vision-agent 0.2.79__tar.gz → 0.2.80__tar.gz

{vision_agent-0.2.79 → vision_agent-0.2.80}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vision-agent
-Version: 0.2.79
+Version: 0.2.80
 Summary: Toolset for Vision Agent
 Author: Landing AI
 Author-email: dev@landing.ai

{vision_agent-0.2.79 → vision_agent-0.2.80}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "vision-agent"
-version = "0.2.79"
+version = "0.2.80"
 description = "Toolset for Vision Agent"
 authors = ["Landing AI <dev@landing.ai>"]
 readme = "README.md"

{vision_agent-0.2.79 → vision_agent-0.2.80}/vision_agent/utils/execute.py

@@ -112,6 +112,11 @@ class Result:
         self.raw = copy.deepcopy(data)
 
         self.text = data.pop(MimeType.TEXT_PLAIN, None)
+        if self.text and (self.text.startswith("'") and self.text.endswith("'")):
+            # This is a workaround for the issue that str result is wrapped with single quotes by notebook.
+            # E.g. input text: "'flower'". what we want: "flower"
+            self.text = self.text[1:-1]
+
         self.html = data.pop(MimeType.TEXT_HTML, None)
         self.markdown = data.pop(MimeType.TEXT_MARKDOWN, None)
         self.svg = data.pop(MimeType.IMAGE_SVG, None)

{vision_agent-0.2.79 → vision_agent-0.2.80}/vision_agent/utils/sim.py

@@ -1,4 +1,5 @@
 import os
+from functools import lru_cache
 from pathlib import Path
 from typing import Dict, List, Optional, Sequence, Union
 
@@ -33,11 +34,7 @@ class Sim:
             model: str: The model to use for embeddings.
         """
         self.df = df
-        if not api_key:
-            self.client = OpenAI()
-        else:
-            self.client = OpenAI(api_key=api_key)
-
+        self.client = OpenAI(api_key=api_key)
         self.model = model
         if "embs" not in df.columns and sim_key is None:
             raise ValueError("key is required if no column 'embs' is present.")
@@ -57,6 +54,7 @@ class Sim:
         df = df.drop("embs", axis=1)
         df.to_csv(sim_file / "df.csv", index=False)
 
+    @lru_cache(maxsize=256)
     def top_k(
         self, query: str, k: int = 5, thresh: Optional[float] = None
     ) -> Sequence[Dict]: