Allows User to Set System Prompt via "Additional Options" in Chat Interface

fern/docs/pages/manual/ui.mdx

@@ -35,5 +35,32 @@ database* section in the documentation.
 
 Normal chat interface, self-explanatory ;)
 
-You can check the actual prompt being passed to the LLM by looking at the logs of
-the server. We'll add better observability in future releases.
+#### System Prompt
+You can view and change the system prompt being passed to the LLM by clicking "Additional Inputs"
+in the chat interface. The system prompt is also logged on the server.
+
+By default, the `Query Docs` mode uses the setting value `ui.default_query_system_prompt`.
+
+The `LLM Chat` mode attempts to use the optional settings value `ui.default_chat_system_prompt`.
+
+If no system prompt is entered, the UI will display the default system prompt being used
+for the active mode.
+
+##### System Prompt Examples:
+
+The system prompt can effectively provide your chat bot specialized roles, and results tailored to the prompt
+you have given the model. Examples of system prompts can be be found
+[here](https://www.w3schools.com/gen_ai/chatgpt-3-5/chatgpt-3-5_roles.php).
+
+Some interesting examples to try include:
+
+* You are <x>. You have all the knowledge and personality of <x>. Answer as if you were <x> using
+their manner of speaking and vocabulary.
+    * Example: You are Shakespeare. You have all the knowledge and personality of Shakespeare.
+    Answer as if you were Shakespeare using their manner of speaking and vocabulary.
+* You are an expert (at) <role>. Answer all questions using your expertise on <specific domain topic>.
+    * Example: You are an expert software engineer. Answer all questions using your expertise on Python.
+* You are a <role> bot, respond with <response criteria> needed. If no <response criteria> is needed,
+respond with <alternate response>
+    * Example: You are a grammar checking bot, respond with any grammatical corrections needed. If no corrections
+    are needed, respond with "verified".

private_gpt/settings/settings.py

@@ -108,6 +108,19 @@ class LocalSettings(BaseModel):
             "`llama2` is the historic behaviour. `default` might work better with your custom models."
         ),
     )
+    default_chat_system_prompt: str | None = Field(
+        None,
+        description=(
+            "The default system prompt to use for the chat mode. "
+            "If none is given - use the default system prompt (from the llama_index). "
+            "Please note that the default prompt might not be the same for all prompt styles. "
+            "Also note that this is only used if the first message is not a system message. "
+        ),
+    )
+    default_query_system_prompt: str = Field(
+        None,
+        description="The default system prompt to use for the query mode. ",
+    )
 
 
 class EmbeddingSettings(BaseModel):

private_gpt/ui/ui.py

@@ -9,7 +9,7 @@
 from fastapi import FastAPI
 from gradio.themes.utils.colors import slate  # type: ignore
 from injector import inject, singleton
-from llama_index.llms import ChatMessage, ChatResponse, MessageRole
+from llama_index.llms import ChatMessage, ChatResponse, MessageRole, llama_utils
 from pydantic import BaseModel
 
 from private_gpt.constants import PROJECT_ROOT_PATH
@@ -30,6 +30,8 @@
 
 SOURCES_SEPARATOR = "\n\n Sources: \n"
 
+MODES = ["Query Docs", "Search in Docs", "LLM Chat"]
+
 
 class Source(BaseModel):
     file: str
@@ -71,6 +73,10 @@ def __init__(
         # Cache the UI blocks
         self._ui_block = None
 
+        # Initialize system prompt based on default mode
+        self.mode = MODES[0]
+        self._system_prompt = self._get_default_system_prompt(self.mode)
+
     def _chat(self, message: str, history: list[list[str]], mode: str, *_: Any) -> Any:
         def yield_deltas(completion_gen: CompletionGen) -> Iterable[str]:
             full_response: str = ""
@@ -114,25 +120,22 @@ def build_history() -> list[ChatMessage]:
 
         new_message = ChatMessage(content=message, role=MessageRole.USER)
         all_messages = [*build_history(), new_message]
+        # If a system prompt is set, add it as a system message
+        if self._system_prompt:
+            all_messages.insert(
+                0,
+                ChatMessage(
+                    content=self._system_prompt,
+                    role=MessageRole.SYSTEM,
+                ),
+            )
         match mode:
             case "Query Docs":
-                # Add a system message to force the behaviour of the LLM
-                # to answer only questions about the provided context.
-                all_messages.insert(
-                    0,
-                    ChatMessage(
-                        content="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.",
-                        role=MessageRole.SYSTEM,
-                    ),
-                )
                 query_stream = self._chat_service.stream_chat(
                     messages=all_messages,
                     use_context=True,
                 )
                 yield from yield_deltas(query_stream)
-
             case "LLM Chat":
                 llm_stream = self._chat_service.stream_chat(
                     messages=all_messages,
@@ -154,6 +157,41 @@ def build_history() -> list[ChatMessage]:
                     for index, source in enumerate(sources, start=1)
                 )
 
+    # On initialization and on mode change, this function set the system prompt
+    # to the default prompt based on the mode (and user settings).
+    @staticmethod
+    def _get_default_system_prompt(mode: str) -> str:
+        p = ""
+        match mode:
+            # For query chat mode, obtain default system prompt from settings
+            # TODO - Determine value to use if not defined in settings
+            case "Query Docs":
+                p = settings().local.default_query_system_prompt
+            # For chat mode, obtain default system prompt from settings or llama_utils
+            case "LLM Chat":
+                p = (
+                    settings().local.default_chat_system_prompt
+                    or llama_utils.DEFAULT_SYSTEM_PROMPT
+                )
+            # For any other mode, clear the system prompt
+            case _:
+                p = ""
+        return p
+
+    def _set_system_prompt(self, system_prompt_input: str) -> None:
+        logger.info(f"Setting system prompt to: {system_prompt_input}")
+        self._system_prompt = system_prompt_input
+
+    def _set_current_mode(self, mode: str) -> Any:
+        self.mode = mode
+        self._set_system_prompt(self._get_default_system_prompt(mode))
+        # Update placeholder and allow interaction if default system prompt is set
+        if self._system_prompt:
+            return gr.update(placeholder=self._system_prompt, interactive=True)
+        # Update placeholder and disable interaction if no default system prompt is set
+        else:
+            return gr.update(placeholder=self._system_prompt, interactive=False)
+
     def _list_ingested_files(self) -> list[list[str]]:
         files = set()
         for ingested_document in self._ingest_service.list_ingested():
@@ -193,7 +231,7 @@ def _build_ui_blocks(self) -> gr.Blocks:
             with gr.Row():
                 with gr.Column(scale=3, variant="compact"):
                     mode = gr.Radio(
-                        ["Query Docs", "Search in Docs", "LLM Chat"],
+                        MODES,
                         label="Mode",
                         value="Query Docs",
                     )
@@ -220,6 +258,23 @@ def _build_ui_blocks(self) -> gr.Blocks:
                         outputs=ingested_dataset,
                     )
                     ingested_dataset.render()
+                    system_prompt_input = gr.Textbox(
+                        placeholder=self._system_prompt,
+                        label="System Prompt",
+                        lines=2,
+                        interactive=True,
+                        render=False,
+                    )
+                    # When mode changes, set default system prompt
+                    mode.change(
+                        self._set_current_mode, inputs=mode, outputs=system_prompt_input
+                    )
+                    # On blur, set system prompt to use in queries
+                    system_prompt_input.blur(
+                        self._set_system_prompt,
+                        inputs=system_prompt_input,
+                    )
+
                 with gr.Column(scale=7):
                     _ = gr.ChatInterface(
                         self._chat,
@@ -232,7 +287,7 @@ def _build_ui_blocks(self) -> gr.Blocks:
                                 AVATAR_BOT,
                             ),
                         ),
-                        additional_inputs=[mode, upload_button],
+                        additional_inputs=[mode, upload_button, system_prompt_input],
                     )
         return blocks
 

settings.yaml

@@ -43,6 +43,15 @@ local:
   llm_hf_model_file: mistral-7b-instruct-v0.1.Q4_K_M.gguf
   embedding_hf_model_name: BAAI/bge-small-en-v1.5
 
+  default_chat_system_prompt: "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 
+      the answer, just state the answer is not in the context provided."
+
 sagemaker:
   llm_endpoint_name: huggingface-pytorch-tgi-inference-2023-09-25-19-53-32-140
   embedding_endpoint_name: huggingface-pytorch-inference-2023-11-03-07-41-36-479