Agent Flow with Streaming Enabled

[raprajapati1208]

Hi,

I am running an Agentic flow via API with stream=true paramter. However the results are not streaming. It never returns the token events. Are agents not able to stream responses?

Regards,
Ranjan

[dosubot[bot]]

Agents are able to stream responses when running an Agentic flow via API with the stream=true parameter. The code supports streaming execution modes and returns a StreamingResponse for real-time results when the stream parameter is set to true ^[1]. If you're not receiving token events, you might want to check if there are any specific conditions or configurations that need to be met for streaming to function correctly, or if there are any issues with the endpoint being used. Note that there is a known issue with the deprecated /api/v1/run/<flow_id>?stream=true endpoint, where AI responses are not saved in the chat memory when streaming is enabled. It is recommended to use the /build endpoint for streaming responses ^[2].

To continue talking to Dosu, mention @dosu.

---

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other}

[raprajapati1208]

@dosu

Here is my api response

{"event": "add_message", "data": {"timestamp": "2025-02-26T11:35:33", "sender": "User", "sender_name": "User", "session_id": "postman_session", "text": "yes", "files": [], "error": false, "edit": false, "properties": {"text_color": "", "background_color": "", "edited": false, "source": {"id": null, "display_name": null, "source": null}, "icon": "", "allow_markdown": false, "positive_feedback": null, "state": "complete", "targets": []}, "category": "message", "content_blocks": [], "id": "e8a5ac64-cb3e-47c6-a6a1-0becb9b10e6e", "flow_id": "5240c000-adc9-44dc-9013-be0775235a0b"}}

{"event": "add_message", "data": {"timestamp": "2025-02-26T11:35:35", "sender": "Machine", "sender_name": "Agent", "session_id": "postman_session", "text": "", "files": [], "error": false, "edit": false, "properties": {"text_color": null, "background_color": null, "edited": false, "source": {"id": null, "display_name": null, "source": null}, "icon": "Bot", "allow_markdown": false, "positive_feedback": null, "state": "partial", "targets": []}, "category": "message", "content_blocks": [{"title": "Agent Steps", "contents": [], "allow_markdown": true, "media_url": null}], "id": "2032628b-d731-493d-a7f6-d74a31d8044d", "flow_id": "5240c000-adc9-44dc-9013-be0775235a0b"}}

{"event": "add_message", "data": {"timestamp": "2025-02-26T11:35:35", "sender": "Machine", "sender_name": "Agent", "session_id": "postman_session", "text": "", "files": [], "error": false, "edit": false, "properties": {"text_color": null, "background_color": null, "edited": false, "source": {"id": null, "display_name": null, "source": null}, "icon": "Bot", "allow_markdown": false, "positive_feedback": null, "state": "partial", "targets": []}, "category": "message", "content_blocks": [{"title": "Agent Steps", "contents": [{"type": "text", "duration": 14, "header": {"title": "Input", "icon": "MessageSquare"}, "text": "Input: yes"}], "allow_markdown": true, "media_url": null}], "id": "2032628b-d731-493d-a7f6-d74a31d8044d", "flow_id": "5240c000-adc9-44dc-9013-be0775235a0b"}}

{"event": "add_message", "data": {"timestamp": "2025-02-26T11:35:35", "sender": "Machine", "sender_name": "Agent", "session_id": "postman_session", "text": "It seems like you might have a question or need assistance. How can I help you today? If you're looking for information on available subsidies, please provide the company name along with its location or website.", "files": [], "error": false, "edit": false, "properties": {"text_color": null, "background_color": null, "edited": false, "source": {"id": null, "display_name": null, "source": null}, "icon": "Bot", "allow_markdown": false, "positive_feedback": null, "state": "complete", "targets": []}, "category": "message", "content_blocks": [{"title": "Agent Steps", "contents": [{"type": "text", "duration": 14, "header": {"title": "Input", "icon": "MessageSquare"}, "text": "Input: yes"}, {"type": "text", "duration": 1415, "header": {"title": "Output", "icon": "MessageSquare"}, "text": "It seems like you might have a question or need assistance. How can I help you today? If you're looking for information on available subsidies, please provide the company name along with its location or website."}], "allow_markdown": true, "media_url": null}], "id": "2032628b-d731-493d-a7f6-d74a31d8044d", "flow_id": "5240c000-adc9-44dc-9013-be0775235a0b"}}

{"event": "add_message", "data": {"timestamp": "2025-02-26T11:35:35", "sender": "Machine", "sender_name": "AI", "session_id": "postman_session", "text": "It seems like you might have a question or need assistance. How can I help you today? If you're looking for information on available subsidies, please provide the company name along with its location or website.", "files": [], "error": false, "edit": false, "properties": {"text_color": "", "background_color": "", "edited": false, "source": {"id": "Agent-NtV7i", "display_name": "Agent", "source": "gpt-4o-mini"}, "icon": "bot", "allow_markdown": false, "positive_feedback": null, "state": "complete", "targets": []}, "category": "message", "content_blocks": [{"title": "Agent Steps", "contents": [{"type": "text", "duration": 14, "header": {"title": "Input", "icon": "MessageSquare"}, "text": "Input: yes"}, {"type": "text", "duration": 1415, "header": {"title": "Output", "icon": "MessageSquare"}, "text": "It seems like you might have a question or need assistance. How can I help you today? If you're looking for information on available subsidies, please provide the company name along with its location or website."}], "allow_markdown": true, "media_url": null}], "id": "2032628b-d731-493d-a7f6-d74a31d8044d", "flow_id": "5240c000-adc9-44dc-9013-be0775235a0b"}}

{"event": "end", "data": {"result": {"session_id": "postman_session", "outputs": [{"inputs": {"input_value": "yes"}, "outputs": [{"results": {"message": {"text_key": "text", "data": {"timestamp": "2025-02-26T11:35:35+00:00", "sender": "Machine", "sender_name": "AI", "session_id": "postman_session", "text": "It seems like you might have a question or need assistance. How can I help you today? If you're looking for information on available subsidies, please provide the company name along with its location or website.", "files": [], "error": false, "edit": false, "properties": {"text_color": "", "background_color": "", "edited": false, "source": {"id": "Agent-NtV7i", "display_name": "Agent", "source": "gpt-4o-mini"}, "icon": "bot", "allow_markdown": false, "positive_feedback": null, "state": "complete", "targets": []}, "category": "message", "content_blocks": [{"title": "Agent Steps", "contents": [{"type": "text", "duration": 14, "header": {"title": "Input", "icon": "MessageSquare"}, "text": "Input: yes"}, {"type": "text", "duration": 1415, "header": {"title": "Output", "icon": "MessageSquare"}, "text": "It seems like you might have a question or need assistance. How can I help you today? If you're looking for information on available subsidies, please provide the company name along with its location or website."}], "allow_markdown": true, "media_url": null}], "id": "2032628b-d731-493d-a7f6-d74a31d8044d", "flow_id": "5240c000-adc9-44dc-9013-be0775235a0b"}, "default_value": "", "text": "It seems like you might have a question or need assistance. How can I help you today? If you're looking for information on available subsidies, please provide the company name along with its location or website.", "sender": "Machine", "sender_name": "AI", "files": [], "session_id": "postman_session", "timestamp": "2025-02-26T11:35:35+00:00", "flow_id": "5240c000-adc9-44dc-9013-be0775235a0b", "error": false, "edit": false, "properties": {"text_color": "", "background_color": "", "edited": false, "source": {"id": "Agent-NtV7i", "display_name": "Agent", "source": "gpt-4o-mini"}, "icon": "bot", "allow_markdown": false, "positive_feedback": null, "state": "complete", "targets": []}, "category": "message", "content_blocks": [{"title": "Agent Steps", "contents": [{"type": "text", "duration": 14, "header": {"title": "Input", "icon": "MessageSquare"}, "text": "Input: yes"}, {"type": "text", "duration": 1415, "header": {"title": "Output", "icon": "MessageSquare"}, "text": "It seems like you might have a question or need assistance. How can I help you today? If you're looking for information on available subsidies, please provide the company name along with its location or website."}], "allow_markdown": true, "media_url": null}]}}, "artifacts": {"message": "It seems like you might have a question or need assistance. How can I help you today? If you're looking for information on available subsidies, please provide the company name along with its location or website.", "sender": "Machine", "sender_name": "AI", "files": [], "type": "object"}, "outputs": {"message": {"message": {"timestamp": "2025-02-26T11:35:35", "sender": "Machine", "sender_name": "AI", "session_id": "postman_session", "text": "It seems like you might have a question or need assistance. How can I help you today? If you're looking for information on available subsidies, please provide the company name along with its location or website.", "files": [], "error": false, "edit": false, "properties": {"text_color": "", "background_color": "", "edited": false, "source": {"id": "Agent-NtV7i", "display_name": "Agent", "source": "gpt-4o-mini"}, "icon": "bot", "allow_markdown": false, "positive_feedback": null, "state": "complete", "targets": []}, "category": "message", "content_blocks": [{"title": "Agent Steps", "contents": [{"type": "text", "duration": 14, "header": {"title": "Input", "icon": "MessageSquare"}, "text": "Input: yes"}, {"type": "text", "duration": 1415, "header": {"title": "Output", "icon": "MessageSquare"}, "text": "It seems like you might have a question or need assistance. How can I help you today? If you're looking for information on available subsidies, please provide the company name along with its location or website."}], "allow_markdown": true, "media_url": null}], "id": "2032628b-d731-493d-a7f6-d74a31d8044d", "flow_id": "5240c000-adc9-44dc-9013-be0775235a0b"}, "type": "message"}}, "logs": {"message": []}, "messages": [{"message": "It seems like you might have a question or need assistance. How can I help you today? If you're looking for information on available subsidies, please provide the company name along with its location or website.", "sender": "Machine", "sender_name": "AI", "session_id": "postman_session", "stream_url": null, "component_id": "ChatOutput-JJLGY", "files": [], "type": "message"}], "timedelta": null, "duration": null, "component_display_name": "Chat Output", "component_id": "ChatOutput-JJLGY", "used_frozen_result": false}]}]}}}

I dont see the token event which does not allow me to stream responses in real time.

My Flow is using Langflow agent with chat input and output. The Agent uses other Agents as tool.

[dosubot[bot]]

If you're not seeing token events in your API response, it might be due to the way the Langflow agent is configured or how the flow is set up. Here are a few things to check:

1. Endpoint Usage: Ensure that you are using the correct endpoint for streaming. The /api/v1/run/<flow_id>?stream=true endpoint is deprecated, and it is recommended to use the /build endpoint for streaming responses ^[1].

2. EventManager Configuration: The EventManager is responsible for managing streaming events, including token events. Make sure that the EventManager is correctly set up to handle and emit token events during the flow execution ^[2].

3. Agent Configuration: When using agents as tools within a flow, ensure that each agent is configured to support streaming. The run_flow_generator function should be used to manage event streaming, and it should be set up to generate token events for each token generated during the flow ^[3].

4. Flow Setup: Verify that the flow is correctly set up to support streaming. This includes ensuring that all components in the flow, including any nested agents, are compatible with streaming and that the stream=true parameter is correctly applied.

If these configurations are correct and you're still not receiving token events, there might be a limitation or issue specific to the current implementation of streaming with agents using other agents as tools.

To continue talking to Dosu, mention @dosu.

---

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other}

[raprajapati1208]

@dosu

Does this Component - https://docs.langflow.org/components-agents#agent-component
Agent from Langflow supports streaming? I am having these agents in my flow.

[dosubot[bot]]

Yes, the Agent component in Langflow does support streaming capabilities. This is implemented in the codebase, allowing users to enable or disable streaming by setting the "stream" parameter to true or false. The streaming functionality is managed using a StreamingResponse for real-time results and involves an EventManager to handle events such as "add_message" for new messages and "token" for individual tokens during streaming ^[1][2][3].

To continue talking to Dosu, mention @dosu.

---

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other}

[raprajapati1208]

@dosu

The Agent Component has no attribute/parameter stream.

[dosubot[bot]]

The Agent component in Langflow does have a parameter named "stream" for enabling streaming. This parameter is of type "bool" and is used to stream the response from the model, specifically in Chat contexts. The "stream" parameter is not required and defaults to false if not set ^[1].

To continue talking to Dosu, mention @dosu.

---

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other}

[raprajapati1208]

@dosu

I have confirmed that the UI of langflow has not parameters called stream for Agent component.

[dosubot[bot]]

The "stream" parameter for the Agent component in Langflow is indeed defined in the codebase, specifically in JSON configuration files like Research Agent.json and Conversational_Notion_Agent.json ^[1][2]. However, if it's not visible in the UI, it might be due to a configuration issue or a version mismatch between the codebase and the deployed UI. The parameter is set to be visible ("show": true), so it should appear unless there are other UI constraints or customizations affecting its display ^[1].

To continue talking to Dosu, mention @dosu.

---

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other}

[raprajapati1208]

@dosu

The Agent type node does not have stream parameter. You are reffering to LLM Models, and they have stream attribute.

"base_classes": [
"Message"
],
"beta": false,
"conditional_paths": [],
"custom_fields": {},
"description": "Define the agent's instructions, then enter a task to complete using tools.",
"display_name": "Agent",
"documentation": "",
"edited": false,
"field_order": [
"agent_llm",
"max_tokens",
"model_kwargs",
"json_mode",
"output_schema",
"model_name",
"openai_api_base",
"api_key",
"temperature",
"seed",
"output_parser",
"system_prompt",
"tools",
"input_value",
"handle_parsing_errors",
"verbose",
"max_iterations",
"agent_description",
"memory",
"sender",
"sender_name",
"n_messages",
"session_id",
"order",
"template",
"add_current_date_tool"
],
"frozen": false,
"icon": "bot",
"legacy": false,
"lf_version": "1.0.19.post2",
"metadata": {},
"output_types": [],
"outputs": [
{
"allows_loop": false,
"cache": true,
"display_name": "Response",
"method": "message_response",
"name": "response",
"selected": "Message",
"tool_mode": true,
"types": [
"Message"
],
"value": "UNDEFINED"
}
],
"pinned": false,
"template": {
"_type": "Component",
"add_current_date_tool": {
"_input_type": "BoolInput",
"advanced": true,
"display_name": "Current Date",
"dynamic": false,
"info": "If true, will add a tool to the agent that returns the current date.",
"list": false,
"name": "add_current_date_tool",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"trace_as_metadata": true,
"type": "bool",
"value": true
},
"agent_description": {
"_input_type": "MultilineInput",
"advanced": true,
"display_name": "Agent Description [Deprecated]",
"dynamic": false,
"info": "The description of the agent. This is only used when in Tool Mode. Defaults to 'A helpful assistant with access to the following tools:' and tools are added dynamically. This feature is deprecated and will be removed in future versions.",
"input_types": [
"Message"
],
"list": false,
"load_from_db": false,
"multiline": true,
"name": "agent_description",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_input": true,
"trace_as_metadata": true,
"type": "str",
"value": "A helpful assistant with access to the following tools:"
},
"agent_llm": {
"input_type": "DropdownInput",
"advanced": false,
"combobox": false,
"display_name": "Model Provider",
"dynamic": false,
"info": "The provider of the language model that the agent will use to generate responses.",
"input_types": [],
"name": "agent_llm",
"options": [
"Amazon Bedrock",
"Anthropic",
"Azure OpenAI",
"Google Generative AI",
"Groq",
"NVIDIA",
"OpenAI",
"SambaNova",
"Custom"
],
"placeholder": "",
"real_time_refresh": true,
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"type": "str",
"value": "OpenAI"
},
"api_key": {
"input_type": "SecretStrInput",
"advanced": false,
"display_name": "OpenAI API Key",
"dynamic": false,
"info": "The OpenAI API Key to use for the OpenAI model.",
"input_types": [
"Message"
],
"load_from_db": true,
"name": "api_key",
"password": true,
"placeholder": "",
"required": true,
"show": true,
"title_case": false,
"type": "str",
"value": ""
},
"code": {
"advanced": true,
"dynamic": true,
"fileTypes": [],
"file_path": "",
"info": "",
"list": false,
"load_from_db": false,
"multiline": true,
"name": "code",
"password": false,
"placeholder": "",
"required": true,
"show": true,
"title_case": false,
"type": "code",
"value": "from langchain_core.tools import StructuredTool\n\nfrom langflow.base.agents.agent import LCToolsAgentComponent\nfrom langflow.base.agents.events import ExceptionWithMessageError\nfrom langflow.base.models.model_input_constants import (\n ALL_PROVIDER_FIELDS,\n MODEL_DYNAMIC_UPDATE_FIELDS,\n MODEL_PROVIDERS_DICT,\n)\nfrom langflow.base.models.model_utils import get_model_name\nfrom langflow.components.helpers import CurrentDateComponent\nfrom langflow.components.helpers.memory import MemoryComponent\nfrom langflow.components.langchain_utilities.tool_calling import ToolCallingAgentComponent\nfrom langflow.custom.custom_component.component import get_component_toolkit\nfrom langflow.custom.utils import update_component_build_config\nfrom langflow.field_typing import Tool\nfrom langflow.io import BoolInput, DropdownInput, MultilineInput, Output\nfrom langflow.logging import logger\nfrom langflow.schema.dotdict import dotdict\nfrom langflow.schema.message import Message\n\n\ndef set_advanced_true(component_input):\n component_input.advanced = True\n return component_input\n\n\nclass AgentComponent(ToolCallingAgentComponent):\n display_name: str = "Agent"\n description: str = "Define the agent's instructions, then enter a task to complete using tools."\n icon = "bot"\n beta = False\n name = "Agent"\n\n memory_inputs = [set_advanced_true(component_input) for component_input in MemoryComponent().inputs]\n\n inputs = [\n DropdownInput(\n name="agent_llm",\n display_name="Model Provider",\n info="The provider of the language model that the agent will use to generate responses.",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), "Custom"],\n value="OpenAI",\n real_time_refresh=True,\n input_types=[],\n ),\n *MODEL_PROVIDERS_DICT["OpenAI"]["inputs"],\n MultilineInput(\n name="system_prompt",\n display_name="Agent Instructions",\n info="System Prompt: Initial instructions and context provided to guide the agent's behavior.",\n value="You are a helpful assistant that can use tools to answer questions and perform tasks.",\n advanced=False,\n ),\n *LCToolsAgentComponent.base_inputs,\n *memory_inputs,\n BoolInput(\n name="add_current_date_tool",\n display_name="Current Date",\n advanced=True,\n info="If true, will add a tool to the agent that returns the current date.",\n value=True,\n ),\n ]\n outputs = [Output(name="response", display_name="Response", method="message_response")]\n\n async def message_response(self) -> Message:\n try:\n # Get LLM model and validate\n llm_model, display_name = self.get_llm()\n if llm_model is None:\n msg = "No language model selected. Please choose a model to proceed."\n raise ValueError(msg)\n self.model_name = get_model_name(llm_model, display_name=display_name)\n\n # Get memory data\n self.chat_history = await self.get_memory_data()\n\n # Add current date tool if enabled\n if self.add_current_date_tool:\n if not isinstance(self.tools, list): # type: ignore[has-type]\n self.tools = []\n current_date_tool = (await CurrentDateComponent(**self.get_base_args()).to_toolkit()).pop(0)\n if not isinstance(current_date_tool, StructuredTool):\n msg = "CurrentDateComponent must be converted to a StructuredTool"\n raise TypeError(msg)\n self.tools.append(current_date_tool)\n\n # Validate tools\n if not self.tools:\n msg = "Tools are required to run the agent. Please add at least one tool."\n raise ValueError(msg)\n\n # Set up and run agent\n self.set(\n llm=llm_model,\n tools=self.tools,\n chat_history=self.chat_history,\n input_value=self.input_value,\n system_prompt=self.system_prompt,\n )\n agent = self.create_agent_runnable()\n return await self.run_agent(agent)\n\n except (ValueError, TypeError, KeyError) as e:\n logger.error(f"{type(e).name}: {e!s}")\n raise\n except ExceptionWithMessageError as e:\n logger.error(f"ExceptionWithMessageError occurred: {e}")\n raise\n except Exception as e:\n logger.error(f"Unexpected error: {e!s}")\n raise\n\n async def get_memory_data(self):\n memory_kwargs = {\n component_input.name: getattr(self, f"{component_input.name}") for component_input in self.memory_inputs\n }\n # filter out empty values\n memory_kwargs = {k: v for k, v in memory_kwargs.items() if v}\n\n return await MemoryComponent(**self.get_base_args()).set(**memory_kwargs).retrieve_messages()\n\n def get_llm(self):\n if not isinstance(self.agent_llm, str):\n return self.agent_llm, None\n\n try:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if not provider_info:\n msg = f"Invalid model provider: {self.agent_llm}"\n raise ValueError(msg)\n\n component_class = provider_info.get("component_class")\n display_name = component_class.display_name\n inputs = provider_info.get("inputs")\n prefix = provider_info.get("prefix", "")\n\n return self.build_llm_model(component_class, inputs, prefix), display_name\n\n except Exception as e:\n logger.error(f"Error building {self.agent_llm} language model: {e!s}")\n msg = f"Failed to initialize language model: {e!s}"\n raise ValueError(msg) from e\n\n def build_llm_model(self, component, inputs, prefix=""):\n model_kwargs = {input.name: getattr(self, f"{prefix}{input.name}") for input in inputs}\n return component.set(**model_kwargs).build_model()\n\n def set_component_params(self, component):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n inputs = provider_info.get("inputs")\n prefix = provider_info.get("prefix")\n model_kwargs = {input.name: getattr(self, f"{prefix}{input.name}") for input in inputs}\n\n return component.set(**model_kwargs)\n return component\n\n def delete_fields(self, build_config: dotdict, fields: dict | list[str]) -> None:\n """Delete specified fields from build_config."""\n for field in fields:\n build_config.pop(field, None)\n\n def update_input_types(self, build_config: dotdict) -> dotdict:\n """Update input types for all fields in build_config."""\n for key, value in build_config.items():\n if isinstance(value, dict):\n if value.get("input_types") is None:\n build_config[key]["input_types"] = []\n elif hasattr(value, "input_types") and value.input_types is None:\n value.input_types = []\n return build_config\n\n async def update_build_config(\n self, build_config: dotdict, field_value: str, field_name: str | None = None\n ) -> dotdict:\n # Iterate over all providers in the MODEL_PROVIDERS_DICT\n # Existing logic for updating build_config\n if field_name in ("agent_llm",):\n build_config["agent_llm"]["value"] = field_value\n provider_info = MODEL_PROVIDERS_DICT.get(field_value)\n if provider_info:\n component_class = provider_info.get("component_class")\n if component_class and hasattr(component_class, "update_build_config"):\n # Call the component class's update_build_config method\n build_config = await update_component_build_config(\n component_class, build_config, field_value, "model_name"\n )\n\n provider_configs: dict[str, tuple[dict, list[dict]]] = {\n provider: (\n MODEL_PROVIDERS_DICT[provider]["fields"],\n [\n MODEL_PROVIDERS_DICT[other_provider]["fields"]\n for other_provider in MODEL_PROVIDERS_DICT\n if other_provider != provider\n ],\n )\n for provider in MODEL_PROVIDERS_DICT\n }\n if field_value in provider_configs:\n fields_to_add, fields_to_delete = provider_configs[field_value]\n\n # Delete fields from other providers\n for fields in fields_to_delete:\n self.delete_fields(build_config, fields)\n\n # Add provider-specific fields\n if field_value == "OpenAI" and not any(field in build_config for field in fields_to_add):\n build_config.update(fields_to_add)\n else:\n build_config.update(fields_to_add)\n # Reset input types for agent_llm\n build_config["agent_llm"]["input_types"] = []\n elif field_value == "Custom":\n # Delete all provider fields\n self.delete_fields(build_config, ALL_PROVIDER_FIELDS)\n # Update with custom component\n custom_component = DropdownInput(\n name="agent_llm",\n display_name="Language Model",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), "Custom"],\n value="Custom",\n real_time_refresh=True,\n input_types=["LanguageModel"],\n )\n build_config.update({"agent_llm": custom_component.to_dict()})\n # Update input types for all fields\n build_config = self.update_input_types(build_config)\n\n # Validate required keys\n default_keys = [\n "code",\n "_type",\n "agent_llm",\n "tools",\n "input_value",\n "add_current_date_tool",\n "system_prompt",\n "agent_description",\n "max_iterations",\n "handle_parsing_errors",\n "verbose",\n ]\n missing_keys = [key for key in default_keys if key not in build_config]\n if missing_keys:\n msg = f"Missing required keys in build_config: {missing_keys}"\n raise ValueError(msg)\n if (\n isinstance(self.agent_llm, str)\n and self.agent_llm in MODEL_PROVIDERS_DICT\n and field_name in MODEL_DYNAMIC_UPDATE_FIELDS\n ):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get("component_class")\n component_class = self.set_component_params(component_class)\n prefix = provider_info.get("prefix")\n if component_class and hasattr(component_class, "update_build_config"):\n # Call each component class's update_build_config method\n # remove the prefix from the field_name\n if isinstance(field_name, str) and isinstance(prefix, str):\n field_name = field_name.replace(prefix, "")\n build_config = await update_component_build_config(\n component_class, build_config, field_value, "model_name"\n )\n return dotdict({k: v.to_dict() if hasattr(v, "to_dict") else v for k, v in build_config.items()})\n\n async def to_toolkit(self) -> list[Tool]:\n component_toolkit = _get_component_toolkit()\n tools_names = self._build_tools_names()\n agent_description = self.get_tool_description()\n # TODO: Agent Description Depreciated Feature to be removed\n description = f"{agent_description}{tools_names}"\n tools = component_toolkit(component=self).get_tools(\n tool_name=self.get_tool_name(), tool_description=description, callbacks=self.get_langchain_callbacks()\n )\n if hasattr(self, "tools_metadata"):\n tools = component_toolkit(component=self, metadata=self.tools_metadata).update_tools_metadata(tools=tools)\n return tools\n"
},
"handle_parsing_errors": {
"_input_type": "BoolInput",
"advanced": true,
"display_name": "Handle Parse Errors",
"dynamic": false,
"info": "Should the Agent fix errors when reading user input for better processing?",
"list": false,
"name": "handle_parsing_errors",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"trace_as_metadata": true,
"type": "bool",
"value": true
},
"input_value": {
"_input_type": "MessageTextInput",
"advanced": false,
"display_name": "Input",
"dynamic": false,
"info": "The input provided by the user for the agent to process.",
"input_types": [
"Message"
],
"list": false,
"load_from_db": false,
"name": "input_value",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": true,
"trace_as_input": true,
"trace_as_metadata": true,
"type": "str",
"value": ""
},
"json_mode": {
"_input_type": "BoolInput",
"advanced": true,
"display_name": "JSON Mode",
"dynamic": false,
"info": "If True, it will output JSON regardless of passing a schema.",
"list": false,
"name": "json_mode",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"trace_as_metadata": true,
"type": "bool",
"value": false
},
"max_iterations": {
"_input_type": "IntInput",
"advanced": true,
"display_name": "Max Iterations",
"dynamic": false,
"info": "The maximum number of attempts the agent can make to complete its task before it stops.",
"list": false,
"name": "max_iterations",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"trace_as_metadata": true,
"type": "int",
"value": 15
},
"max_retries": {
"_input_type": "IntInput",
"advanced": true,
"display_name": "Max Retries",
"dynamic": false,
"info": "The maximum number of retries to make when generating.",
"list": false,
"list_add_label": "Add More",
"name": "max_retries",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"type": "int",
"value": 5
},
"max_tokens": {
"_input_type": "IntInput",
"advanced": true,
"display_name": "Max Tokens",
"dynamic": false,
"info": "The maximum number of tokens to generate. Set to 0 for unlimited tokens.",
"list": false,
"name": "max_tokens",
"placeholder": "",
"range_spec": {
"max": 128000,
"min": 0,
"step": 0.1,
"step_type": "float"
},
"required": false,
"show": true,
"title_case": false,
"trace_as_metadata": true,
"type": "int",
"value": ""
},
"memory": {
"_input_type": "HandleInput",
"advanced": true,
"display_name": "External Memory",
"dynamic": false,
"info": "Retrieve messages from an external memory. If empty, it will use the Langflow tables.",
"input_types": [
"Memory"
],
"list": false,
"name": "memory",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"trace_as_metadata": true,
"type": "other",
"value": ""
},
"model_kwargs": {
"_input_type": "DictInput",
"advanced": true,
"display_name": "Model Kwargs",
"dynamic": false,
"info": "Additional keyword arguments to pass to the model.",
"list": false,
"name": "model_kwargs",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"trace_as_input": true,
"type": "dict",
"value": {}
},
"model_name": {
"_input_type": "DropdownInput",
"advanced": false,
"combobox": true,
"display_name": "Model Name",
"dynamic": false,
"info": "To see the model names, first choose a provider. Then, enter your API key and click the refresh button next to the model name.",
"name": "model_name",
"options": [
"gpt-4o-mini",
"gpt-4o",
"gpt-4-turbo",
"gpt-4-turbo-preview",
"gpt-4",
"gpt-3.5-turbo",
"gpt-3.5-turbo-0125"
],
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"type": "str",
"value": "gpt-4o-mini"
},
"n_messages": {
"_input_type": "IntInput",
"advanced": true,
"display_name": "Number of Messages",
"dynamic": false,
"info": "Number of messages to retrieve.",
"list": false,
"name": "n_messages",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"trace_as_metadata": true,
"type": "int",
"value": 100
},
"openai_api_base": {
"_input_type": "StrInput",
"advanced": true,
"display_name": "OpenAI API Base",
"dynamic": false,
"info": "The base URL of the OpenAI API. Defaults to https://api.openai.com/v1. You can change this to use other APIs like JinaChat, LocalAI and Prem.",
"list": false,
"load_from_db": false,
"name": "openai_api_base",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"trace_as_metadata": true,
"type": "str",
"value": ""
},
"order": {
"_input_type": "DropdownInput",
"advanced": true,
"combobox": false,
"display_name": "Order",
"dynamic": false,
"info": "Order of the messages.",
"name": "order",
"options": [
"Ascending",
"Descending"
],
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"type": "str",
"value": "Ascending"
},
"seed": {
"_input_type": "IntInput",
"advanced": true,
"display_name": "Seed",
"dynamic": false,
"info": "The seed controls the reproducibility of the job.",
"list": false,
"name": "seed",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"trace_as_metadata": true,
"type": "int",
"value": 1
},
"sender": {
"_input_type": "DropdownInput",
"advanced": true,
"combobox": false,
"display_name": "Sender Type",
"dynamic": false,
"info": "Filter by sender type.",
"name": "sender",
"options": [
"Machine",
"User",
"Machine and User"
],
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"type": "str",
"value": "Machine and User"
},
"sender_name": {
"_input_type": "MessageTextInput",
"advanced": true,
"display_name": "Sender Name",
"dynamic": false,
"info": "Filter by sender name.",
"input_types": [
"Message"
],
"list": false,
"load_from_db": false,
"name": "sender_name",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_input": true,
"trace_as_metadata": true,
"type": "str",
"value": ""
},
"session_id": {
"_input_type": "MessageTextInput",
"advanced": true,
"display_name": "Session ID",
"dynamic": false,
"info": "The session ID of the chat. If empty, the current session ID parameter will be used.",
"input_types": [
"Message"
],
"list": false,
"load_from_db": false,
"name": "session_id",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_input": true,
"trace_as_metadata": true,
"type": "str",
"value": ""
},
"system_prompt": {
"_input_type": "MultilineInput",
"advanced": false,
"display_name": "Agent Instructions",
"dynamic": false,
"info": "System Prompt: Initial instructions and context provided to guide the agent's behavior.",
"input_types": [
"Message"
],
"list": false,
"load_from_db": false,
"multiline": true,
"name": "system_prompt",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_input": true,
"trace_as_metadata": true,
"type": "str",
"value": "You are a research analyst with access to Tavily Search."
},
"temperature": {
"_input_type": "FloatInput",
"advanced": true,
"display_name": "Temperature",
"dynamic": false,
"info": "",
"list": false,
"name": "temperature",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"trace_as_metadata": true,
"type": "float",
"value": 0.1
},
"template": {
"_input_type": "MultilineInput",
"advanced": true,
"display_name": "Template",
"dynamic": false,
"info": "The template to use for formatting the data. It can contain the keys {text}, {sender} or any other key in the message data.",
"input_types": [
"Message"
],
"list": false,
"load_from_db": false,
"multiline": true,
"name": "template",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_input": true,
"trace_as_metadata": true,
"type": "str",
"value": "{sender_name}: {text}"
},
"timeout": {
"_input_type": "IntInput",
"advanced": true,
"display_name": "Timeout",
"dynamic": false,
"info": "The timeout for requests to OpenAI completion API.",
"list": false,
"list_add_label": "Add More",
"name": "timeout",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"type": "int",
"value": 700
},
"tools": {
"_input_type": "HandleInput",
"advanced": false,
"display_name": "Tools",
"dynamic": false,
"info": "These are the tools that the agent can use to help with tasks.",
"input_types": [
"Tool"
],
"list": true,
"name": "tools",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"trace_as_metadata": true,
"type": "other",
"value": ""
},
"verbose": {
"_input_type": "BoolInput",
"advanced": true,
"display_name": "Verbose",
"dynamic": false,
"info": "",
"list": false,
"name": "verbose",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"trace_as_metadata": true,
"type": "bool",
"value": true
}
},
"tool_mode": false
},
"type": "Agent"
},

[dosubot[bot]]

The Agent component in Langflow does indeed have a "stream" parameter, which is used to stream the response from the model, specifically in Chat contexts. This parameter is a boolean input and is not required, defaulting to false if not set ^[1]. If the "stream" parameter is not visible in the UI, it might be due to a configuration issue or a version mismatch between the codebase and the deployed UI. The parameter is set to be visible ("show": true), so it should appear unless there are other UI constraints or customizations affecting its display ^[1].

To continue talking to Dosu, mention @dosu.

---

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other}

[raprajapati1208]

@dosu

This is the class of the Agent Component.

from langchain_core.tools import StructuredTool

from langflow.base.agents.agent import LCToolsAgentComponent
from langflow.base.agents.events import ExceptionWithMessageError
from langflow.base.models.model_input_constants import (
ALL_PROVIDER_FIELDS,
MODEL_DYNAMIC_UPDATE_FIELDS,
MODEL_PROVIDERS_DICT,
)
from langflow.base.models.model_utils import get_model_name
from langflow.components.helpers import CurrentDateComponent
from langflow.components.helpers.memory import MemoryComponent
from langflow.components.langchain_utilities.tool_calling import ToolCallingAgentComponent
from langflow.custom.custom_component.component import _get_component_toolkit
from langflow.custom.utils import update_component_build_config
from langflow.field_typing import Tool
from langflow.io import BoolInput, DropdownInput, MultilineInput, Output
from langflow.logging import logger
from langflow.schema.dotdict import dotdict
from langflow.schema.message import Message

def set_advanced_true(component_input):
component_input.advanced = True
return component_input

class AgentComponent(ToolCallingAgentComponent):
display_name: str = "Agent"
description: str = "Define the agent's instructions, then enter a task to complete using tools."
icon = "bot"
beta = False
name = "Agent"

memory_inputs = [set_advanced_true(component_input) for component_input in MemoryComponent().inputs]

inputs = [
    DropdownInput(
        name="agent_llm",
        display_name="Model Provider",
        info="The provider of the language model that the agent will use to generate responses.",
        options=[*sorted(MODEL_PROVIDERS_DICT.keys()), "Custom"],
        value="OpenAI",
        real_time_refresh=True,
        input_types=[],
    ),
    *MODEL_PROVIDERS_DICT["OpenAI"]["inputs"],
    MultilineInput(
        name="system_prompt",
        display_name="Agent Instructions",
        info="System Prompt: Initial instructions and context provided to guide the agent's behavior.",
        value="You are a helpful assistant that can use tools to answer questions and perform tasks.",
        advanced=False,
    ),
    *LCToolsAgentComponent._base_inputs,
    *memory_inputs,
    BoolInput(
        name="add_current_date_tool",
        display_name="Current Date",
        advanced=True,
        info="If true, will add a tool to the agent that returns the current date.",
        value=True,
    ),
]
outputs = [Output(name="response", display_name="Response", method="message_response")]

async def message_response(self) -> Message:
    try:
        # Get LLM model and validate
        llm_model, display_name = self.get_llm()
        if llm_model is None:
            msg = "No language model selected. Please choose a model to proceed."
            raise ValueError(msg)
        self.model_name = get_model_name(llm_model, display_name=display_name)

        # Get memory data
        self.chat_history = await self.get_memory_data()

        # Add current date tool if enabled
        if self.add_current_date_tool:
            if not isinstance(self.tools, list):  # type: ignore[has-type]
                self.tools = []
            current_date_tool = (await CurrentDateComponent(**self.get_base_args()).to_toolkit()).pop(0)
            if not isinstance(current_date_tool, StructuredTool):
                msg = "CurrentDateComponent must be converted to a StructuredTool"
                raise TypeError(msg)
            self.tools.append(current_date_tool)

        # Validate tools
        if not self.tools:
            msg = "Tools are required to run the agent. Please add at least one tool."
            raise ValueError(msg)

        # Set up and run agent
        self.set(
            llm=llm_model,
            tools=self.tools,
            chat_history=self.chat_history,
            input_value=self.input_value,
            system_prompt=self.system_prompt,
        )
        agent = self.create_agent_runnable()
        return await self.run_agent(agent)

    except (ValueError, TypeError, KeyError) as e:
        logger.error(f"{type(e).__name__}: {e!s}")
        raise
    except ExceptionWithMessageError as e:
        logger.error(f"ExceptionWithMessageError occurred: {e}")
        raise
    except Exception as e:
        logger.error(f"Unexpected error: {e!s}")
        raise

async def get_memory_data(self):
    memory_kwargs = {
        component_input.name: getattr(self, f"{component_input.name}") for component_input in self.memory_inputs
    }
    # filter out empty values
    memory_kwargs = {k: v for k, v in memory_kwargs.items() if v}

    return await MemoryComponent(**self.get_base_args()).set(**memory_kwargs).retrieve_messages()

def get_llm(self):
    if not isinstance(self.agent_llm, str):
        return self.agent_llm, None

    try:
        provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)
        if not provider_info:
            msg = f"Invalid model provider: {self.agent_llm}"
            raise ValueError(msg)

        component_class = provider_info.get("component_class")
        display_name = component_class.display_name
        inputs = provider_info.get("inputs")
        prefix = provider_info.get("prefix", "")

        return self._build_llm_model(component_class, inputs, prefix), display_name

    except Exception as e:
        logger.error(f"Error building {self.agent_llm} language model: {e!s}")
        msg = f"Failed to initialize language model: {e!s}"
        raise ValueError(msg) from e

def _build_llm_model(self, component, inputs, prefix=""):
    model_kwargs = {input_.name: getattr(self, f"{prefix}{input_.name}") for input_ in inputs}
    return component.set(**model_kwargs).build_model()

def set_component_params(self, component):
    provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)
    if provider_info:
        inputs = provider_info.get("inputs")
        prefix = provider_info.get("prefix")
        model_kwargs = {input_.name: getattr(self, f"{prefix}{input_.name}") for input_ in inputs}

        return component.set(**model_kwargs)
    return component

def delete_fields(self, build_config: dotdict, fields: dict | list[str]) -> None:
    """Delete specified fields from build_config."""
    for field in fields:
        build_config.pop(field, None)

def update_input_types(self, build_config: dotdict) -> dotdict:
    """Update input types for all fields in build_config."""
    for key, value in build_config.items():
        if isinstance(value, dict):
            if value.get("input_types") is None:
                build_config[key]["input_types"] = []
        elif hasattr(value, "input_types") and value.input_types is None:
            value.input_types = []
    return build_config

async def update_build_config(
    self, build_config: dotdict, field_value: str, field_name: str | None = None
) -> dotdict:
    # Iterate over all providers in the MODEL_PROVIDERS_DICT
    # Existing logic for updating build_config
    if field_name in ("agent_llm",):
        build_config["agent_llm"]["value"] = field_value
        provider_info = MODEL_PROVIDERS_DICT.get(field_value)
        if provider_info:
            component_class = provider_info.get("component_class")
            if component_class and hasattr(component_class, "update_build_config"):
                # Call the component class's update_build_config method
                build_config = await update_component_build_config(
                    component_class, build_config, field_value, "model_name"
                )

        provider_configs: dict[str, tuple[dict, list[dict]]] = {
            provider: (
                MODEL_PROVIDERS_DICT[provider]["fields"],
                [
                    MODEL_PROVIDERS_DICT[other_provider]["fields"]
                    for other_provider in MODEL_PROVIDERS_DICT
                    if other_provider != provider
                ],
            )
            for provider in MODEL_PROVIDERS_DICT
        }
        if field_value in provider_configs:
            fields_to_add, fields_to_delete = provider_configs[field_value]

            # Delete fields from other providers
            for fields in fields_to_delete:
                self.delete_fields(build_config, fields)

            # Add provider-specific fields
            if field_value == "OpenAI" and not any(field in build_config for field in fields_to_add):
                build_config.update(fields_to_add)
            else:
                build_config.update(fields_to_add)
            # Reset input types for agent_llm
            build_config["agent_llm"]["input_types"] = []
        elif field_value == "Custom":
            # Delete all provider fields
            self.delete_fields(build_config, ALL_PROVIDER_FIELDS)
            # Update with custom component
            custom_component = DropdownInput(
                name="agent_llm",
                display_name="Language Model",
                options=[*sorted(MODEL_PROVIDERS_DICT.keys()), "Custom"],
                value="Custom",
                real_time_refresh=True,
                input_types=["LanguageModel"],
            )
            build_config.update({"agent_llm": custom_component.to_dict()})
        # Update input types for all fields
        build_config = self.update_input_types(build_config)

        # Validate required keys
        default_keys = [
            "code",
            "_type",
            "agent_llm",
            "tools",
            "input_value",
            "add_current_date_tool",
            "system_prompt",
            "agent_description",
            "max_iterations",
            "handle_parsing_errors",
            "verbose",
        ]
        missing_keys = [key for key in default_keys if key not in build_config]
        if missing_keys:
            msg = f"Missing required keys in build_config: {missing_keys}"
            raise ValueError(msg)
    if (
        isinstance(self.agent_llm, str)
        and self.agent_llm in MODEL_PROVIDERS_DICT
        and field_name in MODEL_DYNAMIC_UPDATE_FIELDS
    ):
        provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)
        if provider_info:
            component_class = provider_info.get("component_class")
            component_class = self.set_component_params(component_class)
            prefix = provider_info.get("prefix")
            if component_class and hasattr(component_class, "update_build_config"):
                # Call each component class's update_build_config method
                # remove the prefix from the field_name
                if isinstance(field_name, str) and isinstance(prefix, str):
                    field_name = field_name.replace(prefix, "")
                build_config = await update_component_build_config(
                    component_class, build_config, field_value, "model_name"
                )
    return dotdict({k: v.to_dict() if hasattr(v, "to_dict") else v for k, v in build_config.items()})

async def to_toolkit(self) -> list[Tool]:
    component_toolkit = _get_component_toolkit()
    tools_names = self._build_tools_names()
    agent_description = self.get_tool_description()
    # TODO: Agent Description Depreciated Feature to be removed
    description = f"{agent_description}{tools_names}"
    tools = component_toolkit(component=self).get_tools(
        tool_name=self.get_tool_name(), tool_description=description, callbacks=self.get_langchain_callbacks()
    )
    if hasattr(self, "tools_metadata"):
        tools = component_toolkit(component=self, metadata=self.tools_metadata).update_tools_metadata(tools=tools)
    return tools

There is no paramter stream to enable streaming of responses.

[raprajapati1208]

@dosu

Can you check my above comment?

[dosubot[bot]]

The AgentComponent class you provided does not explicitly include a stream parameter in its definition. It seems there might have been a misunderstanding or miscommunication regarding the presence of a stream parameter directly within the AgentComponent class itself. The streaming functionality might be managed at a different level or through another component or configuration in the Langflow system, particularly in the context of LLM models or other components that interact with the agent.

If streaming is required, you might need to look into how the LLM models are configured or how the flow is executed to ensure that streaming is enabled. The stream parameter is typically associated with the execution of flows and might be set at the API request level rather than within the AgentComponent class itself ^[1].

To continue talking to Dosu, mention @dosu.

---

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other}

[RKNSSANG]

@raprajapati1208 hi, i meet the same question. Have you solved the problem?

[AkhilRamani]

Also having same problem. Only getting add_message events