45: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/434amnen8yqdi.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/2tbc_4m20jg4-.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/295ffwyuqa4b6.js"],"PageMetadata"] 46: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/434amnen8yqdi.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/2tbc_4m20jg4-.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/295ffwyuqa4b6.js"],"SearchResultsImage"] 47: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/434amnen8yqdi.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/2tbc_4m20jg4-.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/295ffwyuqa4b6.js"],""] 48: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/434amnen8yqdi.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/2tbc_4m20jg4-.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/295ffwyuqa4b6.js"],"default"] 49: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/434amnen8yqdi.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/2tbc_4m20jg4-.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/295ffwyuqa4b6.js"],"EndpointCTA"] 4a: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/434amnen8yqdi.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/2tbc_4m20jg4-.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/295ffwyuqa4b6.js"],"ModelContent"] 51: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/434amnen8yqdi.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/2tbc_4m20jg4-.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/295ffwyuqa4b6.js"],"default"] 42:["$","$L45",null,{"hasPartnerEndpoint":false}] 4b:T17db,# Model Overview ## Description: Florence-2 is an advanced vision foundation model using a prompt-based approach to handle a wide range of vision and vision-language tasks. It can interpret simple text prompts to perform tasks like captioning, object detection and segmentation. This model is ready for non-commercial use.
## Third-Party Community Consideration This model is not owned or developed by NVIDIA. This model has been developed and built to a third-party’s requirements for this application and use case; see link to the [Florence-2 Model Card](https://huggingface.co/microsoft/Florence-2-large-ft). ### License/Terms of Use [MIT license](https://huggingface.co/microsoft/Florence-2-large-ft/resolve/main/LICENSE). ## References: + [Florence-2 technical report](https://arxiv.org/abs/2311.06242) + [Jupyter Notebook for inference and visualization of Florence-2 model](https://huggingface.co/microsoft/Florence-2-large/blob/main/sample_inference.ipynb) ## Model Architecture: **Architecture Type:** Transformer-Based
**Network Architecture:** DaViT; standard encoder-decoder
## Input: **Input Type(s):** Image, Text.
**Input Format(s):** Red, Green, Blue (RGB), String
**Input Parameters:** Two Dimensional (2D)
**Other Properties Related to Input:** Task prompt. The model can perform 14 different vision language model and computer vision tasks. The input ```content``` field should be formatted as ```""```. Users need to specify the task type at the beginning. Image supports both base64 and NvCF asset id. Some tasks require a text prompt, and users need to provide that after image. Below are the list of tasks: * Caption * Detailed Caption * More Detailed Caption * Region to category * Region to description * Caption to Phrase Grounding * Object Detection * Dense Region Caption * Region proposal * Open vocabulary detection * Referring expression segmentation * Region to segmentation * Optical character recognition * Optical character recognition with region For ``````, ``````, ``````, the text prompt is a normal description. For example: ```'dog

'```. For ``````, ``````, ``````, the text prompt must be formatted as ``````, which is the normalized coordinates from region of interest bbox as calculated below. For example: ```'

'```. ``` x1=int(top_left_x_coor/width*999) y1=int(top_left_y_coor/height*999) x2=int(bottom_right_x_coor/width*999) y2=int(bottom_right_y_coor/height*999) ``` Other tasks don't take text prompt input. For example: ```'

'```.
## Output: **Output Type(s):** Text, Bounding Box, Segmentation Mask
**Output Format:** String or Dictionary (Text), Image (RBG, Black & White) **Output Parameters:** One Dimensional (1D)- Text, 2D- Bounding Box, Segmentation Mask
**Other Properties Related to Output:**
The response data needs to be saved into a zip file and extracted. It contains an overlay image (when bounding box or segmentation is generated) and a ```.response``` JSON file. For caption related tasks, the output is saved in ```"content": "caption"```. For example, ```"content": "A black and brown dog in a grass field"```
For bounding box or segmentation masks, the output is saved in ```"entities": "{"bboxes":[], "quad_boxes":[], "labels":[], "polygons": []}"```. For example, ```"entiites": {"bboxes":[[192.47,68.882,611.081,346.83],[1.529,240.178, 611.081,403.394]],"quad_boxes":null,"labels":["A black and brown dog","a grass field"],"bboxes_labels":null,"polygons":null}```
## Software Integration: **Runtime Engine(s):** * PyTorch
**Supported Hardware Microarchitecture Compatibility:**
* NVIDIA Ampere
* NVIDIA Blackwell
* NVIDIA Jetson
* NVIDIA Hopper
* NVIDIA Lovelace
* NVIDIA Pascal
* NVIDIA Turing
* NVIDIA Volta
**[Preferred/Supported] Operating System(s):**
* Linux
* Windows
## Model Version(s): * Florence-2-base
* Florence-2-large
* Florence-2-base-ft
* Florence-2-large-ft
# Training and Testing Datasets: ## Training Dataset: **Link** * FLD-5B dataset (Microsoft)
**Data Collection Method by dataset**
* Hybrid: Human, Automatic/Sensors
**Labeling Method by dataset**
* Hybrid: Human, Automatic/Sensors
**Properties (Quantity, Dataset Descriptions, Sensor(s))** * The dataset consists of images from a diverse collection of purposes, including caption, detection, segmentation and optical character recognition. There are 126 million images, 500 million text annotations, and 1.3 billion text-region annotations, and 3.6 billion text-phrase-region annotations across different tasks.
## Testing Dataset: **Link** * [COCO](https://cocodataset.org/), [Flickr30k](https://shannon.cs.illinois.edu/DenotationGraph/)
**Data Collection Method by dataset**
* Hybrid: Human, Automatic/Sensors
**Labeling Method by dataset**
* Hybrid: Human, Automatic/Sensors
**Properties (Quantity, Dataset Descriptions, Sensor(s))** * COCO: COCO is a large-scale object detection, segmentation, and captioning dataset. COCO has several features: 330K images (>200K labeled), 1.5 million object instances
* Flickr30k: The Flickr30k dataset contains 31,000 images collected from Flickr, together with five (5) reference sentences provided by human annotators
## Inference: **Engine:** PyTorch
**Test Hardware:**
* NVIDIA L40
4c:T4e5,| Field | Response | | -- | -- | | Generatable or reverse engineerable personally-identifiable information (PII)? | None | | Protected classes used to create this model? | Not Applicable (No PII) | | Was consent obtained for any PII used? | Not Applicable (No PII) | | How often is dataset reviewed? | Before Release | | Is a mechanism in place to honor data subject right of access or deletion of personal data? | No | | If PII collected for the development of the model, was it collected directly by NVIDIA? |Not Applicable | | If PII collected for the development of the model by NVIDIA, do you maintain or have access to disclosures made to data subjects? | Not Applicable | | If PII collected for the development of this AI model, was it minimized to only what was required? | Not Applicable | | Is there provenance for all datasets used in training? | Yes | | Does data labeling (annotation, metadata) comply with privacy laws? | Yes | | Is data compliant with data subject requests for data correction or removal, if such a request was made? | Yes | | Applicable NVIDIA Privacy Policy | [https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/](https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/) |4d:Tb6d,{ "id": "6415f5ec-327f-4e25-affc-71f9babd37d2", "choices": [ { "index": 0, "message": { "role": "assistant", "content": "", "entities": { "bboxes":null, "quad_boxes":[[55.935001373291016,5.039999961853027,1071.8050537109375,5.039999961853027,1071.8050537109375,22.799999237060547,55.935001373291016,22.799999237060547],[780.2650146484375,60.23999786376953,979.14501953125,60.23999786376953,979.14501953125,87.1199951171875,780.2650146484375,87.1199951171875],[45.76499938964844,88.08000183105469,379.114990234375,88.08000183105469,379.114990234375,115.91999816894531,45.76499938964844,115.91999816894531],[780.2650146484375,95.27999877929688,1070.675048828125,93.36000061035156,1070.675048828125,123.1199951171875,780.2650146484375,125.04000091552734],[45.76499938964844,123.1199951171875,298.885009765625,123.1199951171875,298.885009765625,152.87998962402344,45.76499938964844,153.83999633789062],[45.76499938964844,193.67999267578125,350.864990234375,193.67999267578125,350.864990234375,220.55999755859375,45.76499938964844,221.51998901367188],[420.92498779296875,187.9199981689453,631.10498046875,187.9199981689453,631.10498046875,221.51998901367188,420.92498779296875,221.51998901367188],[844.6749877929688,195.59999084472656,863.885009765625,195.59999084472656,863.885009765625,222.47999572753906,844.6749877929688,222.47999572753906],[913.60498046875,193.67999267578125,996.094970703125,191.75999450683594,996.094970703125,216.72000122070312,913.60498046875,218.63999938964844],[138.4250030517578,222.47999572753906,592.6849975585938,222.47999572753906,592.6849975585938,258.47998046875,138.4250030517578,258.47998046875],[844.6749877929688,231.59999084472656,963.3250122070312,230.63999938964844,963.3250122070312,256.55999755859375,844.6749877929688,257.5199890136719],[45.76499938964844,346.32000732421875,346.3450012207031,344.3999938964844,346.3450012207031,382.3199768066406,45.76499938964844,384.239990234375],[893.2650146484375,344.3999938964844,1018.6950073242188,340.55999755859375,1019.8250122070312,377.5199890136719,893.2650146484375,382.3199768066406],[878.5750122070312,385.1999816894531,1061.635009765625,385.1999816894531,1061.635009765625,402.47998046875,878.5750122070312,402.47998046875],[228.8249969482422,436.55999755859375,897.7849731445312,436.55999755859375,897.7849731445312,464.3999938964844,228.8249969482422,464.3999938964844]], "labels":["THE CHEQUE PAPER CONTAINS COLORED MICROPRINTING AND WATERMARK. PROTECTED BY THE LAW OF THE UNITED STATES.","CHECK No 0007","765 Dolor sit Amet APT B5","DATE: auy, 11, 2019","Brooklyn, NY, 12345","PAY TO THE ORDER OF:","Mary Johnson","$","715,39","Seven hundred fifteen and 100","DOLLARS","MEMO Monthly rent","Jsmith","AUTHORIZED SIGNATURE","\"I\" 4567899012\" I\" -6543210981:890987654321091\""], "bboxes_labels":null, "polygons":null } }, "finish_reason": "stop" } ], "usage": { "completion_tokens": 308, "prompt_tokens": 13, "total_tokens": 321 } }4e:T11bb,# The model can perform 14 different vision language model and computer vision tasks. The input ```content``` field should be formatted as ```""```. # Users need to specify the task type at the beginning. Image supports both base64 and NvCF asset id. Some tasks require a text prompt, and users need to provide that after image. Below are the examples for each task. # For , , , users can change the text prompt as other descriptions. # For , , , the text prompt is formatted as , which is the normalized coordinates from region of interest bbox. x1=int(top_left_x_coor/width*999), y1=int(top_left_y_coor/height*999), x2=int(bottom_right_x_coor/width*999), y2=int(bottom_right_y_coor/height*999). import os import sys import zipfile import requests nvai_url = "https://ai.api.nvidia.com/v1/vlm/microsoft/florence-2" header_auth = f'Bearer {os.getenv("API_KEY_REQUIRED_IF_EXECUTING_OUTSIDE_NGC", "")}' prompts = ["", "", "", "", "", "", "A black and brown dog is laying on a grass field.", "a black and brown dog", "", "a black and brown dog", "", "", "", ""] def _upload_asset(input, description): """ Uploads an asset to the NVCF API. :param input: The binary asset to upload :param description: A description of the asset """ authorize = requests.post( "https://api.nvcf.nvidia.com/v2/nvcf/assets", headers={ "Authorization": header_auth, "Content-Type": "application/json", "accept": "application/json", }, json={"contentType": "image/jpeg", "description": description}, timeout=30, ) authorize.raise_for_status() response = requests.put( authorize.json()["uploadUrl"], data=input, headers={ "x-amz-meta-nvcf-asset-description": description, "content-type": "image/jpeg", }, timeout=300, ) response.raise_for_status() return str(authorize.json()["assetId"]) def _generate_content(task_id, asset_id): if task_id < 0 or task_id >= len(prompts): print(f"task_id should within [0, {len(prompts)-1}]") exit(1) prompt = prompts[task_id] content = f'{prompt}

' return content if __name__ == "__main__": """Uploads two images of your choosing to the NVCF API and sends a request to the Visual ChangeNet model to compare them. The response is saved to """ if len(sys.argv) != 4: print("Usage: python test.py \n" "For example: python test.py car.jpg result_dir 0") sys.exit(1) if len(os.getenv("API_KEY_REQUIRED_IF_EXECUTING_OUTSIDE_NGC", "")) == 0: print("API_KEY not set. Please export API_KEY_REQUIRED_IF_EXECUTING_OUTSIDE_NGC= as environment variable.") sys.exit(1) # Local images asset_id = _upload_asset(open(sys.argv[1], "rb"), "Test Image") content = _generate_content(int(sys.argv[3]), asset_id) # Asset IDs returned by the _upload_asset function inputs = { "messages": [{ "role": "user", "content": content }] } # asset_list = f"{asset_id}" headers = { "Content-Type": "application/json", "NVCF-INPUT-ASSET-REFERENCES": asset_id, "NVCF-FUNCTION-ASSET-IDS": asset_id, "Authorization": header_auth, "Accept": "application/json" } print(asset_id, inputs) # Send the request to the NIM API. response = requests.post(nvai_url, headers=headers, json=inputs) with open(f"{sys.argv[2]}.zip", "wb") as out: out.write(response.content) with zipfile.ZipFile(f"{sys.argv[2]}.zip", "r") as z: z.extractall(sys.argv[2]) print(f"Response saved to path: {sys.argv[2]}. File list: {os.listdir(sys.argv[2])}") 4f:T10a0,// The model can perform 14 different vision language model and computer vision tasks. The input ```content``` field should be formatted as ```""```. // Users need to specify the task type at the beginning. Image supports both base64 and NvCF asset id. Some tasks require a text prompt, and users need to provide that after image. Below are the examples for each task. // For , , , users can change the text prompt as other descriptions. // For , , , the text prompt is formatted as , which is the normalized coordinates from region of interest bbox. x1=int(top_left_x_coor/width*999), y1=int(top_left_y_coor/height*999), x2=int(bottom_right_x_coor/width*999), y2=int(bottom_right_y_coor/height*999). // Prerequisites: // npm install decompress@4.2.1 node-fetch@^2.7.0 const fs = require("fs"); const decompress = require("decompress"); const fetch = require("node-fetch") const nvai_url = "https://ai.api.nvidia.com/v1/vlm/microsoft/florence-2"; const header_auth = `Bearer ${process.env.API_KEY_REQUIRED_IF_EXECUTING_OUTSIDE_NGC}`; const prompts = [ "", "", "", "", "", "", "A black and brown dog is laying on a grass field.", "a black and brown dog", "", "a black and brown dog", "", "", "", "" ]; async function uploadAsset(input, description) { const assets_url = "https://api.nvcf.nvidia.com/v2/nvcf/assets"; const headers = { Authorization: header_auth, "Content-Type": "application/json", accept: "application/json", }; const put_headers = { "x-amz-meta-nvcf-asset-description": description, "content-type": "image/jpeg", }; const payload = { contentType: "image/jpeg", description: description, }; const response = await fetch(assets_url, { method: "POST", body: JSON.stringify(payload), headers: headers, }); const data = await response.json(); const asset_url = data["uploadUrl"]; const asset_id = data["assetId"]; const fileData = fs.readFileSync(input); await fetch(asset_url, { method: "PUT", body: fileData, headers: put_headers, }); return asset_id.toString(); } async function generateContent(taskId, assetId) { return `${prompts[taskId]}

` } (async () => { if (process.argv.length !== 5) { console.log( "Usage: node test.js \nFor example: node test.js car.jpg result_dir 0" ); process.exit(1); } if (process.env.API_KEY_REQUIRED_IF_EXECUTING_OUTSIDE_NGC.length == 0) { console.log( "API_KEY not set. Please export API_KEY_REQUIRED_IF_EXECUTING_OUTSIDE_NGC= as environment variable." ); process.exit(1); } const assetId = await uploadAsset(process.argv[2], "Test Image"); const content = await generateContent(process.argv[4], assetId) const inputs = { messages: [{ role: "user", content: content }] }; const response = await fetch(nvai_url, { method: "POST", headers: { "Content-Type": "application/json", "NVCF-INPUT-ASSET-REFERENCES": `${assetId}`, "NVCF-FUNCTION-ASSET-IDS": `${assetId}`, Authorization: header_auth, }, body: JSON.stringify(inputs), }); const buffer = await response.arrayBuffer(); fs.writeFileSync(`${process.argv[3]}.zip`, Buffer.from(buffer)); // Unzip the response synchronously await decompress(`${process.argv[3]}.zip`, process.argv[3]); // Log the output directory and its contents console.log(`Response saved to ${process.argv[3]}`); console.log(fs.readdirSync(process.argv[3])); })(); 50:Tfdc,#!/bin/bash # The model can perform 14 different vision language model and computer vision tasks. The input ```content``` field should be formatted as ```""```. # Users need to specify the task type at the beginning. Image supports both base64 and NvCF asset id. Some tasks require a text prompt, and users need to provide that after image. Below are the examples for each task. # For , , , users can change the text prompt as other descriptions. # For , , , the text prompt is formatted as , which is the normalized coordinates from region of interest bbox. x1=int(top_left_x_coor/width*999), y1=int(top_left_y_coor/height*999), x2=int(bottom_right_x_coor/width*999), y2=int(bottom_right_y_coor/height*999). set -e # Check arguments if [ "$#" -ne 3 ]; then printf "Usage: ./test.sh \nFor example: ./test.sh car.jpg result_dir 0\n" exit 1 fi if [[ -z "${API_KEY_REQUIRED_IF_EXECUTING_OUTSIDE_NGC}" ]]; then echo "API_KEY not set. Please export API_KEY_REQUIRED_IF_EXECUTING_OUTSIDE_NGC= as environment variable." exit 1 fi # Set variables nvai_url="https://ai.api.nvidia.com/v1/vlm/microsoft/florence-2" api_key=$API_KEY_REQUIRED_IF_EXECUTING_OUTSIDE_NGC assets_url="https://api.nvcf.nvidia.com/v2/nvcf/assets" prompts=( "" "" "" "" "" "" "A black and brown dog is laying on a grass field." "a black and brown dog" "" "a black and brown dog" "" "" "" "" ) content_type="image/jpeg" description="Test Image" # Function to upload an asset upload_asset() { local input=$1 local description=$2 # Authorize upload authorize=$(curl -s -X POST $assets_url \ -H "Authorization: Bearer $api_key" \ -H "Content-Type: application/json" \ -H "accept: application/json" \ -d "{\"contentType\": \"$content_type\", \"description\": \"$description\"}") # Get upload URL and asset ID upload_url=$(echo $authorize | jq -r '.uploadUrl') asset_id=$(echo $authorize | jq -r '.assetId') # Upload asset curl -s -X PUT $upload_url \ -H "x-amz-meta-nvcf-asset-description: $description" \ -H "content-type: $content_type" \ --upload-file $input echo $asset_id } # Function to generate content generate_content() { local task_id=$1 local asset_id=$2 prompt=${prompts[$task_id]} content="$prompt

" echo $content } # Upload images asset_id=$(upload_asset $1 $description) content=$(generate_content $3 $asset_id) echo '{ "messages":[{ "role": "user", "content": "'"$content"'" }] }' > payload.json mkdir -p $2 # Compare images via microservice location_command="curl -D - -s -X POST $nvai_url \ -H \"Content-Type: application/json\" \ -H \"NVCF-INPUT-ASSET-REFERENCES: $asset_id\" \ -H \"NVCF-FUNCTION-ASSET-IDS: $asset_id\" \ -H \"Authorization: Bearer $api_key\" \ -d @payload.json \ | grep location | awk '{print \$2}'" location=$(eval ${location_command} | tr -d '\n' | tr -d '\r' | tr -d ' ' | tr -d '"' | tr -d ',') # The download command will download the file from the location header download_command="curl -s '${location}' > $2.zip" echo $location_command # Download the .zip file response=$(eval ${download_command}) # Unzip the file unzip -q $2.zip -d $2 echo "Response saved to $2.zip" echo $(ls $2) 43:[["$","div",".3",{"className":"relative","children":[["$","div",null,{"className":"relative flex min-h-[194px] w-full flex-col overflow-hidden p-md sm:p-ml bg-manitoulinLightBlack","children":[["$","$L46",null,{"alt":"","className":"object-cover object-center !left-1/2 z-10 !w-1/2 brightness-20 lg:brightness-75","fill":true,"priority":true,"src":"https://assets.ngc.nvidia.com/products/api-catalog/images/microsoft-florence-2.jpg","style":{"maskImage":"linear-gradient(to left, rgba(0,0,0,1), rgba(0,0,0,0))"}}],["$","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":[["$","$L47",null,{"className":"w-fit text-ml text-n300 lowercase hover:text-n050","href":"/microsoft","children":"Microsoft"}],["$","div",null,{"className":"flex flex-col items-start gap-3 lg:flex-row lg:items-center","children":[["$","h1",null,{"className":"max-w-full text-lg leading-heading font-medium break-words text-primary","data-testid":"resource-name","id":"resource-name","children":"florence-2"}],[["$","span","DEPRECATION",{"className":"nv-badge nv-badge--kind-solid nv-badge--color-red h-[18px] py-0","data-testid":"nv-badge","ref":"$undefined","children":["$undefined","Deprecated"]}],["$","span","PREVIEW",{"className":"nv-badge nv-badge--kind-solid nv-badge--color-purple h-[18px] py-0","data-testid":"nv-badge","ref":"$undefined","children":["$undefined","Free Endpoint"]}]],"$undefined"]}],["$","p",null,{"className":"max-w-[85ch] text-ms text-primary","id":"resource-description","children":"Vision foundation model capable of performing diverse computer vision and vision language tasks."}],["$","div",null,{"className":"flex w-full flex-col items-start gap-md lg:flex-row lg:items-end lg:justify-between","children":[["$","div",null,{"className":"flex w-full min-w-0 flex-wrap gap-sm lg:flex-1","children":["$","$L48",null,{"artifactType":"ENDPOINT","density":"standard","labels":["Language Generation","Multimodal","Vision Assistant","Visual Question Answering","computer vision","cv","image","nimType:endpoint:nim_type_preview","usecase:endpoint:usecase_image_class","usecase:endpoint:usecase_image_to_text","usecase:endpoint:usecase_object_detect","usecase:endpoint:usecase_text_to_image","vlm"],"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",["$","$L49",null,{"cta":"$undefined","isNIMAccessRestricted":"$undefined","isNIMAvailable":false}]]}]]}]]}]}]}],["$","div",null,{"className":"pointer-events-none absolute right-0 bottom-0 left-0 z-20 h-30 bg-gradient-to-t to-transparent from-manitoulinLightBlack via-manitoulinLightBlack/70"}]]}],["$","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":["$","section",null,{"className":"flex w-full flex-col justify-between rounded-4 border-manitoulinBorderColor bg-manitoulinDarkBlack sm:rounded-6 lg:rounded-8 p-ms lg:p-lg","children":["$","$L4a",null,{"artifact":{"artifactType":"ENDPOINT","name":"microsoft-florence-2","displayName":"florence-2","publisher":"microsoft","shortDescription":"Vision foundation model capable of performing diverse computer vision and vision language tasks.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/microsoft-florence-2.jpg","labels":"$43:0:props:children:0:props:children:1:props:children:props:children:props:children:3:props:children:0:props:children:props:labels","attributes":[{"key":"DEPRECATION","value":"10/10/2025"},{"key":"PREVIEW","value":"true"}],"updatedDate":"2025-04-14T23:33:28.525Z","bias":"| Field | Response |\n| -- | -- |\n|Participation considerations from adversely impacted groups [(protected classes)](https://www.senate.ca.gov/content/protected-classes) in model design and testing: | None of the Above |\n| Measures taken to mitigate against unwanted bias: | No measures taken to mitigate against unwanted bias.|","canGuestDownload":true,"createdDate":"2024-07-31T08:23:58.847Z","description":"$4b","explainability":"| Field | Response |\n| -- | -- |\n| Intended Application(s) & Domain(s): | The primary use of Florence-2 is research on large multimodal models. |\n| Model Type: | Text generation, object detection, segmentation, and OCR from image |\n| Intended Users: | The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence. |\n| Output: | Text, detection, segmentation |\n| Describe how the model works: | Text generation, object detection, segmentation, and OCR from image |\n| Technical Limitations: | |\n| Verified to have met prescribed NVIDIA standards: | |\n| Performance Metrics: | Accuracy |\n| Licensing: | [MIT License](https://huggingface.co/microsoft/Florence-2-large/resolve/main/LICENSE) |","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","privacy":"$4c"},"endpointName":"microsoft-florence-2","endpointSpec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for microsoft/florence-2","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim 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":"MIT","url":"https://huggingface.co/microsoft/Florence-2-large/resolve/main/LICENSE"}},"servers":[{"url":"https://ai.api.nvidia.com/v1"}],"tags":[{"name":"Multimodal API","description":"This API performs inference using vision foundation models"}],"paths":{"/vlm/microsoft/florence-2":{"post":{"tags":["Multimodal API"],"summary":"Request response from the model","description":"Invokes inference using the model chat parameters. If uploading large images, this POST should be used in conjunction with the NVCF API which allows for the upload of large assets. You can find details on how to use NVCF Asset APIs here: https://docs.api.nvidia.com/cloud-functions/reference/createasset","operationId":"invokeFunction","parameters":[{"in":"header","name":"NVCF-INPUT-ASSET-REFERENCES","schema":{"type":"string","maxLength":370,"format":"uuid"},"required":false,"description":"String of asset IDs separated by commas. Data is uploaded to AWS S3 using NVCF Asset APIs and associated with these asset IDs.If the size of an image is more than 180KB, it needs to be uploaded to a presigned S3 URL bucket. The presigned URL allows for secure and temporary access to the S3 bucket for uploading the image. Once the asset is requested, an asset ID is generated for it. Please include this asset ID in this header and to use the uploaded image in a prompt, you need to refer to it using the following format: `

`."}],"requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatRequest"}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletion"}}}},"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}$","maxLength":64}}}},"422":{"description":"Validation failed, provided entity could not be processed.","content":{"application/json":{"schema":{"properties":{"type":{"type":"string","format":"^.{1, 128}$","maxLength":128,"description":"Error type"},"title":{"type":"string","format":"^.{1, 128}$","maxLength":128,"description":"Error title"},"status":{"type":"integer","minimum":100,"maximum":999,"description":"Error status code"},"detail":{"type":"string","format":"^.{1, 1024}$","maxLength":1024,"description":"Detailed information about the error"},"instance":{"type":"string","format":"^.{1, 256}$","maxLength":256,"description":"Function instance used to invoke the request"},"requestId":{"type":"string","format":"uuid","maxLength":36,"description":"UUID of the request"}},"type":"object","required":["type","title","status","detail","instance","requestId"],"title":"InvokeError"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/6018fed7-f227-48dc-99bc-3fd4264d5037","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"properties":{"type":{"type":"string","format":"^.{1, 128}$","maxLength":128,"description":"Error type"},"title":{"type":"string","format":"^.{1, 128}$","maxLength":128,"description":"Error title"},"status":{"type":"integer","minimum":100,"maximum":999,"description":"Error status code"},"detail":{"type":"string","format":"^.{1, 1024}$","maxLength":1024,"description":"Detailed information about the error"},"instance":{"type":"string","format":"^.{1, 256}$","maxLength":256,"description":"Function instance used to invoke the request"},"requestId":{"type":"string","format":"uuid","maxLength":36,"description":"UUID of the request"}},"type":"object","required":["type","title","status","detail","instance","requestId"],"title":"InvokeError"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/6018fed7-f227-48dc-99bc-3fd4264d5037","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}},"x-nvai-meta":{"name":"Create chat completion","returns":"Returns a [chat completion](/docs/api-reference/chat/object) object.","path":"create","examples":[{"name":"dog.jpg","input":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/florence-2/input/dog.jpg","task_prompt":"","text_prompt":"A black and brown dog is laying on a grass field."},"requestJson":"{ \"messages\": [ { \"role\": \"user\", \"content\": \"<%- input.task_prompt %><%- input.text_prompt %>

\\\"/>\" } ], }","responseJson":"{ \"id\": \"55ed6594-8140-4f36-969f-2f37cdf4b64e\", \"choices\": [ { \"index\": 0, \"message\": { \"role\": \"assistant\", \"content\": \"\", \"entities\": { \"bboxes\":[[192.4739990234375,68.88200378417969,611.0819702148438,346.8340148925781],[1.5299999713897705,240.17800903320312, 611.0819702148438,403.3940124511719]], \"quad_boxes\":null, \"labels\":[\"A black and brown dog\",\"a grass field\"],\"bboxes_labels\":null, \"polygons\":null } }, \"finish_reason\": \"stop\" } ], \"usage\": { \"completion_tokens\": 19, \"prompt_tokens\": 22, \"total_tokens\": 41 } }"},{"name":"check.jpeg","input":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/florence-2/input/check.jpeg","task_prompt":"","text_prompt":""},"requestJson":"{ \"messages\": [ { \"role\": \"user\", \"content\": \"<%- input.task_prompt %><%- input.text_prompt %>

\\\"/>\" } ], }","responseJson":"$4d"}],"templates":[{"title":"Default","requestEjs":{"python":"$4e","node.js":"$4f","curl":"$50"},"response":"{\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"...\",\n \"entities\": \"...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}},"/status/{requestId}":{"get":{"tags":["Multimodal API"],"summary":"Gets the result of an earlier function invocation request that returned a status of 202.","operationId":"getFunctionInvocationResult","parameters":[{"name":"requestId","in":"path","description":"requestId to poll results","required":true,"schema":{"type":"string","format":"uuid","maxLength":36}}],"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletion"}}}},"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}$","maxLength":64}}}},"422":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"properties":{"type":{"type":"string","format":"^.{1, 128}$","maxLength":128,"description":"Error type"},"title":{"type":"string","format":"^.{1, 128}$","maxLength":128,"description":"Error title"},"status":{"type":"integer","minimum":100,"maximum":999,"description":"Error status code"},"detail":{"type":"string","format":"^.{1, 1024}$","maxLength":1024,"description":"Detailed information about the error"},"instance":{"type":"string","format":"^.{1, 256}$","maxLength":256,"description":"Function instance used to invoke the request"},"requestId":{"type":"string","format":"uuid","maxLength":36,"description":"UUID of the request"}},"type":"object","required":["type","title","status","detail","instance","requestId"],"title":"InvokeError"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/6018fed7-f227-48dc-99bc-3fd4264d5037","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"properties":{"type":{"type":"string","format":"^.{1, 128}$","maxLength":128,"description":"Error type"},"title":{"type":"string","format":"^.{1, 128}$","maxLength":128,"description":"Error title"},"status":{"type":"integer","minimum":100,"maximum":999,"description":"Error status code"},"detail":{"type":"string","format":"^.{1, 1024}$","maxLength":1024,"description":"Detailed information about the error"},"instance":{"type":"string","format":"^.{1, 256}$","maxLength":256,"description":"Function instance used to invoke the request"},"requestId":{"type":"string","format":"uuid","maxLength":36,"description":"UUID of the request"}},"type":"object","required":["type","title","status","detail","instance","requestId"],"title":"InvokeError"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/6018fed7-f227-48dc-99bc-3fd4264d5037","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"Errors":{"properties":{"type":{"type":"string","format":"^.{1, 128}$\"","maxLength":128,"description":"Error type"},"title":{"type":"string","format":"^.{1, 128}$","maxLength":128,"description":"Error title"},"status":{"type":"integer","minimum":100,"maximum":999,"description":"Error status code"},"detail":{"type":"string","format":"^.{1, 1024}$","maxLength":1024,"description":"Detailed information about the error"},"instance":{"type":"string","format":"^.{1, 256}$","maxLength":256,"description":"Function instance used to invoke the request"},"requestId":{"type":"string","format":"uuid","maxLength":36,"description":"UUID of the request"}},"type":"object","required":["type","title","status","detail","instance","requestId"],"title":"InvokeError"},"ChatCompletion":{"properties":{"id":{"description":"A unique identifier for the completion.","examples":["d6d4f6a9-c96e-4697-82ac-7a247d2eb1ec"],"maxLength":100000000,"pattern":"^.*$","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/Choice"},"maxItems":1,"title":"Choices","type":"array"},"usage":{"allOf":[{"$ref":"#/components/schemas/Usage"}],"description":"Usage statistics for the completion request."}},"required":["id","choices","usage"],"title":"ChatCompletion","type":"object"},"ChatRequest":{"additionalProperties":false,"properties":{"messages":{"description":"A list of messages comprising the conversation.","examples":[[{"content":"A green car parked in front of a yellow building.

","role":"user"}],[{"content":"A green car parked in front of a yellow building.

","role":"user"}]],"items":{"$ref":"#/components/schemas/Message"},"maxItems":10,"minItems":1,"title":"Messages","type":"array"},"early_stopping":{"default":false,"description":"early stopping","title":"Early Stopping","type":"boolean"},"do_sample":{"default":false,"description":"do sample","title":"Do Sample","type":"boolean"},"num_beans":{"default":3,"description":"number of beans","maximum":5,"minimum":1,"title":"Num Beans","type":"integer"},"max_tokens":{"default":1024,"description":"The maximum number of tokens to generate in any given call.","maximum":4096,"minimum":1,"title":"Max Tokens","type":"integer"}},"required":["messages"],"title":"ChatRequest","type":"object"},"Choice":{"properties":{"index":{"default":0,"description":"The index of the choice in the list of choices (always 0).","exclusiveMaximum":1,"minimum":0,"title":"Index","type":"integer"},"message":{"allOf":[{"$ref":"#/components/schemas/MessageWithEntities"}],"description":"A chat completion message generated by the model."},"finish_reason":{"anyOf":[{"enum":["stop","length"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached.","examples":["stop"],"title":"Finish Reason"}},"required":["message"],"title":"Choice","type":"object"},"Entity":{"properties":{"bboxes":{"anyOf":[{"items":{"description":"List of coordinates for each object.","items":{"exclusiveMinimum":-100000000,"maximum":100000000,"type":"number"},"maxItems":4,"minItems":0,"type":"array"},"maxItems":1000000,"type":"array"},{"type":"null"}],"default":null,"description":"Bounding box coordinates of each detection.","examples":[[[1212.43,304.64,55.32,154.42],[195.64,294.74,121.23,275.92]]],"title":"Bboxes"},"quad_boxes":{"anyOf":[{"items":{"description":"List of coordinates for each object.","items":{"exclusiveMinimum":-100000000,"maximum":100000000,"type":"number"},"maxItems":8,"minItems":0,"type":"array"},"maxItems":1000000,"type":"array"},{"type":"null"}],"default":null,"description":"Quad bounding box coordinates of each detection.","examples":[[[1212.43,304.63,55.82,154.43,195.32,294.32,121.54,275.93]]],"title":"Quad Boxes"},"labels":{"anyOf":[{"items":{"maxLength":100000000,"pattern":"^.*$","type":"string"},"maxItems":100000000,"type":"array"},{"type":"null"}],"default":null,"description":"Labels.","examples":[["human","car"]],"title":"Labels"},"bboxes_labels":{"anyOf":[{"items":{"maxLength":100000000,"pattern":"^.*$","type":"string"},"maxItems":100000000,"type":"array"},{"type":"null"}],"default":null,"description":"Labels.","examples":[["human","car"]],"title":"Bboxes Labels"},"polygons":{"anyOf":[{"items":{"description":"List of closed curve for one object.","items":{"description":"Polygon points for each closed curve.","items":{"exclusiveMinimum":-100000000,"maximum":100000000,"type":"number"},"maxItems":1000000,"minItems":0,"type":"array"},"maxItems":1000000,"minItems":0,"type":"array"},"maxItems":1000000,"type":"array"},{"type":"null"}],"default":null,"description":"List of objects segmented.","examples":[[[[250.61,72.92,260.4,71.3,271.42,96.75,275.7,115.34,283.04,115.34]]]],"title":"Polygons"}},"title":"Entity","type":"object"},"Message":{"additionalProperties":false,"properties":{"role":{"description":"The role of the message author.","enum":["user","assistant"],"title":"Role","type":"string"},"content":{"anyOf":[{"maxLength":100000000,"pattern":"^.*$","type":"string"},{"items":{"anyOf":[{"$ref":"#/components/schemas/UserTextContent"},{"$ref":"#/components/schemas/UserImageContent"}]},"maxItems":100000000,"type":"array"},{"type":"null"}],"default":null,"description":"User input content","title":"Content"}},"required":["role"],"title":"Message","type":"object"},"MessageWithEntities":{"additionalProperties":false,"properties":{"role":{"description":"The role of the message author.","enum":["user","assistant"],"title":"Role","type":"string"},"content":{"description":"Result content, the format is text_result.","examples":["The figure has a dog."],"maxLength":100000000,"pattern":"^.*$","title":"Content","type":"string"},"entities":{"anyOf":[{"$ref":"#/components/schemas/Entity"},{"type":"null"}],"default":null,"description":"Result content","examples":[{"bboxes":[[35.52000045776367,159.1199951171875,583.3599853515625,375.1199951171875],[0.3199999928474426,0.23999999463558197,639.0399780273438,304.55999755859375]],"bboxes_labels":null,"labels":["A green car","a yellow building"],"polygons":null,"quad_boxes":null}]}},"required":["role","content"],"title":"MessageWithEntities","type":"object"},"Usage":{"properties":{"completion_tokens":{"description":"Number of tokens in the generated completion.","examples":[19],"maximum":100000000,"minimum":0,"title":"Completion Tokens","type":"integer"},"prompt_tokens":{"description":"Number of tokens in the prompt.","examples":[59],"maximum":100000000,"minimum":0,"title":"Prompt Tokens","type":"integer"},"total_tokens":{"description":"Total number of tokens used in the request (prompt + completion).","examples":[78],"maximum":100000000,"minimum":0,"title":"Total Tokens","type":"integer"}},"required":["completion_tokens","prompt_tokens","total_tokens"],"title":"Usage","type":"object"},"UserImageContent":{"additionalProperties":false,"properties":{"type":{"const":"image_url","description":"The type of the content part.","title":"Type"},"image_url":{"description":"Base64 encoded image data in form of `data:image/{format};base64,{base64encodedimage}`.","maxLength":204800,"pattern":"^.*$","title":"Image Url","type":"string"}},"required":["type","image_url"],"title":"UserImageContent","type":"object"},"UserTextContent":{"additionalProperties":false,"properties":{"type":{"const":"text","description":"The type of the content part.","title":"Type"},"text":{"description":"The text content.","maxLength":204800,"pattern":"^.*$","title":"Text","type":"string"}},"required":["type","text"],"title":"UserTextContent","type":"object"}}}},"namespace":"qc69jvmznzxy","updatedDate":"2025-10-03T08:50:48.207Z","nvcfFunctionId":"94d86bf9-a844-4696-be8c-5703114867ec","createdDate":"2024-07-31T08:23:59.272Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/microsoft-florence-2","termsOfUse":"GOVERNING TERMS: Your use of this API is governed by the NVIDIA API Trial Service Terms of Use; and the use of this model is governed by the MIT License.\n","deprecationNotice":"This API has been deprecated as of 10/10/2025. It will no longer be supported after 10/10/2025. Please transition to another model to avoid any service interruptions. For more models information, visit our API Reference.","showUnavailableBanner":false},"artifactName":"microsoft-florence-2"},"isLoginRequired":true,"playgroundElement":"$undefined","publisherName":"microsoft","searchParams":{},"tabs":[{"label":"Experience","bare":true,"icon":"play","kind":"default","id":"experience","href":"/microsoft/microsoft-florence-2","aliases":["/microsoft/microsoft-florence-2/experience"]}]}]}]}]]}]] 44:["$","$L51",null,{"spec":"$43:0:props:children:1:props:children:props:children:props:endpointSpec"}]