npcsh 0.3.30__py3-none-any.whl → 0.3.32__py3-none-any.whl

npcsh/video.py

@@ -1,6 +1,9 @@
-# video.py 
+# video.py
+
 
 def process_video(file_path, table_name):
+    # implement with moon dream
+
     embeddings = []
     texts = []
     try:
@@ -46,4 +49,4 @@ def process_video(file_path, table_name):
 
     except Exception as e:
         print(f"Error processing video: {e}")
-        return [], []  # Return empty lists in case of error
+        return [], []  # Return empty lists in case of error

npcsh/video_gen.py

@@ -0,0 +1,69 @@
+def generate_video_diffusers(
+    prompt,
+    model,
+    npc=None,
+    device="cpu",
+    output_path="",
+    num_inference_steps=10,
+    num_frames=125,
+    height=256,
+    width=256,
+):
+
+    import torch
+    from diffusers import DiffusionPipeline, DPMSolverMultistepScheduler
+    import numpy as np
+    import cv2
+
+    # Load pipeline
+    pipe = DiffusionPipeline.from_pretrained(
+        "damo-vilab/text-to-video-ms-1.7b", torch_dtype=torch.float32
+    ).to(device)
+    pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
+
+    output = pipe(
+        prompt,
+        num_inference_steps=num_inference_steps,
+        num_frames=num_frames,
+        height=height,
+        width=width,
+    )
+
+    def save_frames_to_video(frames, output_path, fps=8):
+        """Handle the specific 5D array format (1, num_frames, H, W, 3) with proper type conversion"""
+        # Verify input format
+        if not (
+            isinstance(frames, np.ndarray)
+            and frames.ndim == 5
+            and frames.shape[-1] == 3
+        ):
+            raise ValueError(
+                f"Unexpected frame format. Expected 5D RGB array, got {frames.shape}"
+            )
+
+        # Remove batch dimension and convert to 0-255 uint8
+        frames = (frames[0] * 255).astype(np.uint8)  # Shape: (num_frames, H, W, 3)
+
+        # Get video dimensions
+        height, width = frames.shape[1:3]
+
+        # Create video writer
+        fourcc = cv2.VideoWriter_fourcc(*"mp4v")
+        video_writer = cv2.VideoWriter(output_path, fourcc, fps, (width, height))
+
+        if not video_writer.isOpened():
+            raise IOError(f"Could not open video writer for {output_path}")
+
+        # Write frames (convert RGB to BGR for OpenCV)
+        for frame in frames:
+            video_writer.write(cv2.cvtColor(frame, cv2.COLOR_RGB2BGR))
+
+        video_writer.release()
+        print(f"Successfully saved {frames.shape[0]} frames to {output_path}")
+
+    os.makedirs("~/.npcsh/videos/")
+    if output_path == "":
+
+        output_path = "~/.npcsh/videos/" + prompt[0:8] + ".mp4"
+    save_frames_to_video(output.frames, output_path)
+    return output_path

{npcsh-0.3.30.data → npcsh-0.3.32.data}/data/npcsh/npc_team/generic_search.tool

@@ -2,13 +2,21 @@ tool_name: "internet_search"
 description: Searches the web for information based on a query in order to verify timiely details (e.g. current events) or to corroborate information in uncertain situations. Should be mainly only used when users specifically request a search, otherwise an LLMs basic knowledge should be sufficient.
 inputs:
   - query
+  - provider: ''
 steps:
   - engine: "python"
     code: |
       from npcsh.search import search_web
+      from npcsh.npc_sysenv import NPCSH_SEARCH_PROVIDER
       query = "{{ query }}"
+      provider = '{{ provider }}'
+      if provider.strip() != '':
+          results = search_web(query, num_results=5, provider = provider)
+      else:
+          results = search_web(query, num_results=5, provider = NPCSH_SEARCH_PROVIDER)
+
       print('QUERY in tool', query)
-      results = search_web(query, num_results=5)
+      results = search_web(query, num_results=5, provider = NPCSH_SEARCH_PROVIDER)
       print('RESULTS in tool', results)
   - engine: "natural"
     code: |

{npcsh-0.3.30.data → npcsh-0.3.32.data}/data/npcsh/npc_team/npcsh.ctx

@@ -1,5 +1,11 @@
-text: |
+context: |
     The npcsh NPC team is devoted to providing a safe and helpful
     environment for users where they can work and be as successful as possible.
     npcsh is a command-line tool that makes it easy for users to harness
-    the power of LLMs from a command line shell.
+    the power of LLMs from a command line shell.
+databases:
+    - ~/npcsh_history.db
+mcp_servers:
+    - /path/to/mcp/server.py
+    - @npm for server
+