x

See release notes.

README.md

@@ -11,6 +11,12 @@
 3. Execute the program generated by the LLM **safely**.
 4. Program generation takes a single LLM call, as opposed to agents that use a call per action taken.
 
+## Show me! 😹 
+
+[Image manipulation API using PIL](https://langchain-ai.github.io/kork/examples/image_manipulation.html)
+
+<img src="assets/cats.png" alt="Cats!!!" style="max-width: 500px;">
+
 ## How
 
 The chain takes a user query, translates it into a program, and executes it using the `Kork` interpreter.

docs/source/examples/image_manipulation.ipynb

@@ -184,7 +184,9 @@
     "pycharm": {
      "name": "#%%\n"
     },
-    "tags": []
+    "tags": [
+     "hide-input"
+    ]
    },
    "outputs": [],
    "source": [

kork/display.py

@@ -42,8 +42,6 @@ class HtmlResult(TypedDict):
 class _NoExpectedAnswer:
     """A sentinel class to indicate that there is no expected answer."""
 
-    pass
-
 
 NO_EXPECTED_ANSWER = _NoExpectedAnswer()
 
@@ -61,7 +59,12 @@ def as_html_dict(
     code = code_result["code"].strip()
 
     if pretty_print:
-        code = AstPrinter().visit(parse(code), pretty_print=True)
+        try:
+            code = AstPrinter().visit(parse(code), pretty_print=True)
+        except Exception:
+            # This is display code. Broad exception handling OK for now
+            # we can make the code more robust later.
+            code = code
     else:
         code = code
 

pyproject.toml

@@ -1,7 +1,7 @@
 [tool.poetry]
 name = "kork"
-version = "0.0.2"
-description = "Programming with LLMs"
+version = "0.0.3"
+description = "Natural Language Interfaces Powered by LLMs"
 authors = ["LangChain"]
 license = "MIT"
 readme = "README.md"