fixed response formatting when streaming

gpt4all-bindings/python/gpt4all/gpt4all.py

@@ -155,7 +155,7 @@ class GPT4All():
         print("Model downloaded at: " + download_path)
         return download_path
 
-    def generate(self, prompt: str, streaming: bool = False, **generate_kwargs) -> str:
+    def generate(self, prompt: str, streaming: bool = True, **generate_kwargs) -> str:
         """
         Surfaced method of running generate without accessing model object.
 
@@ -211,7 +211,7 @@ class GPT4All():
 
         response = self.model.generate(full_prompt, streaming=streaming, **generate_kwargs)
 
-        if verbose:
+        if verbose and not streaming:
             print(response)
 
         response_dict = {

gpt4all-bindings/python/gpt4all/pyllmodel.py

@@ -225,6 +225,8 @@ class LLModel:
 
         # Revert to old stdout
         sys.stdout = old_stdout
+        # Force new line
+        print()
 
         return stream_processor.output
 

gpt4all-bindings/python/setup.py

@@ -61,7 +61,7 @@ copy_prebuilt_C_lib(SRC_CLIB_DIRECtORY,
 
 setup(
     name=package_name,
-    version="0.2.2",
+    version="0.2.3",
     description="Python bindings for GPT4All",
     author="Richard Guo",
     author_email="richard@nomic.ai",