Skip to content

fix: Wait for dynamic model fetch in Nvidia #12229

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
erichare merged 11 commits into from
Mar 20, 2026
Merged

fix: Wait for dynamic model fetch in Nvidia #12229

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
b0a54a1
fix: Wait for dynamic model fetch in Nvidia
erichare Mar 18, 2026
22013c1
[autofix.ci] apply automated fixes
autofix-ci[bot] Mar 18, 2026
da2b836
Create test_nvidia_component.py
erichare Mar 18, 2026
31cafd8
Update test_nvidia_component.py
erichare Mar 18, 2026
9ba0b78
[autofix.ci] apply automated fixes
autofix-ci[bot] Mar 18, 2026
41b7e13
Potential fix for pull request finding
erichare Mar 18, 2026
357a878
[autofix.ci] apply automated fixes
autofix-ci[bot] Mar 18, 2026
35aef32
Update test_nvidia_component.py
erichare Mar 18, 2026
47b3939
Merge branch 'release-1.9.0' into fix-nvidia-blocking-fetch
erichare Mar 19, 2026
fd6f41b
Update component_index.json
erichare Mar 19, 2026
6ebb9ba
[autofix.ci] apply automated fixes
autofix-ci[bot] Mar 19, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
129 changes: 4 additions & 125 deletions src/lfx/src/lfx/_assets/component_index.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -95195,7 +95195,7 @@
"icon": "NVIDIA",
"legacy": false,
"metadata": {
"code_hash": "fd6cae31c2a0",
"code_hash": "49e60e24ef53",
"dependencies": {
"dependencies": [
{
Expand Down Expand Up @@ -95312,7 +95312,7 @@
"show": true,
"title_case": false,
"type": "code",
"value": "from typing import Any\n\nfrom lfx.base.models.model import LCModelComponent\nfrom lfx.field_typing import LanguageModel\nfrom lfx.field_typing.range_spec import RangeSpec\nfrom lfx.inputs.inputs import BoolInput, DropdownInput, IntInput, MessageTextInput, SecretStrInput, SliderInput\nfrom lfx.log.logger import logger\nfrom lfx.schema.dotdict import dotdict\n\n\nclass NVIDIAModelComponent(LCModelComponent):\n display_name = \"NVIDIA\"\n description = \"Generates text using NVIDIA LLMs.\"\n icon = \"NVIDIA\"\n\n try:\n import warnings\n\n # Suppresses repeated warnings about NIM key in langchain_nvidia_ai_endpoints==0.3.8\n warnings.filterwarnings(\"ignore\", category=UserWarning, module=\"langchain_nvidia_ai_endpoints._common\")\n from langchain_nvidia_ai_endpoints import ChatNVIDIA\n\n all_models = ChatNVIDIA().get_available_models()\n except ImportError as e:\n msg = \"Please install langchain-nvidia-ai-endpoints to use the NVIDIA model.\"\n raise ImportError(msg) from e\n except Exception as e: # noqa: BLE001\n logger.warning(f\"Failed to fetch NVIDIA models during initialization: {e}. Model list will be unavailable.\")\n all_models = []\n\n inputs = [\n *LCModelComponent.get_base_inputs(),\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n info=\"The name of the NVIDIA model to use.\",\n advanced=False,\n value=None,\n options=sorted(model.id for model in all_models),\n combobox=True,\n refresh_button=True,\n ),\n BoolInput(\n name=\"detailed_thinking\",\n display_name=\"Detailed Thinking\",\n info=\"If true, the model will return a detailed thought process. Only supported by reasoning models.\",\n value=False,\n show=False,\n ),\n BoolInput(\n name=\"tool_model_enabled\",\n display_name=\"Enable Tool Models\",\n info=\"If enabled, only show models that support tool-calling.\",\n advanced=False,\n value=False,\n real_time_refresh=True,\n ),\n MessageTextInput(\n name=\"base_url\",\n display_name=\"NVIDIA Base URL\",\n value=\"https://integrate.api.nvidia.com/v1\",\n info=\"The base URL of the NVIDIA API. Defaults to https://integrate.api.nvidia.com/v1.\",\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"NVIDIA API Key\",\n info=\"The NVIDIA API Key.\",\n advanced=False,\n value=\"NVIDIA_API_KEY\",\n ),\n SliderInput(\n name=\"temperature\",\n display_name=\"Temperature\",\n value=0.1,\n info=\"Run inference with this temperature.\",\n range_spec=RangeSpec(min=0, max=1, step=0.01),\n advanced=True,\n ),\n IntInput(\n name=\"seed\",\n display_name=\"Seed\",\n info=\"The seed controls the reproducibility of the job.\",\n advanced=True,\n value=1,\n ),\n ]\n\n def get_models(self, *, tool_model_enabled: bool | None = None) -> list[str]:\n try:\n from langchain_nvidia_ai_endpoints import ChatNVIDIA\n except ImportError as e:\n msg = \"Please install langchain-nvidia-ai-endpoints to use the NVIDIA model.\"\n raise ImportError(msg) from e\n\n # Note: don't include the previous model, as it may not exist in available models from the new base url\n model = ChatNVIDIA(base_url=self.base_url, api_key=self.api_key)\n if tool_model_enabled:\n tool_models = [m for m in model.get_available_models() if m.supports_tools]\n return sorted(m.id for m in tool_models)\n return sorted(m.id for m in model.available_models)\n\n def update_build_config(self, build_config: dotdict, _field_value: Any, field_name: str | None = None):\n if field_name in {\"model_name\", \"tool_model_enabled\", \"base_url\", \"api_key\"}:\n try:\n ids = self.get_models(tool_model_enabled=self.tool_model_enabled)\n build_config[\"model_name\"][\"options\"] = ids\n\n if \"value\" not in build_config[\"model_name\"] or build_config[\"model_name\"][\"value\"] is None:\n build_config[\"model_name\"][\"value\"] = ids[0]\n elif build_config[\"model_name\"][\"value\"] not in ids:\n build_config[\"model_name\"][\"value\"] = None\n\n # TODO: use api to determine if model supports detailed thinking\n if build_config[\"model_name\"][\"value\"] == \"nemotron\":\n build_config[\"detailed_thinking\"][\"show\"] = True\n else:\n build_config[\"detailed_thinking\"][\"value\"] = False\n build_config[\"detailed_thinking\"][\"show\"] = False\n except Exception as e:\n msg = f\"Error getting model names: {e}\"\n build_config[\"model_name\"][\"value\"] = None\n build_config[\"model_name\"][\"options\"] = []\n raise ValueError(msg) from e\n\n return build_config\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n try:\n from langchain_nvidia_ai_endpoints import ChatNVIDIA\n except ImportError as e:\n msg = \"Please install langchain-nvidia-ai-endpoints to use the NVIDIA model.\"\n raise ImportError(msg) from e\n api_key = self.api_key\n temperature = self.temperature\n model_name: str = self.model_name\n max_tokens = self.max_tokens\n seed = self.seed\n return ChatNVIDIA(\n max_tokens=max_tokens or None,\n model=model_name,\n base_url=self.base_url,\n api_key=api_key,\n temperature=temperature or 0.1,\n seed=seed,\n )\n"
"value": "from typing import Any\n\nfrom lfx.base.models.model import LCModelComponent\nfrom lfx.field_typing import LanguageModel\nfrom lfx.field_typing.range_spec import RangeSpec\nfrom lfx.inputs.inputs import BoolInput, DropdownInput, IntInput, MessageTextInput, SecretStrInput, SliderInput\nfrom lfx.schema.dotdict import dotdict\n\n\nclass NVIDIAModelComponent(LCModelComponent):\n display_name = \"NVIDIA\"\n description = \"Generates text using NVIDIA LLMs.\"\n icon = \"NVIDIA\"\n\n inputs = [\n *LCModelComponent.get_base_inputs(),\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n info=\"The name of the NVIDIA model to use.\",\n advanced=False,\n value=None,\n options=[],\n combobox=True,\n refresh_button=True,\n ),\n BoolInput(\n name=\"detailed_thinking\",\n display_name=\"Detailed Thinking\",\n info=\"If true, the model will return a detailed thought process. Only supported by reasoning models.\",\n value=False,\n show=False,\n ),\n BoolInput(\n name=\"tool_model_enabled\",\n display_name=\"Enable Tool Models\",\n info=\"If enabled, only show models that support tool-calling.\",\n advanced=False,\n value=False,\n real_time_refresh=True,\n ),\n MessageTextInput(\n name=\"base_url\",\n display_name=\"NVIDIA Base URL\",\n value=\"https://integrate.api.nvidia.com/v1\",\n info=\"The base URL of the NVIDIA API. Defaults to https://integrate.api.nvidia.com/v1.\",\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"NVIDIA API Key\",\n info=\"The NVIDIA API Key.\",\n advanced=False,\n value=\"NVIDIA_API_KEY\",\n ),\n SliderInput(\n name=\"temperature\",\n display_name=\"Temperature\",\n value=0.1,\n info=\"Run inference with this temperature.\",\n range_spec=RangeSpec(min=0, max=1, step=0.01),\n advanced=True,\n ),\n IntInput(\n name=\"seed\",\n display_name=\"Seed\",\n info=\"The seed controls the reproducibility of the job.\",\n advanced=True,\n value=1,\n ),\n ]\n\n def get_models(self, *, tool_model_enabled: bool | None = None) -> list[str]:\n try:\n from langchain_nvidia_ai_endpoints import ChatNVIDIA\n except ImportError as e:\n msg = \"Please install langchain-nvidia-ai-endpoints to use the NVIDIA model.\"\n raise ImportError(msg) from e\n\n # Note: don't include the previous model, as it may not exist in available models from the new base url\n model = ChatNVIDIA(base_url=self.base_url, api_key=self.api_key)\n if tool_model_enabled:\n tool_models = [m for m in model.get_available_models() if m.supports_tools]\n return sorted(m.id for m in tool_models)\n return sorted(m.id for m in model.available_models)\n\n def update_build_config(self, build_config: dotdict, _field_value: Any, field_name: str | None = None):\n if field_name in {\"model_name\", \"tool_model_enabled\", \"base_url\", \"api_key\"}:\n try:\n ids = self.get_models(tool_model_enabled=self.tool_model_enabled)\n build_config[\"model_name\"][\"options\"] = ids\n\n if \"value\" not in build_config[\"model_name\"] or build_config[\"model_name\"][\"value\"] is None:\n build_config[\"model_name\"][\"value\"] = ids[0]\n elif build_config[\"model_name\"][\"value\"] not in ids:\n build_config[\"model_name\"][\"value\"] = None\n\n # TODO: use api to determine if model supports detailed thinking\n if build_config[\"model_name\"][\"value\"] == \"nemotron\":\n build_config[\"detailed_thinking\"][\"show\"] = True\n else:\n build_config[\"detailed_thinking\"][\"value\"] = False\n build_config[\"detailed_thinking\"][\"show\"] = False\n except Exception as e:\n msg = f\"Error getting model names: {e}\"\n build_config[\"model_name\"][\"value\"] = None\n build_config[\"model_name\"][\"options\"] = []\n raise ValueError(msg) from e\n\n return build_config\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n try:\n from langchain_nvidia_ai_endpoints import ChatNVIDIA\n except ImportError as e:\n msg = \"Please install langchain-nvidia-ai-endpoints to use the NVIDIA model.\"\n raise ImportError(msg) from e\n api_key = self.api_key\n temperature = self.temperature\n model_name: str = self.model_name\n max_tokens = self.max_tokens\n seed = self.seed\n return ChatNVIDIA(\n max_tokens=max_tokens or None,\n model=model_name,\n base_url=self.base_url,\n api_key=api_key,\n temperature=temperature or 0.1,\n seed=seed,\n )\n"
},
"detailed_thinking": {
"_input_type": "BoolInput",
Expand Down Expand Up @@ -95389,128 +95389,7 @@
"external_options": {},
"info": "The name of the NVIDIA model to use.",
"name": "model_name",
"options": [
"01-ai/yi-large",
"abacusai/dracarys-llama-3.1-70b-instruct",
"aisingapore/sea-lion-7b-instruct",
"baichuan-inc/baichuan2-13b-chat",
"bytedance/seed-oss-36b-instruct",
"deepseek-ai/deepseek-r1",
"deepseek-ai/deepseek-r1-0528",
"deepseek-ai/deepseek-r1-distill-llama-8b",
"deepseek-ai/deepseek-r1-distill-qwen-14b",
"deepseek-ai/deepseek-r1-distill-qwen-32b",
"deepseek-ai/deepseek-r1-distill-qwen-7b",
"deepseek-ai/deepseek-v3.1",
"deepseek-ai/deepseek-v3.1-terminus",
"deepseek-ai/deepseek-v3.2",
"google/codegemma-7b",
"google/gemma-2-27b-it",
"google/gemma-2-2b-it",
"google/gemma-2-9b-it",
"google/gemma-3-12b-it",
"google/gemma-3-1b-it",
"google/gemma-3-27b-it",
"google/gemma-3-4b-it",
"google/gemma-3n-e2b-it",
"google/gemma-3n-e4b-it",
"google/gemma-7b",
"google/paligemma",
"google/shieldgemma-9b",
"gotocompany/gemma-2-9b-cpt-sahabatai-instruct",
"ibm/granite-3.3-8b-instruct",
"ibm/granite-guardian-3.0-8b",
"igenius/colosseum_355b_instruct_16k",
"igenius/italia_10b_instruct_16k",
"institute-of-science-tokyo/llama-3.1-swallow-70b-instruct-v0.1",
"institute-of-science-tokyo/llama-3.1-swallow-8b-instruct-v0.1",
"marin/marin-8b-instruct",
"mediatek/breeze-7b-instruct",
"meta/llama-3.1-405b-instruct",
"meta/llama-3.1-70b-instruct",
"meta/llama-3.1-8b-instruct",
"meta/llama-3.2-11b-vision-instruct",
"meta/llama-3.2-1b-instruct",
"meta/llama-3.2-3b-instruct",
"meta/llama-3.2-90b-vision-instruct",
"meta/llama-3.3-70b-instruct",
"meta/llama-4-maverick-17b-128e-instruct",
"meta/llama-4-scout-17b-16e-instruct",
"meta/llama-guard-4-12b",
"meta/llama3-70b-instruct",
"meta/llama3-8b-instruct",
"microsoft/phi-3-medium-128k-instruct",
"microsoft/phi-3-medium-4k-instruct",
"microsoft/phi-3-mini-128k-instruct",
"microsoft/phi-3-mini-4k-instruct",
"microsoft/phi-3-small-128k-instruct",
"microsoft/phi-3-small-8k-instruct",
"microsoft/phi-3-vision-128k-instruct",
"microsoft/phi-3.5-mini-instruct",
"microsoft/phi-3.5-vision-instruct",
"microsoft/phi-4-mini-flash-reasoning",
"microsoft/phi-4-mini-instruct",
"microsoft/phi-4-multimodal-instruct",
"minimaxai/minimax-m2",
"mistralai/codestral-22b-instruct-v0.1",
"mistralai/magistral-small-2506",
"mistralai/mamba-codestral-7b-v0.1",
"mistralai/mathstral-7b-v0.1",
"mistralai/ministral-14b-instruct-2512",
"mistralai/mistral-7b-instruct-v0.2",
"mistralai/mistral-7b-instruct-v0.3",
"mistralai/mistral-large-3-675b-instruct-2512",
"mistralai/mistral-medium-3-instruct",
"mistralai/mistral-nemotron",
"mistralai/mistral-small-24b-instruct",
"mistralai/mistral-small-3.1-24b-instruct-2503",
"mistralai/mixtral-8x22b-instruct-v0.1",
"mistralai/mixtral-8x22b-v0.1",
"mistralai/mixtral-8x7b-instruct-v0.1",
"moonshotai/kimi-k2-instruct",
"moonshotai/kimi-k2-instruct-0905",
"moonshotai/kimi-k2-thinking",
"nv-mistralai/mistral-nemo-12b-instruct",
"nvidia/llama-3.1-nemoguard-8b-content-safety",
"nvidia/llama-3.1-nemoguard-8b-topic-control",
"nvidia/llama-3.1-nemotron-70b-reward",
"nvidia/llama-3.1-nemotron-nano-4b-v1.1",
"nvidia/llama-3.1-nemotron-nano-8b-v1",
"nvidia/llama-3.1-nemotron-nano-vl-8b-v1",
"nvidia/llama-3.1-nemotron-ultra-253b-v1",
"nvidia/llama-3.3-nemotron-super-49b-v1",
"nvidia/llama-3.3-nemotron-super-49b-v1.5",
"nvidia/llama3-chatqa-1.5-8b",
"nvidia/nemoretriever-parse",
"nvidia/nemotron-3-nano-30b-a3b",
"nvidia/nemotron-4-mini-hindi-4b-instruct",
"nvidia/nemotron-mini-4b-instruct",
"nvidia/nvclip",
"nvidia/nvidia-nemotron-nano-9b-v2",
"nvidia/riva-translate-4b-instruct",
"nvidia/usdcode-llama-3.1-70b-instruct",
"openai/gpt-oss-120b",
"openai/gpt-oss-20b",
"qwen/qwen2-7b-instruct",
"qwen/qwen2.5-7b-instruct",
"qwen/qwen2.5-coder-32b-instruct",
"qwen/qwen2.5-coder-7b-instruct",
"qwen/qwen3-235b-a22b",
"qwen/qwen3-next-80b-a3b-instruct",
"qwen/qwen3-next-80b-a3b-thinking",
"qwen/qwq-32b",
"rakuten/rakutenai-7b-chat",
"rakuten/rakutenai-7b-instruct",
"speakleash/bielik-11b-v2.3-instruct",
"stepfun-ai/step-3.5-flash",
"thudm/chatglm3-6b",
"tiiuae/falcon3-7b-instruct",
"tokyotech-llm/llama-3-swallow-70b-instruct-v0.1",
"upstage/solar-10.7b-instruct",
"utter-project/eurollm-9b-instruct",
"yentinglin/llama-3-taiwan-70b-instruct",
"zyphra/zamba2-7b-instruct"
],
"options": [],
"options_metadata": [],
"override_skip": false,
"placeholder": "",
Expand Down Expand Up @@ -118996,6 +118875,6 @@
"num_components": 360,
"num_modules": 97
},
"sha256": "51c85e55df57a79a1f07284039a71a762897e18eaf82c45bba2d3d0345dda69b",
"sha256": "b94764855c04b62d41aebb120df8bbe3cf0a0df12d2759ee638923624666b5b9",
"version": "0.4.0"
}
Loading
Loading