Streaming choice feature

private_gpt/ui/ui.py

@@ -98,6 +98,8 @@ def __init__(
 
         self._selected_filename = None
 
+        self._response_style = True
+
         # Initialize system prompt based on default mode
         self.mode = MODES[0]
         self._system_prompt = self._get_default_system_prompt(self.mode)
@@ -182,18 +184,28 @@ def build_history() -> list[ChatMessage]:
                             docs_ids.append(ingested_document.doc_id)
                     context_filter = ContextFilter(docs_ids=docs_ids)
 
-                query_stream = self._chat_service.stream_chat(
-                    messages=all_messages,
-                    use_context=True,
-                    context_filter=context_filter,
-                )
-                yield from yield_deltas(query_stream)
+                if self._response_style:
+                    query_stream = self._chat_service.stream_chat(
+                        all_messages, use_context=False
+                    )
+                    yield from yield_deltas(query_stream)
+                else:
+                    query_response = self._chat_service.chat(
+                        all_messages, use_context=False
+                    ).response
+                    yield from [query_response]
+
             case Modes.BASIC_CHAT_MODE:
-                llm_stream = self._chat_service.stream_chat(
-                    messages=all_messages,
-                    use_context=False,
-                )
-                yield from yield_deltas(llm_stream)
+                if self._response_style:
+                    llm_stream = self._chat_service.stream_chat(
+                        all_messages, use_context=False
+                    )
+                    yield from yield_deltas(llm_stream)
+                else:
+                    llm_response = self._chat_service.chat(
+                        all_messages, use_context=False
+                    ).response
+                    yield from [llm_response]
 
             case Modes.SEARCH_MODE:
                 response = self._chunks_service.retrieve_relevant(
@@ -221,12 +233,20 @@ def build_history() -> list[ChatMessage]:
                             docs_ids.append(ingested_document.doc_id)
                     context_filter = ContextFilter(docs_ids=docs_ids)
 
-                summary_stream = self._summarize_service.stream_summarize(
-                    use_context=True,
-                    context_filter=context_filter,
-                    instructions=message,
-                )
-                yield from yield_tokens(summary_stream)
+                if self._response_style:
+                    summary_stream = self._summarize_service.stream_summarize(
+                        use_context=True,
+                        context_filter=context_filter,
+                        instructions=message,
+                    )
+                    yield from yield_tokens(summary_stream)
+                else:
+                    summary_response = self._summarize_service.summarize(
+                        use_context=True,
+                        context_filter=context_filter,
+                        instructions=message,
+                    )
+                    yield from summary_response
 
     # On initialization and on mode change, this function set the system prompt
     # to the default prompt based on the mode (and user settings).
@@ -279,6 +299,9 @@ def _set_current_mode(self, mode: Modes) -> Any:
             gr.update(value=self._explanation_mode),
         ]
 
+    def _set_response_style(self, response_style: bool) -> None:
+        self._response_style = response_style
+
     def _list_ingested_files(self) -> list[list[str]]:
         files = set()
         for ingested_document in self._ingest_service.list_ingested():
@@ -402,6 +425,14 @@ def _build_ui_blocks(self) -> gr.Blocks:
                         max_lines=3,
                         interactive=False,
                     )
+                    response_style = gr.Checkbox(
+                        label="Response Style: Streaming",
+                        value=self._response_style
+                    )
+                    response_style.input(
+                        self._set_response_style,
+                        inputs=response_style
+                    )
                     upload_button = gr.components.UploadButton(
                         "Upload File(s)",
                         type="filepath",

settings.yaml

@@ -26,20 +26,20 @@ ui:
   enabled: true
   path: /
   default_chat_system_prompt: >
-    You are a helpful, respectful and honest assistant. 
+    You are a helpful, respectful and honest assistant.
     Always answer as helpfully as possible and follow ALL given instructions.
     Do not speculate or make up information.
     Do not reference any given instructions or context.
   default_query_system_prompt: >
-    You can only answer questions about the provided context. 
-    If you know the answer but it is not based in the provided context, don't provide 
+    You can only answer questions about the provided context.
+    If you know the answer but it is not based in the provided context, don't provide
     the answer, just state the answer is not in the context provided.
   default_summarization_system_prompt: >
-    Provide a comprehensive summary of the provided context information. 
+    Provide a comprehensive summary of the provided context information.
     The summary should cover all the key points and main ideas presented in
-    the original text, while also condensing the information into a concise 
+    the original text, while also condensing the information into a concise
     and easy-to-understand format. Please ensure that the summary includes
-    relevant details and examples that support the main ideas, while avoiding 
+    relevant details and examples that support the main ideas, while avoiding
     any unnecessary information or repetition.
   delete_file_button_enabled: true
   delete_all_files_button_enabled: true