ai-parrot 0.3.5__tar.gz → 0.3.6__tar.gz

{ai_parrot-0.3.5 → ai_parrot-0.3.6}/PKG-INFO

@@ -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 → ai_parrot-0.3.6}/ai_parrot.egg-info/PKG-INFO

@@ -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 → ai_parrot-0.3.6}/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)

{ai_parrot-0.3.5 → ai_parrot-0.3.6}/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"