("photo.jpg")
+width, height = img.size
+pixel_x1 = int(bbox_x1 * width)
+pixel_y1 = int(bbox_y1 * height)
+```
+
 
 ## Bulk Requests
 Clients have the ability to send multiple requests at once, and these requests will be handled sequentially. The builder class takes care of this. The response is a list of all individual request responses.

{ahnlich_client_py-0.2.0 → ahnlich_client_py-0.3.0}/README.md

@@ -773,6 +773,105 @@ async with Channel(host="127.0.0.1", port=1370) as channel:
     )
 ```
 
+### Convert Store Input To Embeddings
+
+Converts raw inputs (text, images, audio) into embeddings without storing them.
+
+**Basic Example:**
+```python
+from grpclib.client import Channel
+from ahnlich_client_py.grpc.services.ai_service import AiServiceStub
+from ahnlich_client_py.grpc.ai import query as ai_query
+from ahnlich_client_py.grpc.ai.models import AiModel
+from ahnlich_client_py.grpc.ai import preprocess
+from ahnlich_client_py.grpc import keyval
+
+async with Channel(host="127.0.0.1", port=1370) as channel:
+    client = AiServiceStub(channel)
+    
+    inputs = [keyval.StoreInput(raw_string="Hello world")]
+    
+    response = await client.convert_store_input_to_embeddings(
+        ai_query.ConvertStoreInputToEmbeddings(
+            store_inputs=inputs,
+            preprocess_action=preprocess.PreprocessAction.NoPreprocessing,
+            model=AiModel.ALL_MINI_LM_L6_V2,
+        )
+    )
+    
+    # Access embeddings
+    for item in response.values:
+        if item.single and item.single.embedding:
+            print(f"Embedding size: {len(item.single.embedding.key)}")
+```
+
+**Face Detection with Bounding Box Metadata (v0.2.1+):**
+
+Buffalo-L and SFace models return normalized bounding boxes (0-1 range) and confidence scores:
+
+```python
+from grpclib.client import Channel
+from ahnlich_client_py.grpc.services.ai_service import AiServiceStub
+from ahnlich_client_py.grpc.ai import query as ai_query
+from ahnlich_client_py.grpc.ai.models import AiModel
+from ahnlich_client_py.grpc.ai import preprocess
+from ahnlich_client_py.grpc import keyval
+
+async with Channel(host="127.0.0.1", port=1370) as channel:
+    client = AiServiceStub(channel)
+    
+    # Load image
+    with open("group_photo.jpg", "rb") as f:
+        image_bytes = f.read()
+    
+    inputs = [keyval.StoreInput(image=image_bytes)]
+    
+    response = await client.convert_store_input_to_embeddings(
+        ai_query.ConvertStoreInputToEmbeddings(
+            store_inputs=inputs,
+            preprocess_action=preprocess.PreprocessAction.ModelPreprocessing,
+            model=AiModel.BUFFALO_L,
+        )
+    )
+    
+    # Process detected faces with metadata
+    for item in response.values:
+        if item.multiple:
+            print(f"Detected {len(item.multiple.embeddings)} faces")
+            
+            for i, face_data in enumerate(item.multiple.embeddings):
+                # Access embedding
+                embedding = face_data.embedding.key  # 512-dim for Buffalo_L
+                print(f"Face {i}: {len(embedding)}-dim embedding")
+                
+                # Access bounding box metadata
+                if face_data.metadata:
+                    metadata = face_data.metadata.value
+                    
+                    bbox_x1 = float(metadata["bbox_x1"].value)
+                    bbox_y1 = float(metadata["bbox_y1"].value)
+                    bbox_x2 = float(metadata["bbox_x2"].value)
+                    bbox_y2 = float(metadata["bbox_y2"].value)
+                    confidence = float(metadata["confidence"].value)
+                    
+                    print(f"  BBox: ({bbox_x1:.3f}, {bbox_y1:.3f}) "
+                          f"to ({bbox_x2:.3f}, {bbox_y2:.3f})")
+                    print(f"  Confidence: {confidence:.3f}")
+```
+
+**Metadata Fields:**
+- `bbox_x1`, `bbox_y1`, `bbox_x2`, `bbox_y2`: Normalized coordinates (0.0-1.0)
+- `confidence`: Detection confidence score (0.0-1.0)
+
+To convert to pixel coordinates:
+```python
+from PIL import Image
+img = Image.open("photo.jpg")
+width, height = img.size
+pixel_x1 = int(bbox_x1 * width)
+pixel_y1 = int(bbox_y1 * height)
+```
+
 
 ## Bulk Requests
 Clients have the ability to send multiple requests at once, and these requests will be handled sequentially. The builder class takes care of this. The response is a list of all individual request responses.

ahnlich_client_py-0.3.0/VERSION

@@ -0,0 +1,2 @@
+CLIENT="0.3.0"
+PROTOCOL="0.3.0"

{ahnlich_client_py-0.2.0 → ahnlich_client_py-0.3.0}/ahnlich_client_py/grpc/ai/models/__init__.py

@@ -20,6 +20,7 @@ class AiModel(betterproto.Enum):
     SFACE_YUNET = 8
     CLAP_AUDIO = 9
     CLAP_TEXT = 10
+    JINA_EMBEDDINGS_V2_BASE_CODE = 11
 
 
 class AiStoreInputType(betterproto.Enum):

{ahnlich_client_py-0.2.0 → ahnlich_client_py-0.3.0}/ahnlich_client_py/grpc/ai/server/__init__.py

@@ -92,16 +92,24 @@ class AiStoreInfo(betterproto.Message):
     )
 
 
+@dataclass(eq=False, repr=False)
+class EmbeddingWithMetadata(betterproto.Message):
+    embedding: "__keyval__.StoreKey" = betterproto.message_field(1)
+    metadata: Optional["__keyval__.StoreValue"] = betterproto.message_field(
+        2, optional=True
+    )
+
+
 @dataclass(eq=False, repr=False)
 class MultipleEmbedding(betterproto.Message):
-    embeddings: List["__keyval__.StoreKey"] = betterproto.message_field(1)
+    embeddings: List["EmbeddingWithMetadata"] = betterproto.message_field(1)
 
 
 @dataclass(eq=False, repr=False)
 class SingleInputToEmbedding(betterproto.Message):
     input: "__keyval__.StoreInput" = betterproto.message_field(1)
     multiple: "MultipleEmbedding" = betterproto.message_field(2, group="variant")
-    single: "__keyval__.StoreKey" = betterproto.message_field(3, group="variant")
+    single: "EmbeddingWithMetadata" = betterproto.message_field(3, group="variant")
 
 
 @dataclass(eq=False, repr=False)

{ahnlich_client_py-0.2.0 → ahnlich_client_py-0.3.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "ahnlich-client-py"
-version = "0.2.0"
+version = "0.3.0"
 description = "A python client for interacting with Ahnlich DB and AI"
 authors = ["David Onuh <davidonuh1@gmail.com>"]
 readme = "README.md"

ahnlich_client_py-0.2.0/VERSION

@@ -1,2 +0,0 @@
-CLIENT="0.2.0"
-PROTOCOL="0.2.0"