From 49fa4914541f6018cab310d8fc6a0ad77c6b0bd2 Mon Sep 17 00:00:00 2001
From: Ankit raj <113342181+ankit-v2-3@users.noreply.github.com>
Date: Wed, 26 Jun 2024 20:41:06 +0530
Subject: [PATCH 1/6] fix: search and vision interface

---
 videodb/__init__.py   |  2 ++
 videodb/_constants.py |  4 ++--
 videodb/collection.py |  4 ++++
 videodb/search.py     | 21 +++++++++++++++++----
 videodb/video.py      | 25 ++++++++++++++++++-------
 5 files changed, 43 insertions(+), 13 deletions(-)

diff --git a/videodb/__init__.py b/videodb/__init__.py
index b96558d..7aa45a7 100644
--- a/videodb/__init__.py
+++ b/videodb/__init__.py
@@ -7,6 +7,7 @@
 from videodb._utils._video import play_stream
 from videodb._constants import (
     VIDEO_DB_API,
+    IndexType,
     SceneExtractionType,
     MediaType,
     SearchType,
@@ -30,6 +31,7 @@
     "VideodbError",
     "AuthenticationError",
     "InvalidRequestError",
+    "IndexType",
     "SearchError",
     "play_stream",
     "MediaType",
diff --git a/videodb/_constants.py b/videodb/_constants.py
index e0ed017..f45141f 100644
--- a/videodb/_constants.py
+++ b/videodb/_constants.py
@@ -18,12 +18,12 @@ class SearchType:
 
 
 class IndexType:
-    semantic = "semantic"
+    spoken = "spoken"
     scene = "scene"
 
 
 class SceneExtractionType:
-    scene_based = "scene"
+    shot_based = "shot"
     time_based = "time"
 
 
diff --git a/videodb/collection.py b/videodb/collection.py
index 040979f..25bcb47 100644
--- a/videodb/collection.py
+++ b/videodb/collection.py
@@ -10,6 +10,7 @@
 )
 from videodb._constants import (
     ApiPath,
+    IndexType,
     SearchType,
 )
 from videodb.video import Video
@@ -100,6 +101,7 @@ def search(
         self,
         query: str,
         search_type: Optional[str] = SearchType.semantic,
+        index_type: Optional[str] = IndexType.spoken,
         result_threshold: Optional[int] = None,
         score_threshold: Optional[float] = None,
         dynamic_score_percentage: Optional[float] = None,
@@ -108,6 +110,8 @@ def search(
         return search.search_inside_collection(
             collection_id=self.id,
             query=query,
+            search_type=search_type,
+            index_type=index_type,
             result_threshold=result_threshold,
             score_threshold=score_threshold,
             dynamic_score_percentage=dynamic_score_percentage,
diff --git a/videodb/search.py b/videodb/search.py
index e9e6942..168d10f 100644
--- a/videodb/search.py
+++ b/videodb/search.py
@@ -1,6 +1,7 @@
 from abc import ABC, abstractmethod
 from videodb._utils._video import play_stream
 from videodb._constants import (
+    IndexType,
     SearchType,
     ApiPath,
     SemanticSearchDefaultValues,
@@ -109,6 +110,8 @@ def search_inside_video(
         self,
         video_id: str,
         query: str,
+        search_type: str,
+        index_type: str,
         result_threshold: Optional[int] = None,
         score_threshold: Optional[float] = None,
         dynamic_score_percentage: Optional[float] = None,
@@ -117,7 +120,8 @@ def search_inside_video(
         search_data = self._connection.post(
             path=f"{ApiPath.video}/{video_id}/{ApiPath.search}",
             data={
-                "index_type": SearchType.semantic,
+                "search_type": search_type,
+                "index_type": index_type,
                 "query": query,
                 "score_threshold": score_threshold
                 or SemanticSearchDefaultValues.score_threshold,
@@ -133,6 +137,8 @@ def search_inside_collection(
         self,
         collection_id: str,
         query: str,
+        search_type: str,
+        index_type: str,
         result_threshold: Optional[int] = None,
         score_threshold: Optional[float] = None,
         dynamic_score_percentage: Optional[float] = None,
@@ -141,7 +147,8 @@ def search_inside_collection(
         search_data = self._connection.post(
             path=f"{ApiPath.collection}/{collection_id}/{ApiPath.search}",
             data={
-                "index_type": SearchType.semantic,
+                "search_type": search_type,
+                "index_type": index_type,
                 "query": query,
                 "score_threshold": score_threshold
                 or SemanticSearchDefaultValues.score_threshold,
@@ -162,6 +169,8 @@ def search_inside_video(
         self,
         video_id: str,
         query: str,
+        search_type: str,
+        index_type: str,
         result_threshold: Optional[int] = None,
         score_threshold: Optional[float] = None,
         dynamic_score_percentage: Optional[float] = None,
@@ -170,7 +179,8 @@ def search_inside_video(
         search_data = self._connection.post(
             path=f"{ApiPath.video}/{video_id}/{ApiPath.search}",
             data={
-                "index_type": SearchType.keyword,
+                "search_type": search_type,
+                "index_type": index_type,
                 "query": query,
                 "score_threshold": score_threshold,
                 "result_threshold": result_threshold,
@@ -190,6 +200,8 @@ def search_inside_video(
         self,
         video_id: str,
         query: str,
+        search_type: str,
+        index_type: str,
         result_threshold: Optional[int] = None,
         score_threshold: Optional[float] = None,
         dynamic_score_percentage: Optional[float] = None,
@@ -198,7 +210,8 @@ def search_inside_video(
         search_data = self._connection.post(
             path=f"{ApiPath.video}/{video_id}/{ApiPath.search}",
             data={
-                "index_type": SearchType.scene,
+                "search_type": search_type,
+                "index_type": IndexType.scene,
                 "query": query,
                 "score_threshold": score_threshold,
                 "result_threshold": result_threshold,
diff --git a/videodb/video.py b/videodb/video.py
index 845e32d..6c4fb65 100644
--- a/videodb/video.py
+++ b/videodb/video.py
@@ -49,6 +49,7 @@ def search(
         self,
         query: str,
         search_type: Optional[str] = SearchType.semantic,
+        index_type: Optional[str] = IndexType.spoken,
         result_threshold: Optional[int] = None,
         score_threshold: Optional[float] = None,
         dynamic_score_percentage: Optional[float] = None,
@@ -58,6 +59,8 @@ def search(
         return search.search_inside_video(
             video_id=self.id,
             query=query,
+            search_type=search_type,
+            index_type=index_type,
             result_threshold=result_threshold,
             score_threshold=score_threshold,
             dynamic_score_percentage=dynamic_score_percentage,
@@ -152,7 +155,7 @@ def index_spoken_words(
         self._connection.post(
             path=f"{ApiPath.video}/{self.id}/{ApiPath.index}",
             data={
-                "index_type": IndexType.semantic,
+                "index_type": IndexType.spoken,
                 "language_code": language_code,
                 "force": force,
                 "callback_url": callback_url,
@@ -207,11 +210,11 @@ def _format_scene_collection(self, scene_collection_data: dict) -> SceneCollecti
 
     def extract_scenes(
         self,
-        extraction_type: SceneExtractionType = SceneExtractionType.scene_based,
+        extraction_type: SceneExtractionType = SceneExtractionType.shot_based,
         extraction_config: dict = {},
         force: bool = False,
         callback_url: str = None,
-    ):
+    ) -> Optional[SceneCollection]:
         scenes_data = self._connection.post(
             path=f"{ApiPath.video}/{self.id}/{ApiPath.scenes}",
             data={
@@ -225,10 +228,14 @@ def extract_scenes(
             return None
         return self._format_scene_collection(scenes_data.get("scene_collection"))
 
-    def get_scene_collection(self, collection_id: str):
+    def get_scene_collection(self, collection_id: str) -> Optional[SceneCollection]:
+        if not collection_id:
+            raise ValueError("collection_id is required")
         scenes_data = self._connection.get(
             path=f"{ApiPath.video}/{self.id}/{ApiPath.scenes}/{collection_id}"
         )
+        if not scenes_data:
+            return None
         return self._format_scene_collection(scenes_data.get("scene_collection"))
 
     def list_scene_collection(self):
@@ -238,13 +245,15 @@ def list_scene_collection(self):
         return scene_collections_data.get("scene_collections", [])
 
     def delete_scene_collection(self, collection_id: str) -> None:
+        if not collection_id:
+            raise ValueError("collection_id is required")
         self._connection.delete(
             path=f"{ApiPath.video}/{self.id}/{ApiPath.scenes}/{collection_id}"
         )
 
     def index_scenes(
         self,
-        extraction_type: SceneExtractionType = SceneExtractionType.scene_based,
+        extraction_type: SceneExtractionType = SceneExtractionType.shot_based,
         extraction_config: Dict = {},
         prompt: Optional[str] = None,
         model: Optional[str] = None,
@@ -253,7 +262,7 @@ def index_scenes(
         scenes: Optional[List[Scene]] = None,
         force: Optional[bool] = False,
         callback_url: Optional[str] = None,
-    ) -> Optional[List]:
+    ) -> Optional[str]:
         scenes_data = self._connection.post(
             path=f"{ApiPath.video}/{self.id}/{ApiPath.index}/{ApiPath.scene}",
             data={
@@ -270,7 +279,7 @@ def index_scenes(
         )
         if not scenes_data:
             return None
-        return scenes_data.get("scene_index_records", [])
+        return scenes_data.get("scene_index_id")
 
     def list_scene_index(self) -> List:
         index_data = self._connection.get(
@@ -287,6 +296,8 @@ def get_scene_index(self, scene_index_id: str) -> Optional[List]:
         return index_data.get("scene_index_records", [])
 
     def delete_scene_index(self, scene_index_id: str) -> None:
+        if not scene_index_id:
+            raise ValueError("scene_index_id is required")
         self._connection.delete(
             path=f"{ApiPath.video}/{self.id}/{ApiPath.index}/{ApiPath.scene}/{scene_index_id}"
         )

From 125cf89371e2de0176c1ac576c92108c3dc07d1d Mon Sep 17 00:00:00 2001
From: Ankit raj <113342181+ankit-v2-3@users.noreply.github.com>
Date: Wed, 26 Jun 2024 20:46:00 +0530
Subject: [PATCH 2/6] fix: index type

---
 videodb/_constants.py | 2 +-
 videodb/collection.py | 2 +-
 videodb/video.py      | 4 ++--
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/videodb/_constants.py b/videodb/_constants.py
index f45141f..0d9a02b 100644
--- a/videodb/_constants.py
+++ b/videodb/_constants.py
@@ -18,7 +18,7 @@ class SearchType:
 
 
 class IndexType:
-    spoken = "spoken"
+    spoken_word = "spoken_word"
     scene = "scene"
 
 
diff --git a/videodb/collection.py b/videodb/collection.py
index 25bcb47..b610009 100644
--- a/videodb/collection.py
+++ b/videodb/collection.py
@@ -101,7 +101,7 @@ def search(
         self,
         query: str,
         search_type: Optional[str] = SearchType.semantic,
-        index_type: Optional[str] = IndexType.spoken,
+        index_type: Optional[str] = IndexType.spoken_word,
         result_threshold: Optional[int] = None,
         score_threshold: Optional[float] = None,
         dynamic_score_percentage: Optional[float] = None,
diff --git a/videodb/video.py b/videodb/video.py
index 6c4fb65..5e713ab 100644
--- a/videodb/video.py
+++ b/videodb/video.py
@@ -49,7 +49,7 @@ def search(
         self,
         query: str,
         search_type: Optional[str] = SearchType.semantic,
-        index_type: Optional[str] = IndexType.spoken,
+        index_type: Optional[str] = IndexType.spoken_word,
         result_threshold: Optional[int] = None,
         score_threshold: Optional[float] = None,
         dynamic_score_percentage: Optional[float] = None,
@@ -155,7 +155,7 @@ def index_spoken_words(
         self._connection.post(
             path=f"{ApiPath.video}/{self.id}/{ApiPath.index}",
             data={
-                "index_type": IndexType.spoken,
+                "index_type": IndexType.spoken_word,
                 "language_code": language_code,
                 "force": force,
                 "callback_url": callback_url,

From 3841880d86fd77e444b6766a94841acb2a702e72 Mon Sep 17 00:00:00 2001
From: Ankit raj <113342181+ankit-v2-3@users.noreply.github.com>
Date: Thu, 27 Jun 2024 16:48:14 +0530
Subject: [PATCH 3/6] feat: add scene and frame describe

---
 videodb/_constants.py |  6 ++++++
 videodb/image.py      |  9 +++++++++
 videodb/scene.py      | 14 +++++++++++++-
 videodb/video.py      |  1 +
 4 files changed, 29 insertions(+), 1 deletion(-)

diff --git a/videodb/_constants.py b/videodb/_constants.py
index 0d9a02b..400850e 100644
--- a/videodb/_constants.py
+++ b/videodb/_constants.py
@@ -27,6 +27,10 @@ class SceneExtractionType:
     time_based = "time"
 
 
+class SceneModels:
+    gpt4_o = "gpt4-o"
+
+
 class Workflows:
     add_subtitles = "add_subtitles"
 
@@ -58,6 +62,8 @@ class ApiPath:
     invoices = "invoices"
     scenes = "scenes"
     scene = "scene"
+    frame = "frame"
+    describe = "describe"
 
 
 class Status:
diff --git a/videodb/image.py b/videodb/image.py
index c1bd2ef..bc427dd 100644
--- a/videodb/image.py
+++ b/videodb/image.py
@@ -1,5 +1,6 @@
 from videodb._constants import (
     ApiPath,
+    SceneModels,
 )
 
 
@@ -61,3 +62,11 @@ def to_json(self):
             "frame_time": self.frame_time,
             "description": self.description,
         }
+
+    def describe(self, prompt: str = None, model_name=SceneModels.gpt4_o):
+        description_data = self._connection.post(
+            path=f"{ApiPath.video}/{self.video_id}/{ApiPath.frame}/{self.id}/{ApiPath.describe}",
+            data={"prompt": prompt, "model_name": model_name},
+        )
+        self.description = description_data.get("description", None)
+        return self.description
diff --git a/videodb/scene.py b/videodb/scene.py
index 182bfe8..c17ca16 100644
--- a/videodb/scene.py
+++ b/videodb/scene.py
@@ -1,6 +1,6 @@
 from typing import List
 
-from videodb._constants import ApiPath
+from videodb._constants import ApiPath, SceneModels
 
 from videodb.image import Frame
 
@@ -14,6 +14,7 @@ def __init__(
         description: str,
         id: str = None,
         frames: List[Frame] = [],
+        connection=None,
     ):
         self.id = id
         self.video_id = video_id
@@ -21,6 +22,7 @@ def __init__(
         self.end = end
         self.frames: List[Frame] = frames
         self.description = description
+        self._connection = connection
 
     def __repr__(self) -> str:
         return (
@@ -43,6 +45,16 @@ def to_json(self):
             "description": self.description,
         }
 
+    def describe(self, prompt: str = None, model_name=SceneModels.gpt4_o) -> None:
+        if self._connection is None:
+            raise ValueError("Connection is required to describe a scene")
+        description_data = self._connection.post(
+            path=f"{ApiPath.video}/{self.video_id}/{ApiPath.scene}/{self.id}/{ApiPath.describe}",
+            data={"prompt": prompt, "model_name": model_name},
+        )
+        self.description = description_data.get("description", None)
+        return self.description
+
 
 class SceneCollection:
     def __init__(
diff --git a/videodb/video.py b/videodb/video.py
index 5e713ab..f2e2687 100644
--- a/videodb/video.py
+++ b/videodb/video.py
@@ -197,6 +197,7 @@ def _format_scene_collection(self, scene_collection_data: dict) -> SceneCollecti
                 description=scene.get("description"),
                 id=scene.get("scene_id"),
                 frames=frames,
+                connection=self._connection,
             )
             scenes.append(scene)
 

From 43001635aa46c9aefee0f61723604aa19f59cb9e Mon Sep 17 00:00:00 2001
From: Ankit raj <113342181+ankit-v2-3@users.noreply.github.com>
Date: Thu, 27 Jun 2024 17:05:31 +0530
Subject: [PATCH 4/6] refactor: model to model_name

---
 videodb/_constants.py | 4 ----
 videodb/image.py      | 3 +--
 videodb/scene.py      | 4 ++--
 videodb/video.py      | 4 ++--
 4 files changed, 5 insertions(+), 10 deletions(-)

diff --git a/videodb/_constants.py b/videodb/_constants.py
index 400850e..7f12586 100644
--- a/videodb/_constants.py
+++ b/videodb/_constants.py
@@ -27,10 +27,6 @@ class SceneExtractionType:
     time_based = "time"
 
 
-class SceneModels:
-    gpt4_o = "gpt4-o"
-
-
 class Workflows:
     add_subtitles = "add_subtitles"
 
diff --git a/videodb/image.py b/videodb/image.py
index bc427dd..5a97b87 100644
--- a/videodb/image.py
+++ b/videodb/image.py
@@ -1,6 +1,5 @@
 from videodb._constants import (
     ApiPath,
-    SceneModels,
 )
 
 
@@ -63,7 +62,7 @@ def to_json(self):
             "description": self.description,
         }
 
-    def describe(self, prompt: str = None, model_name=SceneModels.gpt4_o):
+    def describe(self, prompt: str = None, model_name=None):
         description_data = self._connection.post(
             path=f"{ApiPath.video}/{self.video_id}/{ApiPath.frame}/{self.id}/{ApiPath.describe}",
             data={"prompt": prompt, "model_name": model_name},
diff --git a/videodb/scene.py b/videodb/scene.py
index c17ca16..3bb1028 100644
--- a/videodb/scene.py
+++ b/videodb/scene.py
@@ -1,6 +1,6 @@
 from typing import List
 
-from videodb._constants import ApiPath, SceneModels
+from videodb._constants import ApiPath
 
 from videodb.image import Frame
 
@@ -45,7 +45,7 @@ def to_json(self):
             "description": self.description,
         }
 
-    def describe(self, prompt: str = None, model_name=SceneModels.gpt4_o) -> None:
+    def describe(self, prompt: str = None, model_name=None) -> None:
         if self._connection is None:
             raise ValueError("Connection is required to describe a scene")
         description_data = self._connection.post(
diff --git a/videodb/video.py b/videodb/video.py
index f2e2687..5a0e291 100644
--- a/videodb/video.py
+++ b/videodb/video.py
@@ -257,7 +257,7 @@ def index_scenes(
         extraction_type: SceneExtractionType = SceneExtractionType.shot_based,
         extraction_config: Dict = {},
         prompt: Optional[str] = None,
-        model: Optional[str] = None,
+        model_name: Optional[str] = None,
         model_config: Optional[Dict] = None,
         name: Optional[str] = None,
         scenes: Optional[List[Scene]] = None,
@@ -270,7 +270,7 @@ def index_scenes(
                 "extraction_type": extraction_type,
                 "extraction_config": extraction_config,
                 "prompt": prompt,
-                "model": model,
+                "model_name": model_name,
                 "model_config": model_config,
                 "name": name,
                 "force": force,

From 157b439fb80085653888fdc858de3db6a5ec0b31 Mon Sep 17 00:00:00 2001
From: Ankit raj <113342181+ankit-v2-3@users.noreply.github.com>
Date: Thu, 27 Jun 2024 17:41:34 +0530
Subject: [PATCH 5/6] build: upgrade version and add license

---
 setup.py             | 1 +
 videodb/__about__.py | 3 ++-
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/setup.py b/setup.py
index b97aad2..db2f955 100644
--- a/setup.py
+++ b/setup.py
@@ -23,6 +23,7 @@
     version=about["__version__"],
     author=about["__author__"],
     author_email=about["__email__"],
+    license=about["__license__"],
     description="VideoDB Python SDK",
     long_description=long_description,
     long_description_content_type="text/markdown",
diff --git a/videodb/__about__.py b/videodb/__about__.py
index d71b052..aa144bc 100644
--- a/videodb/__about__.py
+++ b/videodb/__about__.py
@@ -1,8 +1,9 @@
 """ About information for videodb sdk"""
 
 
-__version__ = "0.2.0"
+__version__ = "0.2.1"
 __title__ = "videodb"
 __author__ = "videodb"
 __email__ = "contact@videodb.io"
 __url__ = "https://github.com/video-db/videodb-python"
+__license__ = "Apache License 2.0"

From a28842cb56cf0b4e82a1db69a7d1a521ddae8152 Mon Sep 17 00:00:00 2001
From: Ankit raj <113342181+ankit-v2-3@users.noreply.github.com>
Date: Thu, 27 Jun 2024 17:54:54 +0530
Subject: [PATCH 6/6] build: upgrade twine

---
 requirements-dev.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/requirements-dev.txt b/requirements-dev.txt
index bf8db06..07fee5c 100644
--- a/requirements-dev.txt
+++ b/requirements-dev.txt
@@ -1,4 +1,4 @@
 ruff==0.1.7
 pytest==7.4.3
-twine==4.0.2
+twine==5.1.1
 wheel==0.42.0