ai-parrot 0.3.5__cp311-cp311-manylinux_2_28_x86_64.whl → 0.3.6__cp311-cp311-manylinux_2_28_x86_64.whl

{ai_parrot-0.3.5.dist-info → ai_parrot-0.3.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ai-parrot
-Version: 0.3.5
+Version: 0.3.6
 Summary: Live Chatbots based on Langchain chatbots and Agents     Integrated into Navigator Framework or used into aiohttp applications.
 Home-page: https://github.com/phenobarbital/ai-parrot
 Author: Jesus Lara

{ai_parrot-0.3.5.dist-info → ai_parrot-0.3.6.dist-info}/RECORD

@@ -4,7 +4,7 @@ parrot/exceptions.cpython-311-x86_64-linux-gnu.so,sha256=VNyBh3uLxGQgB0l1bkWjQDq
 parrot/manager.py,sha256=NhzXoWxSgtoWHpmYP8cV2Ujq_SlvCbQYQBaohAeL2TM,5935
 parrot/models.py,sha256=RsVQCqhSXBKRPcu-BCga9Y1wyvENFXDCuq3_ObIKvAo,13452
 parrot/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-parrot/version.py,sha256=RknhCGT72EptwSfSvr4rE9_fulip0_-gBlla3iuIIi4,373
+parrot/version.py,sha256=x5KFeKUhuf0IyJRSN3fSKlwqSDRNfHYDoFae9slFeKc,373
 parrot/chatbots/__init__.py,sha256=ypskCnME0xUv6psBEGCEyXCrD0J0ULHSllpVmSxqb4A,200
 parrot/chatbots/abstract.py,sha256=CmDn3k4r9uKImOZRN4L9zxLbCdC-1MPUAorDlfZT-kA,26421
 parrot/chatbots/asktroc.py,sha256=gyWzyvpAnmXwXd-3DEKoIJtAxt6NnP5mUZdZbkFky8s,604
@@ -68,7 +68,7 @@ parrot/loaders/repo.py,sha256=vBqBAnwU6p3_DCvI9DVhi1Bs8iCDYHwFGp0P9zvGRyw,3737
 parrot/loaders/rtd.py,sha256=oKOC9Qn3iwulYx5BEvXy4_kusKRsy5RLYNHS-e5p-1k,1988
 parrot/loaders/txt.py,sha256=AeGroWffFT--7TYlTSTr5Av5zAr8YIp1fxt8r5qdi-A,2802
 parrot/loaders/video.py,sha256=pl5Ho69bp5vrWMqg5tLbsnHUus1LByTDoL6NPk57Ays,2929
-parrot/loaders/videolocal.py,sha256=VBjtDIZ7CxkmgISXNr2Nc68MHa9-57qQr0uSxLIsAOU,4326
+parrot/loaders/videolocal.py,sha256=o1upjpsMHp1NV4ZQVRc2DS8nKyJI1l0x9p3PjJUr3fU,5018
 parrot/loaders/vimeo.py,sha256=zOvOOIiaZr_bRswJFI7uIMKISgALOxcSim9ZRUFY1Fc,4114
 parrot/loaders/web.py,sha256=3x06JNpfTGFtvSBPAEBVoVdZkpVXePcJeMtj61B2xJk,8867
 parrot/loaders/web_base.py,sha256=5SjQddT0Vhne8C9s30iU3Ex_9O1PJ8kyDmy8EdhGBo0,4380
@@ -103,8 +103,8 @@ resources/users/handlers.py,sha256=BGzqBvPY_OaIF_nONWX4b_B5OyyBrdGuSihIsdlFwjk,2
 resources/users/models.py,sha256=glk7Emv7QCi6i32xRFDrGc8UwK23_LPg0XUOJoHnwRU,6799
 settings/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 settings/settings.py,sha256=9ueEvyLNurUX-AaIeRPV8GKX1c4YjDLbksUAeqEq6Ck,1854
-ai_parrot-0.3.5.dist-info/LICENSE,sha256=vRKOoa7onTsLNvSzJtGtMaNhWWh8B3YAT733Tlu6M4o,1070
-ai_parrot-0.3.5.dist-info/METADATA,sha256=G19tFikgbnhRqltqs2_OulmbuqdrA4Gwp2wW_dx5URk,9721
-ai_parrot-0.3.5.dist-info/WHEEL,sha256=UQ-0qXN3LQUffjrV43_e_ZXj2pgORBqTmXipnkj0E8I,113
-ai_parrot-0.3.5.dist-info/top_level.txt,sha256=qHoO4BhYDfeTkyKnciZSQtn5FSLN3Q-P5xCTkyvbuxg,26
-ai_parrot-0.3.5.dist-info/RECORD,,
+ai_parrot-0.3.6.dist-info/LICENSE,sha256=vRKOoa7onTsLNvSzJtGtMaNhWWh8B3YAT733Tlu6M4o,1070
+ai_parrot-0.3.6.dist-info/METADATA,sha256=UukaICPH6ngFNm_DU3TmP2E89_BpgchSP0oPLxypwso,9721
+ai_parrot-0.3.6.dist-info/WHEEL,sha256=UQ-0qXN3LQUffjrV43_e_ZXj2pgORBqTmXipnkj0E8I,113
+ai_parrot-0.3.6.dist-info/top_level.txt,sha256=qHoO4BhYDfeTkyKnciZSQtn5FSLN3Q-P5xCTkyvbuxg,26
+ai_parrot-0.3.6.dist-info/RECORD,,

parrot/loaders/videolocal.py

@@ -1,10 +1,26 @@
 from typing import Any
 from collections.abc import Callable
+import math
 from pathlib import PurePath
 from langchain.docstore.document import Document
 from .basevideo import BaseVideoLoader
 
 
+def split_text(text, max_length):
+    """Split text into chunks of a maximum length, ensuring not to break words."""
+    chunks = []
+    while len(text) > max_length:
+        # Find the last space before the max_length
+        split_point = text.rfind(' ', 0, max_length)
+        # If no space found, split at max_length
+        if split_point == -1:
+            split_point = max_length
+        chunks.append(text[:split_point])
+        text = text[split_point:].strip()
+    chunks.append(text)
+    return chunks
+
+
 class VideoLocalLoader(BaseVideoLoader):
     """
     Generating Video transcripts from local Videos.
@@ -54,14 +70,17 @@ class VideoLocalLoader(BaseVideoLoader):
             transcript = ''
         # Summarize the transcript
         if transcript:
+            # Split transcript into chunks
+            transcript_chunks = split_text(transcript, 32767)
             summary = self.get_summary_from_text(transcript)
             # Create Two Documents, one is for transcript, second is VTT:
             metadata['summary'] = summary
-            doc = Document(
-                page_content=transcript,
-                metadata=metadata
-            )
-            documents.append(doc)
+            for chunk in transcript_chunks:
+                doc = Document(
+                    page_content=chunk,
+                    metadata=metadata
+                )
+                documents.append(doc)
         if transcript_whisper:
             # VTT version:
             transcript = self.transcript_to_vtt(transcript_whisper, transcript_path)

parrot/version.py

@@ -3,7 +3,7 @@
 __title__ = "ai-parrot"
 __description__ = "Live Chatbots based on Langchain chatbots and Agents \
     Integrated into Navigator Framework or used into aiohttp applications."
-__version__ = "0.3.5"
+__version__ = "0.3.6"
 __author__ = "Jesus Lara"
 __author_email__ = "jesuslarag@gmail.com"
 __license__ = "MIT"