@sateeshreddy/n8n-nodes-nvidia-nim 1.0.8 → 1.0.9

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/README.md +27 -24
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -30,7 +30,8 @@ This package includes **two nodes**:
30
30
  - ✅ Free tier models via [build.nvidia.com](https://build.nvidia.com)
31
31
  - ✅ **Language model node** — plugs into AI Agent, Basic LLM Chain, Summarization Chain
32
32
  - ✅ **Embeddings node** — plugs into any n8n vector store (Qdrant, Pinecone, PGVector, Supabase, Weaviate, Chroma)
33
- - ✅ Supports 17+ chat models including Llama 4, Mistral, Qwen3, Gemma, and more
33
+ - ✅ Supports 17 latest chat models including DeepSeek v4, Nemotron-3, Mistral, and Gemma 4
34
+ - ✅ **Smart Defaults:** Automatically updates optimal temperature and max tokens when a chat model is selected
34
35
  - ✅ Supports 5 embedding models including free hosted endpoints
35
36
  - ✅ Drop-in OpenAI-compatible API — no extra setup
36
37
 
@@ -40,25 +41,27 @@ This package includes **two nodes**:
40
41
 
41
42
  ### Chat / Language Models
42
43
 
43
- | Model | Value |
44
- |---|---|
45
- | Llama 4 Maverick 17B 128E Instruct *(default)* | `meta/llama-4-maverick-17b-128e-instruct` |
46
- | Mistral Large 3 675B Instruct | `mistralai/mistral-large-3-675b-instruct-2512` |
47
- | Qwen3 Coder 480B A35B Instruct | `qwen/qwen3-coder-480b-a35b-instruct` |
48
- | Mistral Nemotron (Function Calling) | `mistralai/mistral-nemotron` |
49
- | Mistral Medium 3 Instruct | `mistralai/mistral-medium-3-instruct` |
50
- | Magistral Small 2506 | `mistralai/magistral-small-2506` |
51
- | Step 3.5 Flash (Agentic) | `stepfun-ai/step-3.5-flash` |
52
- | Seed OSS 36B Instruct (Agentic) | `bytedance/seed-oss-36b-instruct` |
53
- | GLM-4.7 (Tool Calling) | `thudm/glm-4.7` |
54
- | MiniMax M2.7 | `minimax/minimax-m2.7` |
55
- | Phi-4 Multimodal Instruct | `microsoft/phi-4-multimodal-instruct` |
56
- | Gemma 3N E4B IT | `google/gemma-3n-e4b-it` |
57
- | Gemma 3N E2B IT | `google/gemma-3n-e2b-it` |
58
- | Gemma 2 2B IT | `google/gemma-2-2b-it` |
59
- | Dracarys Llama 3.1 70B Instruct | `abacusai/dracarys-llama-3.1-70b-instruct` |
60
- | Nemotron Mini 4B Instruct | `nvidia/nemotron-mini-4b-instruct` |
61
- | Solar 10.7B Instruct | `upstage/solar-10.7b-instruct` |
44
+ When you select a model, the node will automatically configure the recommended `max_tokens` and `temperature` to provide the best results out of the box. You can still override these manually.
45
+
46
+ | Model ID | Default Max Tokens | Default Temperature |
47
+ |---|---|---|
48
+ | `minimaxai/minimax-m3` | 8192 | 1 |
49
+ | `nvidia/nemotron-3-ultra-550b-a55b` | 16384 | 1 |
50
+ | `stepfun-ai/step-3.7-flash` | 16384 | 1 |
51
+ | `moonshotai/kimi-k2.6` | 16384 | 1 |
52
+ | `mistralai/mistral-medium-3.5-128b` | 16384 | 0.7 |
53
+ | `mistralai/mistral-nemotron` | 4096 | 0.6 |
54
+ | `sarvamai/sarvam-m` | 16384 | 0.5 |
55
+ | `nvidia/nemotron-3-nano-30b-a3b` | 16384 | 1 |
56
+ | `stepfun-ai/step-3.5-flash` | 16384 | 1 |
57
+ | `qwen/qwen3.5-122b-a10b` | 16384 | 0.6 |
58
+ | `nvidia/nemotron-3-super-120b-a12b` | 16384 | 1 |
59
+ | `mistralai/mistral-small-4-119b-2603` | 16384 | 0.1 |
60
+ | `google/gemma-4-31b-it` | 16384 | 1 |
61
+ | `minimaxai/minimax-m2.7` | 8192 | 1 |
62
+ | `z-ai/glm-5.1` | 16384 | 1 |
63
+ | `deepseek-ai/deepseek-v4-pro` | 16384 | 1 |
64
+ | `deepseek-ai/deepseek-v4-flash` | 16384 | 1 |
62
65
 
63
66
  ### Embedding Models
64
67
 
@@ -118,16 +121,16 @@ Use this node anywhere n8n expects a **language model**.
118
121
  1. Add an **AI Agent** (or Basic LLM Chain) node to your workflow
119
122
  2. In the **Model** slot, click `+`
120
123
  3. Search for **NVIDIA NIM** and select it
121
- 4. Choose your model, set temperature and max tokens
124
+ 4. Choose your model the optimal temperature and max tokens will be populated automatically!
122
125
  5. Run your workflow
123
126
 
124
127
  **Configuration Options:**
125
128
 
126
129
  | Parameter | Type | Default | Description |
127
130
  |---|---|---|---|
128
- | Model | Dropdown | `llama-4-maverick-17b-128e-instruct` | The NIM chat model to use |
129
- | Temperature | Number (0–2) | `0.7` | Controls output randomness. Lower = more deterministic |
130
- | Max Tokens | Number (1–4096) | `1000` | Maximum tokens in the response |
131
+ | Model | Dropdown | `deepseek-ai/deepseek-v4-flash` | The NIM chat model to use |
132
+ | Temperature | Number | *Dynamic* | Controls output randomness. Automatically updates based on the model chosen. |
133
+ | Max Tokens | Number | *Dynamic* | Maximum tokens in the response. Automatically updates based on the model chosen. |
131
134
 
132
135
  ---
133
136
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@sateeshreddy/n8n-nodes-nvidia-nim",
3
- "version": "1.0.8",
3
+ "version": "1.0.9",
4
4
  "description": "n8n community node for NVIDIA NIM",
5
5
  "main": "dist/nodes/NvidiaNim/NvidiaNim.node.js",
6
6
  "scripts": {