3a:I[603186,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/37fulsfv80et3.js","/_next/static/chunks/1qibxep3kn6qx.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/1hir463fky0ew.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2tbc_4m20jg4-.js"],"PageMetadata"] 3b:I[831915,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/37fulsfv80et3.js","/_next/static/chunks/1qibxep3kn6qx.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/1hir463fky0ew.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2tbc_4m20jg4-.js"],"SearchResultsImage"] 3c:I[430295,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/37fulsfv80et3.js","/_next/static/chunks/1qibxep3kn6qx.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/1hir463fky0ew.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2tbc_4m20jg4-.js"],""] 3d:I[299632,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/37fulsfv80et3.js","/_next/static/chunks/1qibxep3kn6qx.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/1hir463fky0ew.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2tbc_4m20jg4-.js"],"default"] 3e:I[400402,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/37fulsfv80et3.js","/_next/static/chunks/1qibxep3kn6qx.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/1hir463fky0ew.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2tbc_4m20jg4-.js"],"EndpointCTA"] 3f:I[331699,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/37fulsfv80et3.js","/_next/static/chunks/1qibxep3kn6qx.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/1hir463fky0ew.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2tbc_4m20jg4-.js"],"ModelContent"] 4a:I[261442,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/37fulsfv80et3.js","/_next/static/chunks/1qibxep3kn6qx.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/1hir463fky0ew.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2tbc_4m20jg4-.js"],"default"] 4b:I[946424,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/37fulsfv80et3.js","/_next/static/chunks/1qibxep3kn6qx.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/1hir463fky0ew.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2tbc_4m20jg4-.js"],"default"] 37:["$","$L3a",null,{"hasPartnerEndpoint":false}] 40:T1552,# nemotron-parse Overview nemotron-parse is a general purpose text-extraction model, specifically designed to handle documents. Given an image, nemotron-parse is able to extract formatted-text, with bounding-boxes and the corresponding semantic class. This has downstream benefits for several tasks such as increasing the availability of training-data for Large Language Models (LLMs), improving the accuracy of retriever systems, and enhancing document understanding pipelines. This model is ready for commercial use. ## License GOVERNING TERMS: This trial service is governed by the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). Use of this model is governed by the [NVIDIA Community Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-community-models-license/).Use of the tokenizer included in this model is governed by the [CC-BY-4.0 license](https://creativecommons.org/licenses/by/4.0/). ## Deployment Geography: Global ## Use Case: nemotron-parse will be capable of comprehensive text understanding and document structure understanding. It will be used in retriever and curator solutions. Its text extraction datasets and capabilities will help with LLM and VLM training, as well as improve run-time inference accuracy of VLMs. The nemotron-parse model will perform text extraction from PDF and PPT documents. The nemotron-parse can classify the objects (title, section, caption, index, footnote, lists, tables, bibliography, image) in a given document, and provide bounding boxes with coordinates. ## Release Date: October 28, 2025 ## References * https://huggingface.co/docs/transformers/en/model_doc/mbart ## Model Architecture ### Architecture Type : Transformer-based vision-encoder-decoder model ### Network Architecture * Vision Encoder: ViT-H model (https://huggingface.co/nvidia/C-RADIO)
* Adapter Layer: 1D convolutions & norms to compress dimensionality and sequence length of the latent space (1280 tokens to 320 tokens)
* Decoder: mBart [1] 10 blocks
* Tokenizer: Use of the tokenizer included in this model is governed by the [CC-BY-4.0 license](https://creativecommons.org/licenses/by/4.0/)
* Number of Parameters: <1B
## Computational Load (For NVIDIA Models Only) **Cumulative Compute:** 1.4e+21
**Estimated Energy and Emissions for Model Training:** Energy Consumption: 6200 kWh
Carbon Emissions: 2.55
### Input * Input Type: Image, Text
* Input Type(s): Red, Green, Blue (RGB) + Prompt (String) * Input Parameters: 2D, 1D - Other Properties Related to Input: - Max Input Resolution (Width, Height): 1648, 2048 - Min Input Resolution (Width, Height): 1024, 1280 - Channel Count: 3 ### Output * Output Type: Text
* Output Format: String * Output Parameters: 1D - Other Properties Related to Output: - nemotron-parse output format is a string which encodes text content (formatted or not) as well as bounding boxes and class attributes.
Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA’s hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.
## Software Integration: Runtime Engine(s): TensorRT-LLM Supported Hardware Microarchitecture Compatibility:
NVIDIA Hopper/NVIDIA Ampere/NVIDIA Turing
Supported Operating System(s): Linux
The integration of foundation and fine-tuned models into AI systems requires additional testing using use-case-specific data to ensure safe and effective deployment. Following the V-model methodology, iterative testing and validation at both unit and system levels are essential to mitigate risks, meet technical and functional requirements, and ensure compliance with safety and ethical standards before deployment.
## Model Version: nemotron-parse: As part of this first release, we share the set of weights named overjoyed-adder. ## Training, Testing, and Evaluation Datasets: ### Training Dataset nemotron-parse is first pre-trained on our internal datasets: human, synthetic and automated. Data Modality: *Text *Image
Data Collection Method by Dataset: Hybrid: Human, Synthetic, Automated Labeling Method by Dataset: Hybrid: Human, Synthetic, Automated ### Testing and Evaluation Dataset: nemotron-parse is evaluated on multiple datasets for robustness, including public and internal dataset. Data Collection Method by Dataset: Hybrid: Human, Synthetic, Automated Labeling Method by Dataset: Hybrid: Human, Synthetic, Automated ## Inference Runtime Engine(s): TensorRT-LLM Test Hardware: NVIDIA H100 ## Ethical Considerations NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their supporting model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/). **You are responsible for ensuring that your use of NVIDIA AI Models complies with all applicable laws.**41:Ta89,## Explainability | Field | Response | | :---- | :---- | | Intended Task/Domain: | image to text | | Model Type: | Transformer-based vision-encoder-decoder model| | Intended Users: | Generative AI creators working with conversational AI models and image content. | | Output: | Text | | Describe how the model works: | Generates text by predicting the next word or token based on the context provided in the input sequence using multiple self-attention layers. | | Name the adversely impacted groups this has been tested to deliver comparable outcomes regardless of: | Not Applicable | | Technical Limitations & Mitigation: | The model demonstrates weakness to alignment-breaking attacks. Users are advised to deploy language model guardrails alongside this model to prevent potentially harmful outputs. The Model may generate answers that are inaccurate, omit key information, or include irrelevant or redundant text. | | Verified to have met prescribed NVIDIA quality standards: | Yes | | Performance Metrics: | Accuracy, Throughput, and User-side throughput | | Potential Known Risks: | The model was optimized explicitly for instruction following and as such is more susceptible to prompt injection and jailbreaking in various forms as a result of its instruction tuning. This means that the model should be paired with additional rails or system filtering to limit exposure to instructions from malicious sources \-- either directly or indirectly by retrieval (e.g. via visiting a website) \-- as they may yield outputs that can lead to harmful, system-level outcomes up to and including remote code execution in agentic systems when effective security controls including guardrails are not in place. The model was trained on data that contains toxic language and societal biases originally crawled from the internet. Therefore, the model may amplify those biases and return toxic responses especially when prompted with toxic prompts. The model may generate answers that may be inaccurate, omit key information, or include irrelevant or redundant text producing socially unacceptable or undesirable text, even if the prompt itself does not include anything explicitly offensive. | | Licensing: | GOVERNING TERMS: This trial service is governed by the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). Use of this model is governed by the [NVIDIA Community Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-community-models-license/). Use of the tokenizer included in this model is governed by the [CC-BY-4.0 license](https://creativecommons.org/licenses/by/4.0/).|42:T459,| Field | Response | | :---- | :---- | | Model Application Field(s): | Chat, Instruction Following, Chatbot Development, Code Generation, Reasoning, Customer Service | | Describe the life critical impact (if present). | Not Applicable | | Use Case Restrictions: | GOVERNING TERMS: This trial service is governed by the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). Use of this model is governed by the [NVIDIA Community Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-community-models-license/). Use of the tokenizer included in this model is governed by the [CC-BY-4.0 license](https://creativecommons.org/licenses/by/4.0/).| | Model and dataset restrictions: | The Principle of least privilege (PoLP) is applied limiting access for dataset generation and model development. Restrictions enforce dataset access during training, and dataset license constraints adhered to. | **You are responsible for ensuring that your use of NVIDIA AI Models complies with all applicable laws.**43:T15f2,{ "id": "chatcmpl-1074badc476a4030bcfeb234170b91b6", "object": "chat.completion", "created": 1761100218, "model": "nvidia/nemotron-parse", "choices": [ { "index": 0, "message": { "role": "assistant", "content": null, "refusal": null, "annotations": null, "audio": null, "function_call": null, "tool_calls": [ { "id": "chatcmpl-tool-27b642d737d94a4c8d8f159a8344d08a", "type": "function", "function": { "name": "markdown_bbox", "arguments": "[[{\"bbox\": {\"xmin\": 0.5422449275362318, \"ymin\": 0.03609420949902409, \"xmax\": 0.9328985507246378, \"ymax\": 0.05581470396877032}, \"text\": \"**CUDA C++ Programming Guide, Release 12.8**\", \"type\": \"Page-header\"}, {\"bbox\": {\"xmin\": 0.07575942028985506, \"ymin\": 0.407718932986337, \"xmax\": 0.9328985507246378, \"ymax\": 0.44196330513988286}, \"text\": \"These thread scopes are implemented as extensions to standard C++ in the CUDA Standard C++ library.\", \"type\": \"Text\"}, {\"bbox\": {\"xmin\": 0.07575942028985506, \"ymin\": 0.4754081977878985, \"xmax\": 0.513136231884058, \"ymax\": 0.508586597267404}, \"text\": \"## 5.6. Compute Capability\", \"type\": \"Section-header\"}, {\"bbox\": {\"xmin\": 0.07575942028985506, \"ymin\": 0.5305722836694861, \"xmax\": 0.9328985507246378, \"ymax\": 0.5950636304489265}, \"text\": \"The _compute capability_ of a device is represented by a version number, also sometimes called its \\\"SM version\\\". This version number identifies the features supported by the GPU hardware and is used by applications at runtime to determine which hardware features and/or instructions are available on the present GPU.\", \"type\": \"Text\"}, {\"bbox\": {\"xmin\": 0.07575942028985506, \"ymin\": 0.600260247234873, \"xmax\": 0.9328985507246378, \"ymax\": 0.6335718932986337}, \"text\": \"The compute capability comprises a major revision number _X_ and a minor revision number _Y_ and is denoted by _X.Y_.\", \"type\": \"Text\"}, {\"bbox\": {\"xmin\": 0.07575942028985506, \"ymin\": 0.6398344827586208, \"xmax\": 0.9328985507246378, \"ymax\": 0.719915679895901}, \"text\": \"Devices with the same major revision number are of the same core architecture. The major revision number is 9 for devices based on the _NVIDIA Hopper GPU_ architecture, 8 for devices based on the _NVIDIA Ampere GPU_ architecture, 7 for devices based on the _Volta_ architecture, 6 for devices based on the _Pascal_ architecture, 5 for devices based on the _Maxwell_ architecture, and 3 for devices based on the _Kepler_ architecture.\", \"type\": \"Text\"}, {\"bbox\": {\"xmin\": 0.07575942028985506, \"ymin\": 0.7251122966818477, \"xmax\": 0.9328985507246378, \"ymax\": 0.7584239427456083}, \"text\": \"The minor revision number corresponds to an incremental improvement to the core architecture, possibly including new features.\", \"type\": \"Text\"}, {\"bbox\": {\"xmin\": 0.07575942028985506, \"ymin\": 0.76375380611581, \"xmax\": 0.9328985507246378, \"ymax\": 0.7979981782693559}, \"text\": \"_Turing_ is the architecture for devices of compute capability 7.5, and is an incremental update based on the _Volta_ architecture.\", \"type\": \"Text\"}, {\"bbox\": {\"xmin\": 0.07575942028985506, \"ymin\": 0.8031947950553024, \"xmax\": 0.9328985507246378, \"ymax\": 0.836506441119063}, \"text\": \"_CUDA-Enabled GPUs_ lists of all CUDA-enabled devices along with their compute capability. _Compute Capabilities_ gives the technical specifications of each compute capability.\", \"type\": \"Text\"}, {\"bbox\": {\"xmin\": 0.07575942028985506, \"ymin\": 0.8574261548471047, \"xmax\": 0.9328985507246378, \"ymax\": 0.9229834743005856}, \"text\": \"**Note:** The compute capability version of a particular GPU should not be confused with the CUDA version (for example, CUDA 7.5, CUDA 8, CUDA 9), which is the version of the CUDA _software platform_. The CUDA platform is used by application developers to create applications that run on many generations of GPU architectures, including future GPU architectures yet to be invented. While new versions\", \"type\": \"Text\"}, {\"bbox\": {\"xmin\": 0.07575942028985506, \"ymin\": 0.956295120364346, \"xmax\": 0.9328985507246378, \"ymax\": 0.974949642160052}, \"text\": \"**5.6. Compute Capability** 19\", \"type\": \"Page-footer\"}, {\"bbox\": {\"xmin\": 0.0802376811594203, \"ymin\": 0.09951958360442419, \"xmax\": 0.9300623188405798, \"ymax\": 0.3910631099544567}, \"text\": \"\\\\begin{tabular}{cc}\\n**Thread Scope** & **Description** \\\\\\\\ cuda::thread_scope::thread_scope_thread & Only the CUDA thread which initiated asynchronous operations synchronizes. \\\\\\\\ cuda::thread_scope::thread_scope_block & All or any CUDA threads within the same thread block as the initiating thread synchronizes. \\\\\\\\ cuda::thread_scope::thread_scope_device & All or any CUDA threads in the same GPU device as the initiating thread synchronizes. \\\\\\\\ cuda::thread_scope::thread_scope_system & All or any CUDA or CPU threads in the same system as the initiating thread synchronizes. \\\\\\\\ \\\\end{tabular}\", \"type\": \"Table\"}]]" } } ], "reasoning_content": null }, "logprobs": null, "finish_reason": "stop", "stop_reason": null } ], "service_tier": null, "system_fingerprint": null, "usage": { "prompt_tokens": 5, "total_tokens": 672, "completion_tokens": 667, "prompt_tokens_details": null }, "prompt_logprobs": null, "kv_transfer_params": null } 44:T1234,{ "id": "chatcmpl-176bacf3c57740b79775f5e1ac510e98", "object": "chat.completion", "created": 1761288425, "model": "nvidia/nemotron-parse", "choices": [ { "index": 0, "message": { "role": "assistant", "content": null, "refusal": null, "annotations": null, "audio": null, "function_call": null, "tool_calls": [ { "id": "chatcmpl-tool-a35b6925ef0f4d2e878f432534304387", "type": "function", "function": { "name": "markdown_bbox", "arguments": "[[{\"bbox\": {\"xmin\": 0.0565878453038674, \"ymin\": 0.0633, \"xmax\": 0.9412497237569062, \"ymax\": 0.0797}, \"text\": \"_Appl. Sci._ **2023**, _13_, 12967 4 of 21\", \"type\": \"Page-header\"}, {\"bbox\": {\"xmin\": 0.2732861878453039, \"ymin\": 0.3055, \"xmax\": 0.9412497237569062, \"ymax\": 0.518}, \"text\": \"The adopted experimental equipment for performing VHCF tests was an ultrasonic fatigue testing machine (UFTM). The UFTM is shown in Figure 1 and was developed at Politecnico di Torino for testing components in the chosen fatigue range. The UFTM can perform tests at \\\$20\\\\pm 0.5\\\$ kHz under fully reversed tension-compression stress (_R_=-1), which significantly reduces the testing time compared to conventional testing apparatuses. To perform fatigue tests, the UFTM adopts the following devices: (i) an electric generator (Branson DCX 4 kW, not visible in Figure 1) which generates an electrical sinusoidal wave at 20 kHz; (ii) a piezoelectric transducer, responsible for converting the electrical wave into a mechanical vibration; (iii) a booster and a horn made of Ti-6Al-4V that amplify and convey the vibration to the specimen under testing; (iv) the specimen under investigation, which was designed for the UFTM resonance conditions; (v) a laser displacement sensor that measures the displacement at the specimen free end; (vi) vortex tubes to keep the temperature controlled in the range (20-24) \\\$^\\\\circ\\\$C; and (vii) a temperature sensor to observe the temperature evolution during the test execution.\", \"type\": \"Text\"}, {\"bbox\": {\"xmin\": 0.2732861878453039, \"ymin\": 0.8484, \"xmax\": 0.9412497237569062, \"ymax\": 0.932}, \"text\": \"Performing fatigue tests with the UFTM consists of the application of alternated stress in specimens that are designed to work in resonance conditions. The specimen and the vibration components are thus designed to have a resonance frequency corresponding to a longitudinal mode of vibration close to 20 kHz. Moreover, the UFTM adopts a closed-loop proportional-integrative-derivative (PID) control logic where the displacement measured\", \"type\": \"Text\"}, {\"bbox\": {\"xmin\": 0.0565878453038674, \"ymin\": 0.1375, \"xmax\": 0.9401116022099447, \"ymax\": 0.2891}, \"text\": \"\\\\begin{tabular}{cccccc}\\n\\\\multirow{2}{*}{**Quantity**} & \\\\multirow{2}{*}{**Symbol**} & \\\\multirow{2}{*}{**Units**} & \\\\multicolumn{3}{c}{**Materials**} \\\\\\\\ & & & **Ti-6Al-4V** & **Al. 7075 T6** & **SikaPower\\u00ae-1277** \\\\\\\\ Modulus of elasticity & E & MPa & 115,000 & 71,955 \\u00b1 224 & 2280 \\u00b1 533 \\\\\\\\ Poisson\\u2019s ratio & _v_ & / & 0.34 & 0.3 & 0.33 \\\\\\\\ Ultimate tensile strength & _\\u03c3uts_ & MPa & 950 & 610 \\u00b1 15 & 35.7 \\u00b1 1.4 \\\\\\\\ Density & _\\u03c1_ & g/cc & 4.395 & 2.8 & 1.1 \\\\\\\\ Loss factor & LF & / & 2.96 \\u00d7 10-4 & 3.5 \\u00d7 10-3 & 2 \\u00d7 10-2 \\\\\\\\ Viscosity & V & Pa\\u00b7s & / & / & 430 (at 20 \\u00b0C) \\\\\\\\ \\\\end{tabular}\", \"type\": \"Table\"}, {\"bbox\": {\"xmin\": 0.1543524861878453, \"ymin\": 0.5305, \"xmax\": 0.8500861878453039, \"ymax\": 0.8187}, \"text\": \"Piezoelectric transducer Vortex tube Booster Horn Temperature sensor Specimen Laser-displacement sensor\", \"type\": \"Picture\"}, {\"bbox\": {\"xmin\": 0.2732861878453039, \"ymin\": 0.1109, \"xmax\": 0.5322088397790055, \"ymax\": 0.1281}, \"text\": \"** 1.** Adopted material properties.\", \"type\": \"Caption\"}, {\"bbox\": {\"xmin\": 0.2732861878453039, \"ymin\": 0.8305, \"xmax\": 0.526632044198895, \"ymax\": 0.8461}, \"text\": \"**Figure 1.** The UFTM equipment [43].\", \"type\": \"Caption\"}]]" } } ], "reasoning_content": null }, "logprobs": null, "finish_reason": "stop", "stop_reason": null } ], "service_tier": null, "system_fingerprint": null, "usage": { "prompt_tokens": 5, "total_tokens": 881, "completion_tokens": 876, "prompt_tokens_details": null }, "prompt_logprobs": null, "kv_transfer_params": null } 45:T1d2a,<% // Catalog ejs locals replace JSON with {stringify} only (spread skips non-enumerable parse). const deepClone = (value) => { if (Array.isArray(value)) return value.map(deepClone); if (value && typeof value === "object") { const out = {}; for (const key of Object.keys(value)) out[key] = deepClone(value[key]); return out; } return value; }; const mediaConfig = {"image": {"mimeTypes": {}}, "video": {"mimeTypes": {}}, "audio": {"mimeTypes": {}, "defaultFormat": "wav"}}; const stripNulls = (value) => { if (Array.isArray(value)) return value.map(stripNulls); if (value && typeof value === "object") { const out = {}; for (const [key, item] of Object.entries(value)) { if (item === null || item === undefined) continue; out[key] = stripNulls(item); } return out; } return value; }; const payloadForSnippet = stripNulls(deepClone(request || {})); const hasStream = payloadForSnippet.stream !== undefined && payloadForSnippet.stream !== null; const pyStream = payloadForSnippet.stream ? "True" : "False"; if (hasStream) payloadForSnippet.stream = "__STREAM__"; const hasMediaKind = (kind) => Object.keys(mediaConfig[kind].mimeTypes || {}).length > 0; const isInlineDataUrl = (url, kind) => ( typeof url === "string" && new RegExp(`^data:${kind}/[^;]+;base64,`, "i").test(url) ); const mediaUrl = (part, key) => { const slot = part?.[key]; return typeof slot === "string" ? slot : slot?.url; }; const setMediaUrl = (part, key, url) => { if (typeof part[key] === "string") part[key] = url; else { if (!part[key] || typeof part[key] !== "object") part[key] = {}; part[key].url = url; } }; let imageCount = 0; let videoCount = 0; let audioCount = 0; (payloadForSnippet.messages || []).forEach((message) => { if (!Array.isArray(message?.content)) return; message.content.forEach((part) => { const imageUrl = mediaUrl(part, "image_url"); const videoUrl = mediaUrl(part, "video_url"); const audioUrl = mediaUrl(part, "audio_url"); // File helpers only for inline base64; http(s) URLs stay as-is in the payload. if (hasMediaKind("image") && part?.type === "image_url" && isInlineDataUrl(imageUrl, "image")) { setMediaUrl(part, "image_url", `__IMAGE_DATA_URL_${imageCount}__`); imageCount += 1; } else if (hasMediaKind("video") && part?.type === "video_url" && isInlineDataUrl(videoUrl, "video")) { setMediaUrl(part, "video_url", `__VIDEO_DATA_URL_${videoCount}__`); videoCount += 1; } else if (hasMediaKind("audio") && part?.type === "audio_url" && isInlineDataUrl(audioUrl, "audio")) { setMediaUrl(part, "audio_url", `__AUDIO_DATA_URL_${audioCount}__`); audioCount += 1; } else if (hasMediaKind("audio") && part?.type === "input_audio" && part.input_audio?.data) { part.input_audio.data = `__AUDIO_B64_${audioCount}__`; part.input_audio.format = part.input_audio.format || mediaConfig.audio.defaultFormat; audioCount += 1; } }); }); const pyRepr = (value, level = 0) => { if (value === null) return "None"; if (typeof value === "boolean") return value ? "True" : "False"; if (typeof value === "number") return String(value); if (typeof value === "string") return JSON.stringify(value); const pad = " ".repeat(level); const innerPad = " ".repeat(level + 2); if (Array.isArray(value)) { if (value.length === 0) return "[]"; return "[\n" + value.map((item) => `${innerPad}${pyRepr(item, level + 2)}`).join(",\n") + "\n" + pad + "]"; } if (typeof value === "object") { const entries = Object.entries(value); if (entries.length === 0) return "{}"; return "{\n" + entries.map(([key, item]) => `${innerPad}${JSON.stringify(key)}: ${pyRepr(item, level + 2)}`).join(",\n") + "\n" + pad + "}"; } return "None"; }; const replaceAll = (s, a, b) => s.split(a).join(b); let renderedPayload = pyRepr(payloadForSnippet); if (hasStream) renderedPayload = replaceAll(renderedPayload, '"__STREAM__"', "stream"); for (let i = 0; i < imageCount; i++) { renderedPayload = replaceAll(renderedPayload, `"__IMAGE_DATA_URL_${i}__"`, `image_data_urls[${i}]`); } for (let i = 0; i < videoCount; i++) { renderedPayload = replaceAll(renderedPayload, `"__VIDEO_DATA_URL_${i}__"`, `video_data_urls[${i}]`); } for (let i = 0; i < audioCount; i++) { renderedPayload = replaceAll(renderedPayload, `"__AUDIO_DATA_URL_${i}__"`, `audio_data_urls[${i}]`); renderedPayload = replaceAll(renderedPayload, `"__AUDIO_B64_${i}__"`, `audio_b64s[${i}]`); } // Either file helpers XOR inline base64 - never emit unused helpers. const usesFileHelpers = imageCount + videoCount + audioCount > 0 && [...Array(imageCount).keys()].every((i) => renderedPayload.includes(`image_data_urls[${i}]`)) && [...Array(videoCount).keys()].every((i) => renderedPayload.includes(`video_data_urls[${i}]`)) && [...Array(audioCount).keys()].every( (i) => renderedPayload.includes(`audio_data_urls[${i}]`) || renderedPayload.includes(`audio_b64s[${i}]`) ); if (!usesFileHelpers) { imageCount = 0; videoCount = 0; audioCount = 0; const restored = stripNulls(deepClone(request || {})); const restoredStream = restored.stream !== undefined && restored.stream !== null; if (restoredStream) restored.stream = "__STREAM__"; renderedPayload = pyRepr(restored); if (restoredStream) renderedPayload = replaceAll(renderedPayload, '"__STREAM__"', "stream"); } const hasMedia = usesFileHelpers; const mimePy = (mimes) => "{" + Object.entries(mimes).map(([k, v]) => `${JSON.stringify(k)}: ${JSON.stringify(v)}`).join(", ") + "}"; %> <% if (hasMedia) { %>import base64 from pathlib import Path <% } %>import requests invoke_url = "https://integrate.api.nvidia.com/v1/chat/completions" stream = <%- pyStream %> <% if (hasMedia) { %> def media_data_url(kind, index, mime_types): for suffix, mime in mime_types.items(): path = Path(f"{kind}_{index}{suffix}") if path.exists(): return f"data:{mime};base64,{base64.b64encode(path.read_bytes()).decode()}" raise FileNotFoundError(f"Expected {kind}_{index} with suffix in {list(mime_types)}") <% if (imageCount > 0) { %> image_data_urls = [media_data_url("image", i, <%- mimePy(mediaConfig.image.mimeTypes) %>) for i in <%- imageCount === 1 ? "[1]" : ("range(1, " + (imageCount + 1) + ")") %>] <% } %><% if (videoCount > 0) { %> video_data_urls = [media_data_url("video", i, <%- mimePy(mediaConfig.video.mimeTypes) %>) for i in <%- videoCount === 1 ? "[1]" : ("range(1, " + (videoCount + 1) + ")") %>] <% } %><% if (audioCount > 0) { %> audio_data_urls = [media_data_url("audio", i, <%- mimePy(mediaConfig.audio.mimeTypes) %>) for i in <%- audioCount === 1 ? "[1]" : ("range(1, " + (audioCount + 1) + ")") %>] audio_b64s = [url.split(",", 1)[1] for url in audio_data_urls] <% } %><% } %> headers = { "Authorization": "Bearer $NVIDIA_API_KEY", "Accept": "text/event-stream" if stream else "application/json", } payload = <%- renderedPayload %> response = requests.post(invoke_url, headers=headers, json=payload, stream=stream) if stream: for line in response.iter_lines(): if line: print(line.decode("utf-8")) else: print(response.json()) 46:T1647,<% const deepClone = (value) => { if (Array.isArray(value)) return value.map(deepClone); if (value && typeof value === "object") { const out = {}; for (const key of Object.keys(value)) out[key] = deepClone(value[key]); return out; } return value; }; const mediaConfig = {"image": {"mimeTypes": {}}, "video": {"mimeTypes": {}}, "audio": {"mimeTypes": {}, "defaultFormat": "wav"}}; const payloadForSnippet = deepClone(request || {}); const messagesForSnippet = deepClone(payloadForSnippet.messages || []); const hasMediaKind = (kind) => Object.keys(mediaConfig[kind].mimeTypes || {}).length > 0; const isInlineDataUrl = (url, kind) => ( typeof url === "string" && new RegExp(`^data:${kind}/[^;]+;base64,`, "i").test(url) ); const mediaUrl = (part, key) => { const slot = part?.[key]; return typeof slot === "string" ? slot : slot?.url; }; const setMediaUrl = (part, key, url) => { if (typeof part[key] === "string") part[key] = url; else { if (!part[key] || typeof part[key] !== "object") part[key] = {}; part[key].url = url; } }; let imageCount = 0; let hasUnsupportedMedia = false; messagesForSnippet.forEach((message) => { if (!Array.isArray(message?.content)) return; message.content.forEach((part) => { const imageUrl = mediaUrl(part, "image_url"); if (hasMediaKind("image") && part?.type === "image_url" && isInlineDataUrl(imageUrl, "image")) { setMediaUrl(part, "image_url", `__IMAGE_DATA_URL_${imageCount}__`); imageCount += 1; } else if (part?.type === "video_url" && isInlineDataUrl(mediaUrl(part, "video_url"), "video")) { // LangChain cannot ship local file helpers for video; reject inline only. hasUnsupportedMedia = true; setMediaUrl(part, "video_url", "__UNSUPPORTED_MEDIA_DATA__"); } else if (part?.type === "audio_url" && isInlineDataUrl(mediaUrl(part, "audio_url"), "audio")) { hasUnsupportedMedia = true; setMediaUrl(part, "audio_url", "__UNSUPPORTED_MEDIA_DATA__"); } else if (part?.type === "input_audio" && part.input_audio?.data) { hasUnsupportedMedia = true; part.input_audio.data = "__UNSUPPORTED_MEDIA_DATA__"; } }); }); const pyRepr = (value, level = 0) => { if (value === null) return "None"; if (typeof value === "boolean") return value ? "True" : "False"; if (typeof value === "number") return String(value); if (typeof value === "string") return JSON.stringify(value); const pad = " ".repeat(level); const innerPad = " ".repeat(level + 2); if (Array.isArray(value)) { if (value.length === 0) return "[]"; return "[\n" + value.map((item) => `${innerPad}${pyRepr(item, level + 2)},`).join("\n") + "\n" + pad + "]"; } if (typeof value === "object") { const entries = Object.entries(value); if (entries.length === 0) return "{}"; return "{\n" + entries.map(([key, item]) => `${innerPad}${JSON.stringify(key)}: ${pyRepr(item, level + 2)},`).join("\n") + "\n" + pad + "}"; } return "None"; }; const replaceAll = (s, a, b) => s.split(a).join(b); let renderedMessages = pyRepr(messagesForSnippet); for (let i = 0; i < imageCount; i++) { renderedMessages = replaceAll(renderedMessages, `"__IMAGE_DATA_URL_${i}__"`, `image_data_urls[${i}]`); } // Either file helpers XOR inline base64 - never emit unused helpers. const usesFileHelpers = imageCount > 0 && [...Array(imageCount).keys()].every((i) => renderedMessages.includes(`image_data_urls[${i}]`)); if (!usesFileHelpers) { imageCount = 0; renderedMessages = pyRepr(deepClone((request || {}).messages || [])); } %> from langchain_nvidia_ai_endpoints import ChatNVIDIA <% if (imageCount > 0) { %>from pathlib import Path import base64 <% } %> client = ChatNVIDIA( model="<%- request.model %>", api_key="$NVIDIA_API_KEY", temperature=<%- request.temperature %>, top_p=<%- request.top_p %>, max_completion_tokens=<%- request.max_tokens %>, ) <% if (imageCount > 0) { %> def find_image_path(index): image_mime_types = <%- pyRepr(mediaConfig.image.mimeTypes) %> for suffix in image_mime_types: path = Path(f"image_{index}{suffix}") if path.exists(): return path expected = "/".join(f".{suffix.lstrip('.')}" for suffix in image_mime_types) raise FileNotFoundError(f"Expected image_{index}{expected}") def read_image_data_url(path): image_mime_types = <%- pyRepr(mediaConfig.image.mimeTypes) %> with open(path, "rb") as f: image_b64 = base64.b64encode(f.read()).decode() return f"data:{image_mime_types[path.suffix.lower()]};base64,{image_b64}" image_data_urls = [read_image_data_url(find_image_path(i)) for i in range(1, <%- imageCount + 1 %>)] <% } %><% if (hasUnsupportedMedia) { %> raise ValueError("LangChain snippet currently supports text and image input. Use Python, Node.js, or Shell for video or audio input.") <% } %> lc_messages = <%- renderedMessages %> <% if (request.stream) { %> for chunk in client.stream(lc_messages<%= request.chat_template_kwargs ? ', chat_template_kwargs=' + pyRepr(request.chat_template_kwargs) : '' %>): if chunk.additional_kwargs and "reasoning_content" in chunk.additional_kwargs: print(chunk.additional_kwargs["reasoning_content"], end="") print(chunk.content, end="") <% } else { %> response = client.invoke(lc_messages<%= request.chat_template_kwargs ? ', chat_template_kwargs=' + pyRepr(request.chat_template_kwargs) : '' %>) if response.additional_kwargs and "reasoning_content" in response.additional_kwargs: print(response.additional_kwargs["reasoning_content"]) print(response.content) <% } %> 47:T1a86,<% const deepClone = (value) => { if (Array.isArray(value)) return value.map(deepClone); if (value && typeof value === "object") { const out = {}; for (const key of Object.keys(value)) out[key] = deepClone(value[key]); return out; } return value; }; const mediaConfig = {"image": {"mimeTypes": {}}, "video": {"mimeTypes": {}}, "audio": {"mimeTypes": {}, "defaultFormat": "wav"}}; const payloadForSnippet = deepClone(request || {}); const hasStream = payloadForSnippet.stream !== undefined && payloadForSnippet.stream !== null; if (hasStream) payloadForSnippet.stream = "__STREAM__"; const hasMediaKind = (kind) => Object.keys(mediaConfig[kind].mimeTypes || {}).length > 0; const isInlineDataUrl = (url, kind) => ( typeof url === "string" && new RegExp(`^data:${kind}/[^;]+;base64,`, "i").test(url) ); let imageCount = 0; let videoCount = 0; let audioCount = 0; (payloadForSnippet.messages || []).forEach((message) => { if (!Array.isArray(message?.content)) return; message.content.forEach((part) => { if (hasMediaKind("image") && part?.type === "image_url" && isInlineDataUrl(part.image_url?.url, "image")) { part.image_url.url = `__IMAGE_DATA_URL_${imageCount}__`; imageCount += 1; } else if (hasMediaKind("video") && part?.type === "video_url" && isInlineDataUrl(part.video_url?.url, "video")) { part.video_url.url = `__VIDEO_DATA_URL_${videoCount}__`; videoCount += 1; } else if (hasMediaKind("audio") && part?.type === "audio_url" && isInlineDataUrl(part.audio_url?.url, "audio")) { part.audio_url.url = `__AUDIO_DATA_URL_${audioCount}__`; audioCount += 1; } else if (hasMediaKind("audio") && part?.type === "input_audio" && part.input_audio?.data) { part.input_audio.data = `__AUDIO_B64_${audioCount}__`; part.input_audio.format = part.input_audio.format || mediaConfig.audio.defaultFormat; audioCount += 1; } }); }); const replaceAll = (s, a, b) => s.split(a).join(b); let renderedPayload = JSON.stringify(payloadForSnippet, null, 2); if (hasStream) renderedPayload = replaceAll(renderedPayload, '"__STREAM__"', "stream"); for (let i = 0; i < imageCount; i++) { renderedPayload = replaceAll(renderedPayload, `"__IMAGE_DATA_URL_${i}__"`, `imageDataUrls[${i}]`); } for (let i = 0; i < videoCount; i++) { renderedPayload = replaceAll(renderedPayload, `"__VIDEO_DATA_URL_${i}__"`, `videoDataUrls[${i}]`); } for (let i = 0; i < audioCount; i++) { renderedPayload = replaceAll(renderedPayload, `"__AUDIO_DATA_URL_${i}__"`, `audioDataUrls[${i}]`); renderedPayload = replaceAll(renderedPayload, `"__AUDIO_B64_${i}__"`, `audioB64s[${i}]`); } // Either file helpers XOR inline base64 - never emit unused helpers. const usesFileHelpers = imageCount + videoCount + audioCount > 0 && [...Array(imageCount).keys()].every((i) => renderedPayload.includes(`imageDataUrls[${i}]`)) && [...Array(videoCount).keys()].every((i) => renderedPayload.includes(`videoDataUrls[${i}]`)) && [...Array(audioCount).keys()].every( (i) => renderedPayload.includes(`audioDataUrls[${i}]`) || renderedPayload.includes(`audioB64s[${i}]`) ); if (!usesFileHelpers) { imageCount = 0; videoCount = 0; audioCount = 0; const restored = deepClone(request || {}); const restoredStream = restored.stream !== undefined && restored.stream !== null; if (restoredStream) restored.stream = "__STREAM__"; renderedPayload = JSON.stringify(restored, null, 2); if (restoredStream) renderedPayload = replaceAll(renderedPayload, '"__STREAM__"', "stream"); } const hasMedia = usesFileHelpers; %> import axios from 'axios'; <% if (hasMedia) { %>import { existsSync } from 'node:fs'; import { readFile } from 'node:fs/promises'; import { extname } from 'node:path'; <% } %> const invokeUrl = "https://integrate.api.nvidia.com/v1/chat/completions"; const stream = <%- request.stream %>; const headers = { "Authorization": "Bearer $NVIDIA_API_KEY", "Accept": stream ? "text/event-stream" : "application/json" }; <% if (hasMedia) { %> function findMediaPath(kind, index, mimeTypes) { for (const suffix of Object.keys(mimeTypes)) { const path = `${kind}_${index}${suffix}`; if (existsSync(path)) { return path; } } const expected = Object.keys(mimeTypes).join("/"); throw new Error(`Expected ${kind}_${index}${expected}`); } async function readMediaB64(path) { return Buffer.from(await readFile(path)).toString('base64'); } function mediaDataUrl(path, mediaB64, mimeTypes) { return `data:${mimeTypes[extname(path).toLowerCase()]};base64,${mediaB64}`; } <% } %> async function main() { <% if (imageCount > 0) { %> const imageMimeTypes = <%- JSON.stringify(mediaConfig.image.mimeTypes, null, 2) %>; const imagePaths = [<% for (let i = 1; i <= imageCount; i++) { %>findMediaPath("image", <%- i %>, imageMimeTypes)<%- i < imageCount ? ", " : "" %><% } %>]; const imageB64s = await Promise.all(imagePaths.map(readMediaB64)); const imageDataUrls = imagePaths.map((path, index) => mediaDataUrl(path, imageB64s[index], imageMimeTypes)); <% } %><% if (videoCount > 0) { %> const videoMimeTypes = <%- JSON.stringify(mediaConfig.video.mimeTypes, null, 2) %>; const videoPaths = [<% for (let i = 1; i <= videoCount; i++) { %>findMediaPath("video", <%- i %>, videoMimeTypes)<%- i < videoCount ? ", " : "" %><% } %>]; const videoB64s = await Promise.all(videoPaths.map(readMediaB64)); const videoDataUrls = videoPaths.map((path, index) => mediaDataUrl(path, videoB64s[index], videoMimeTypes)); <% } %><% if (audioCount > 0) { %> const audioMimeTypes = <%- JSON.stringify(mediaConfig.audio.mimeTypes, null, 2) %>; const audioPaths = [<% for (let i = 1; i <= audioCount; i++) { %>findMediaPath("audio", <%- i %>, audioMimeTypes)<%- i < audioCount ? ", " : "" %><% } %>]; const audioB64s = await Promise.all(audioPaths.map(readMediaB64)); const audioDataUrls = audioPaths.map((path, index) => mediaDataUrl(path, audioB64s[index], audioMimeTypes)); <% } %> const payload = <%- renderedPayload %>; const response = await axios.post(invokeUrl, payload, { headers: headers, responseType: stream ? 'stream' : 'json' }); if (stream) { response.data.on('data', (chunk) => { console.log(chunk.toString()); }); } else { console.log(JSON.stringify(response.data)); } } main().catch(error => { if (error.response) { console.error(`HTTP ${error.response.status}`); if (error.response.data?.on) { error.response.data.on('data', (chunk) => console.error(chunk.toString())); } else { console.error(error.response.data); } } else { console.error(error); } }); 48:T153d,<% const deepClone = (value) => { if (Array.isArray(value)) return value.map(deepClone); if (value && typeof value === "object") { const out = {}; for (const key of Object.keys(value)) out[key] = deepClone(value[key]); return out; } return value; }; const mediaConfig = {"image": {"mimeTypes": {}}, "video": {"mimeTypes": {}}, "audio": {"mimeTypes": {}, "defaultFormat": "wav"}}; const payloadForSnippet = deepClone(request || {}); const hasMediaKind = (kind) => Object.keys(mediaConfig[kind].mimeTypes || {}).length > 0; const isInlineDataUrl = (url, kind) => ( typeof url === "string" && new RegExp(`^data:${kind}/[^;]+;base64,`, "i").test(url) ); let imageCount = 0; let videoCount = 0; let audioCount = 0; (payloadForSnippet.messages || []).forEach((message) => { if (!Array.isArray(message?.content)) return; message.content.forEach((part) => { if (hasMediaKind("image") && part?.type === "image_url" && isInlineDataUrl(part.image_url?.url, "image")) { part.image_url.url = `__IMAGE_DATA_URL_${imageCount}__`; imageCount += 1; } else if (hasMediaKind("video") && part?.type === "video_url" && isInlineDataUrl(part.video_url?.url, "video")) { part.video_url.url = `__VIDEO_DATA_URL_${videoCount}__`; videoCount += 1; } else if (hasMediaKind("audio") && part?.type === "audio_url" && isInlineDataUrl(part.audio_url?.url, "audio")) { part.audio_url.url = `__AUDIO_DATA_URL_${audioCount}__`; audioCount += 1; } else if (hasMediaKind("audio") && part?.type === "input_audio" && part.input_audio?.data) { part.input_audio.data = `__AUDIO_B64_${audioCount}__`; part.input_audio.format = part.input_audio.format || mediaConfig.audio.defaultFormat; audioCount += 1; } }); }); const replaceAll = (s, a, b) => s.split(a).join(b); let renderedPayload = JSON.stringify(payloadForSnippet, null, 2); for (let i = 0; i < imageCount; i++) { renderedPayload = replaceAll(renderedPayload, `"__IMAGE_DATA_URL_${i}__"`, `"${"${"}image_${i + 1}_data_url}"`); } for (let i = 0; i < videoCount; i++) { renderedPayload = replaceAll(renderedPayload, `"__VIDEO_DATA_URL_${i}__"`, `"${"${"}video_${i + 1}_data_url}"`); } for (let i = 0; i < audioCount; i++) { renderedPayload = replaceAll(renderedPayload, `"__AUDIO_DATA_URL_${i}__"`, `"${"${"}audio_${i + 1}_data_url}"`); renderedPayload = replaceAll(renderedPayload, `"__AUDIO_B64_${i}__"`, `"${"${"}audio_${i + 1}_b64}"`); } // Either file helpers XOR inline base64 - never emit unused helpers. const usesFileHelpers = imageCount + videoCount + audioCount > 0 && [...Array(imageCount).keys()].every((i) => renderedPayload.includes(`image_${i + 1}_data_url`)) && [...Array(videoCount).keys()].every((i) => renderedPayload.includes(`video_${i + 1}_data_url`)) && [...Array(audioCount).keys()].every( (i) => renderedPayload.includes(`audio_${i + 1}_data_url`) || renderedPayload.includes(`audio_${i + 1}_b64`) ); if (!usesFileHelpers) { imageCount = 0; videoCount = 0; audioCount = 0; renderedPayload = JSON.stringify(deepClone(request || {}), null, 2); } const hasMedia = usesFileHelpers; %> stream=<%- request.stream %> if [ "$stream" = true ]; then accept_header='Accept: text/event-stream' else accept_header='Accept: application/json' fi <% if (hasMedia) { %> mime_type_for() { case "$1" in <% for (const [suffix, mimeType] of Object.entries({...mediaConfig.image.mimeTypes, ...mediaConfig.video.mimeTypes, ...mediaConfig.audio.mimeTypes})) { %> *<%- suffix %>) echo "<%- mimeType %>" ;; <% } %> *) echo "Unsupported media file: $1" >&2; return 1 ;; esac } find_media_path() { local kind="$1" local index="$2" shift 2 local ext path for ext in "$@"; do path="${kind}_${index}.${ext}" if [ -f "$path" ]; then echo "$path" return 0 fi done echo "Expected ${kind}_${index}.$*" >&2 return 1 } media_b64() { base64 < "$1" | tr -d '\n' } media_data_url() { local path="$1" local mime_type media_base64 mime_type=$(mime_type_for "$path") || return 1 media_base64=$(media_b64 "$path") || return 1 printf 'data:%s;base64,%s' "$mime_type" "$media_base64" } <% for (let i = 1; i <= imageCount; i++) { %> image_<%- i %>_path=$(find_media_path image <%- i %><% for (const suffix of Object.keys(mediaConfig.image.mimeTypes)) { %> <%- suffix.slice(1) %><% } %>) image_<%- i %>_data_url=$(media_data_url "$image_<%- i %>_path") <% } %><% for (let i = 1; i <= videoCount; i++) { %> video_<%- i %>_path=$(find_media_path video <%- i %><% for (const suffix of Object.keys(mediaConfig.video.mimeTypes)) { %> <%- suffix.slice(1) %><% } %>) video_<%- i %>_data_url=$(media_data_url "$video_<%- i %>_path") <% } %><% for (let i = 1; i <= audioCount; i++) { %> audio_<%- i %>_path=$(find_media_path audio <%- i %><% for (const suffix of Object.keys(mediaConfig.audio.mimeTypes)) { %> <%- suffix.slice(1) %><% } %>) audio_<%- i %>_b64=$(media_b64 "$audio_<%- i %>_path") audio_<%- i %>_data_url=$(media_data_url "$audio_<%- i %>_path") <% } %><% } %> cat > payload.json < JSON curl https://integrate.api.nvidia.com/v1/chat/completions \ -H "Authorization: Bearer $NVIDIA_API_KEY" \ -H "Content-Type: application/json" \ -H "$accept_header" \ -d @payload.json49:T509,## Step 1. Generate API Key ::generate-api-key ## Step 2. Pull and Run the NIM ```bash $ docker login nvcr.io Username: $oauthtoken Password: ``` Pull and run the NVIDIA NIM with the command below. This will download the optimized model for your infrastructure. ```bash export NGC_API_KEY= export LOCAL_NIM_CACHE=~/.cache/nim mkdir -p "$LOCAL_NIM_CACHE" docker run -it --rm \ --gpus all \ --shm-size=16GB \ -e NGC_API_KEY \ -v "$LOCAL_NIM_CACHE:/opt/nim/.cache" \ -u $(id -u) \ -p 8000:8000 \ nvcr.io/nim/nvidia/nemotron-parse:latest ``` ## Step 3. Test the NIM You can now make a local API call using this curl command: ```bash curl -X 'POST' \ 'http://0.0.0.0:8000/v1/chat/completions' \ -H 'accept: application/json' \ -H 'Content-Type: application/json' \ -d '{ "model": "nvidia/nemotron-parse", "messages": [{"role":"user", "content":[ { "type": "image_url", "image_url": {"url": "https://assets.ngc.nvidia.com/products/api-catalog/nemotron-parse/example_2.jpg"} } ]}], "max_tokens": 256 }' ``` For more details on getting started with this NIM, visit the [NVIDIA NIM Docs](https://docs.nvidia.com/nim/vision-language-models/latest/getting-started.html).38:[["$","div",".3",{"className":"relative","children":[["$","div",null,{"className":"relative flex min-h-[194px] w-full flex-col overflow-hidden p-md sm:p-ml bg-manitoulinLightBlack","children":[["$","$L3b",null,{"alt":"","className":"object-cover object-center !left-1/2 z-10 !w-1/2 brightness-20 lg:brightness-75","fill":true,"priority":true,"src":"https://assets.ngc.nvidia.com/products/api-catalog/images/nemotron-parse.jpg","style":{"maskImage":"linear-gradient(to left, rgba(0,0,0,1), rgba(0,0,0,0))"}}],["$","div",null,{"className":"z-30 mx-auto flex w-full max-w-screen-xl min-w-0 flex-1 flex-col items-start justify-between gap-md lg:flex-row lg:gap-ml","children":["$","section",null,{"aria-describedby":"resource-description","aria-labelledby":"resource-name","className":"flex w-full min-w-0 flex-col lg:flex-1","children":["$","div",null,{"className":"flex flex-col gap-1.5 whitespace-pre-wrap","children":[["$","$L3c",null,{"className":"w-fit text-ml text-n300 lowercase hover:text-n050","href":"/nvidia","children":"NVIDIA"}],["$","div",null,{"className":"flex flex-col items-start gap-3 lg:flex-row lg:items-center","children":[["$","h1",null,{"className":"max-w-full text-lg leading-heading font-medium break-words text-primary","data-testid":"resource-name","id":"resource-name","children":"nemotron-parse"}],[["$","span","AVAILABLE",{"className":"nv-badge nv-badge--kind-solid h-[18px] py-0","data-testid":"nv-badge","ref":"$undefined","children":["$undefined","Downloadable"]}]],"$undefined"]}],["$","p",null,{"className":"max-w-[85ch] text-ms text-primary","id":"resource-description","children":"Cutting-edge vision-language model exceling in retrieving text and metadata from images."}],["$","div",null,{"className":"flex w-full flex-col items-start gap-md lg:flex-row lg:items-end lg:justify-between","children":[["$","div",null,{"className":"flex w-full min-w-0 flex-wrap gap-sm lg:flex-1","children":["$","$L3d",null,{"artifactType":"ENDPOINT","density":"standard","labels":["document parsing","nimType:endpoint:nim_type_run_anywhere","supported language - english","text and table extraction"],"searchRoutePath":"/models"}]}],["$","div",null,{"className":"z-30 flex w-full flex-row justify-start gap-ms sm:justify-end lg:w-auto lg:shrink-0","children":["$undefined",["$","$L3e",null,{"cta":{"text":"Apply to Self-Host","url":"https://www.nvidia.com/en-us/ai/nim-notifyme/","nim_available_override_url":"https://catalog.ngc.nvidia.com/orgs/nim/teams/nvidia/containers/nemotron-parse"},"isNIMAccessRestricted":"$undefined","isNIMAvailable":true}]]}]]}]]}]}]}],["$","div",null,{"className":"pointer-events-none absolute right-0 bottom-0 left-0 z-20 h-30 bg-gradient-to-t to-transparent from-manitoulinLightBlack via-manitoulinLightBlack/70"}]]}],["$","div",null,{"className":"px-4 mx-auto flex max-w-screen-xl flex-col pt-0 lg:px-0","data-body-background":"light-black","children":["$","section",null,{"className":"flex w-full flex-col justify-between rounded-4 border-manitoulinBorderColor bg-manitoulinDarkBlack sm:rounded-6 lg:rounded-8 p-ms lg:p-lg","children":["$","$L3f",null,{"artifact":{"artifactType":"ENDPOINT","name":"nemotron-parse","displayName":"nemotron-parse","publisher":"nvidia","shortDescription":"Cutting-edge vision-language model exceling in retrieving text and metadata from images.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/nemotron-parse.jpg","labels":"$38:0:props:children:0:props:children:1:props:children:props:children:props:children:3:props:children:0:props:children:props:labels","attributes":[{"key":"AVAILABLE","value":"true"},{"key":"PREVIEW","value":"false"},{"key":"last_month_api_invocation_count","value":"1249231"},{"key":"last_month_download_count","value":"0"}],"updatedDate":"2025-10-28T18:51:38.495Z","bias":"## Bias\n| Field | Response |\n| :---- | :---- |\n| Participation considerations from adversely impacted groups [protected classes](https://calcivilrights.ca.gov/disputeresolution/protected-characteristics/) in model design and testing: | None |\n| Measures taken to mitigate against unwanted bias: | Not applicable |\n| Bias Metric (If Measured): | [None |","canGuestDownload":true,"createdDate":"2025-10-28T18:51:38.495Z","description":"$40","explainability":"$41","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","privacy":"Field | Response |\n| :---- | :---- |\n| Generatable or reverse engineerable personal data? | No |\n| Personal data used to create this model? | No |\n| Was consent obtained for any personal data used? | Not Applicable |\n| How often is the dataset reviewed? | Before Release |\n| Is there provenance for all datasets used in training? | Yes |\n| Does data labeling (annotation, metadata) comply with privacy laws? | Yes |\n| Is data compliant with data subject requests for data correction or removal, if such a request was made? | No, not possible with externally-sourced data. |\n| Applicable Privacy Policy | [NVIDIA Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/) |","safetyAndSecurity":"$42"},"endpointName":"nemotron-parse","endpointSpec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for nvidia/nemotron-parse","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/nvidia-nemotron-parse for more details.","version":"1.0.0","termsOfService":"https://nvidia.com/legal/terms-of-use","contact":{"name":"NVIDIA Support","url":"https://help.nvidia.com/"},"license":{"name":"NVIDIA Software and Model Evaluation License Agreement","url":"https://developer.download.nvidia.com/licenses/NVIDIA_Software_and_Model_Evaluation_License_Agreement.pdf"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1/"}],"tags":[{"name":"Multimodal API","description":"This API performs inference using document content extraction models"}],"paths":{"/chat/completions":{"post":{"tags":["Multimodal API"],"summary":"Request response from the model","description":"Invokes inference using the model chat parameters.","operationId":"invokeFunction","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/NIMLLMChatCompletionRequest"}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionResponse"}},"text/event-stream":{"schema":{"$ref":"#/components/schemas/ChatCompletionStreamResponse"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid","maxLength":36}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string","format":"^[a-zA-Z-]{1,64}$","maxLength":64}}}},"422":{"description":"Validation failed, provided entity could not be processed.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}},"x-nvai-meta":{"name":"Create chat completion","returns":"Returns a [chat completion](/docs/api-reference/chat/object) object.\n","path":"create","examples":[{"name":"document1","input":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/nemoretriever-parse/example_1.jpg","task_prompt":"markdown_bbox"},"requestJson":"{\n \"model\": \"nvidia/nemotron-parse\",\n \"tools\": [{\"type\": \"function\", \"function\": {\"name\": \"<%- input.task_prompt %>\"}}],\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": [{\"type\": \"image_url\", \"image_url\": {\"url\": \"<%- input.image %>\"}}]\n }\n ]\n}\n","responseJson":"$43"},{"name":"document2","input":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/nemotron-parse/example_2.jpg","task_prompt":"markdown_bbox"},"requestJson":"{\n \"model\": \"nvidia/nemotron-parse\",\n \"tools\": [{\"type\": \"function\", \"function\": {\"name\": \"<%- input.task_prompt %>\"}}],\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": [{\"type\": \"image_url\", \"image_url\": {\"url\": \"<%- input.image %>\"}}]\n }\n ]\n}\n","responseJson":"$44"}],"templates":[{"title":"Default","response":"{\n \"id\": \"...\",\n \"object\": \"chat.completion\",\n \"created\": ...,\n \"model\": \"nvidia/nemotron-parse\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"...\"\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\",\n \"stop_reason\": null\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 5,\n \"total_tokens\": 35,\n \"completion_tokens\": 30\n },\n \"prompt_logprobs\": null\n}\n","requestEjs":{"python":"$45","langChain":"$46","node.js":"$47","curl":"$48"}}]}}},"/status/{requestId}":{"get":{"tags":["Multimodal API"],"summary":"Gets the result of an earlier function invocation request that returned a status of 202.","operationId":"getFunctionInvocationResult","parameters":[{"name":"requestId","in":"path","description":"requestId to poll results","required":true,"schema":{"type":"string","format":"uuid","maxLength":36}}],"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionResponse"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid","maxLength":36}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string","format":"^[a-zA-Z-]{1,64}$","maxLength":64}}}},"422":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"ChatCompletionResponse":{"properties":{"id":{"type":"string","title":"Id"},"object":{"type":"string","enum":["chat.completion"],"const":"chat.completion","title":"Object","default":"chat.completion"},"created":{"type":"integer","title":"Created"},"model":{"type":"string","title":"Model"},"choices":{"items":{"$ref":"#/components/schemas/ChatCompletionResponseChoice"},"type":"array","title":"Choices"},"usage":{"$ref":"#/components/schemas/UsageInfo"}},"additionalProperties":false,"type":"object","required":["model","choices","usage"],"title":"ChatCompletionResponse"},"ChatCompletionResponseChoice":{"properties":{"index":{"type":"integer","title":"Index"},"message":{"$ref":"#/components/schemas/ChatMessage"},"finish_reason":{"anyOf":[{"type":"string","enum":["stop","length"]},{"type":"null"}],"title":"Finish Reason"},"stop_reason":{"anyOf":[{"type":"integer"},{"type":"string"},{"type":"null"}],"title":"Stop Reason"}},"additionalProperties":false,"type":"object","required":["index","message"],"title":"ChatCompletionResponseChoice"},"ChatCompletionResponseStreamChoice":{"properties":{"index":{"type":"integer","title":"Index"},"delta":{"$ref":"#/components/schemas/DeltaMessage"},"finish_reason":{"anyOf":[{"type":"string","enum":["stop","length"]},{"type":"null"}],"title":"Finish Reason"},"stop_reason":{"anyOf":[{"type":"integer"},{"type":"string"},{"type":"null"}],"title":"Stop Reason"}},"additionalProperties":false,"type":"object","required":["index","delta"],"title":"ChatCompletionResponseStreamChoice"},"ChatCompletionStreamResponse":{"properties":{"id":{"type":"string","title":"Id"},"object":{"type":"string","enum":["chat.completion.chunk"],"const":"chat.completion.chunk","title":"Object","default":"chat.completion.chunk"},"created":{"type":"integer","title":"Created"},"model":{"type":"string","title":"Model"},"choices":{"items":{"$ref":"#/components/schemas/ChatCompletionResponseStreamChoice"},"type":"array","title":"Choices"},"usage":{"anyOf":[{"$ref":"#/components/schemas/UsageInfo"},{"type":"null"}]}},"additionalProperties":false,"type":"object","required":["model","choices"],"title":"ChatCompletionStreamResponse"},"ChatMessage":{"properties":{"role":{"type":"string","title":"Role"},"content":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Content"}},"additionalProperties":false,"type":"object","required":["role"],"title":"ChatMessage"},"DeltaMessage":{"properties":{"role":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Role"},"content":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Content"}},"additionalProperties":false,"type":"object","title":"DeltaMessage"},"ErrorResponse":{"properties":{"object":{"type":"string","title":"Object","default":"error"},"message":{"type":"string","title":"Message"},"type":{"type":"string","title":"Type"},"param":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Param"},"code":{"type":"integer","title":"Code"}},"additionalProperties":false,"type":"object","required":["message","type","code"],"title":"ErrorResponse"},"HTTPValidationError":{"properties":{"detail":{"items":{"$ref":"#/components/schemas/ValidationError"},"type":"array","title":"Detail"}},"type":"object","title":"HTTPValidationError"},"ImageURL":{"properties":{"url":{"type":"string","title":"Url"}},"type":"object","required":["url"],"title":"ImageURL"},"NIMLLMChatCompletionMessage":{"properties":{"role":{"allOf":[{"$ref":"#/components/schemas/Role"}],"description":"The role of the message's author."},"content":{"anyOf":[{"type":"string"},{"items":{"anyOf":[{"$ref":"#/components/schemas/NIMVLMChatCompletionContentPartImage"},{"$ref":"#/components/schemas/NIMVLMChatCompletionContentPartText"}]},"type":"array"}],"title":"Content","description":"The contents of the message.\n
To pass media (only with role=`user`):\n
- Use content parts. Text is passed with `type`=`text`.\n
- Images are passed with `type`=`image_url`; set `image_url.url` to an image URL or a base64 data URI like `data:image/{format};base64,{base64encodedimage}`.\n
For `system` and `assistant` roles, the object list format is not supported.\n"}},"type":"object","required":["role","content"],"title":"NIMLLMChatCompletionMessage"},"NIMLLMChatCompletionRequest":{"properties":{"messages":{"items":{"$ref":"#/components/schemas/NIMLLMChatCompletionMessage"},"type":"array","minItems":1,"title":"Messages","description":"A list of messages comprising the conversation so far."},"model":{"type":"string","title":"Model","description":"The model to use.","default":"nvidia/nemotron-parse"},"frequency_penalty":{"anyOf":[{"type":"number","maximum":2,"minimum":-2},{"type":"null"}],"title":"Frequency Penalty","description":"Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.","default":0},"max_tokens":{"anyOf":[{"type":"integer","maximum":8192,"minimum":1},{"type":"null"}],"title":"Max Tokens","description":"The maximum number of tokens that can be generated.","default":3500},"presence_penalty":{"anyOf":[{"type":"number","maximum":2,"minimum":-2},{"type":"null"}],"title":"Presence Penalty","description":"Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.","default":0},"seed":{"anyOf":[{"type":"integer","maximum":9223372036854776000,"minimum":-9223372036854776000},{"type":"null"}],"title":"Seed","description":"Changing the seed will produce a different response with similar characteristics. Fixing the seed will reproduce the same results if all other parameters are also kept constant."},"stop":{"anyOf":[{"type":"string"},{"items":{"type":"string"},"type":"array"},{"type":"null"}],"title":"Stop","description":"Sequences where the API will stop generating further tokens."},"stream":{"anyOf":[{"type":"boolean"},{"type":"null"}],"title":"Stream","description":"If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]`","default":false},"temperature":{"anyOf":[{"type":"number","maximum":2,"minimum":0},{"type":"null"}],"title":"Temperature","description":"What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.","default":0},"top_p":{"anyOf":[{"type":"number","maximum":1,"exclusiveMinimum":0},{"type":"null"}],"title":"Top P","description":"An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both.","default":1}},"additionalProperties":false,"type":"object","required":["messages","model"],"title":"NIMLLMChatCompletionRequest"},"NIMVLMChatCompletionContentPartImage":{"properties":{"image_url":{"$ref":"#/components/schemas/ImageURL"},"type":{"type":"string","enum":["image_url"],"const":"image_url","title":"Type"}},"type":"object","required":["image_url","type"],"title":"NIMVLMChatCompletionContentPartImage"},"NIMVLMChatCompletionContentPartText":{"properties":{"text":{"type":"string","title":"Text"},"type":{"type":"string","enum":["text"],"const":"text","title":"Type"}},"type":"object","required":["text","type"],"title":"NIMVLMChatCompletionContentPartText"},"Role":{"type":"string","enum":["assistant","user"],"title":"Role"},"UsageInfo":{"properties":{"prompt_tokens":{"type":"integer","title":"Prompt Tokens","default":0},"total_tokens":{"type":"integer","title":"Total Tokens","default":0},"completion_tokens":{"anyOf":[{"type":"integer"},{"type":"null"}],"title":"Completion Tokens","default":0}},"additionalProperties":false,"type":"object","title":"UsageInfo"},"ValidationError":{"properties":{"loc":{"items":{"anyOf":[{"type":"string"},{"type":"integer"}]},"type":"array","title":"Location"},"msg":{"type":"string","title":"Message"},"type":{"type":"string","title":"Error Type"}},"type":"object","required":["loc","msg","type"],"title":"ValidationError"}}}},"namespace":"qc69jvmznzxy","updatedDate":"2026-08-10T20:29:54.568Z","nvcfFunctionId":"6dac0f3d-28ce-4c0c-bc26-b1cb9d22d9c7","createdDate":"2025-10-28T18:51:38.994Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/nvidia-nemotron-parse","termsOfUse":"GOVERNING TERMS: Access to this model is governed by the NVIDIA API Trial Terms of Service; use of the model is governed by the NVIDIA Community Model License. Use of the tokenizer included in this model is governed by the CC-BY-4.0 license.\n","showUnavailableBanner":false,"cta":"$38:0:props:children:0:props:children:1:props:children:props:children:props:children:3:props:children:1:props:children:1:props:cta","playground":{"type":"hidden"},"deploy":[{"label":"Linux with Docker","filename":"linux.md","contents":"$49"}],"modelCapability":{"functionCalling":true,"structuredOutput":false,"reasoning":true}},"artifactName":"nemotron-parse"},"isLoginRequired":true,"playgroundElement":"$4a","publisherName":"nvidia","searchParams":{"model":"nemotron-parse"},"tabs":[{"label":"Experience","bare":true,"icon":"play","kind":"default","id":"experience","href":"/nvidia/nemotron-parse","aliases":["/nvidia/nemotron-parse/experience"]},{"label":"Model Card","icon":"book","kind":"default","id":"modelcard","href":"/nvidia/nemotron-parse/modelcard","aliases":"$undefined"},{"label":"Deploy","kind":"default","id":"deploy","href":"/nvidia/nemotron-parse/deploy","aliases":"$undefined"}]}]}]}]]}]] 39:["$","$L4b",null,{"spec":"$38:0:props:children:1:props:children:props:children:props:endpointSpec"}]