CAGRA CuVS
vector-searchvector-databaseretrieval-augmented-generationRAPIDScloud-hyperscalersllm-frameworksfunction-callingnvidiaweaviate-recipesintegrationsPythongenerative-ai
Export
CAGRA Demo with NVIDIA cuVS
Learn more about CAGRA here!
[1]
Thu Aug 8 21:15:04 2024
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 535.104.05 Driver Version: 535.104.05 CUDA Version: 12.2 |
|-----------------------------------------+----------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+======================+======================|
| 0 Tesla T4 Off | 00000000:00:04.0 Off | 0 |
| N/A 50C P8 10W / 70W | 0MiB / 15360MiB | 0% Default |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+
+---------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=======================================================================================|
| No running processes found |
+---------------------------------------------------------------------------------------+
Check which version of CUDA you are using, if 11.x -- you will need to use pylibraft-cu11.
[2]
Looking in indexes: https://pypi.org/simple, https://pypi.nvidia.com
Collecting cuvs-cu12
Downloading https://pypi.nvidia.com/cuvs-cu12/cuvs_cu12-24.8.0-cp310-cp310-manylinux_2_28_x86_64.whl (1127.3 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.1/1.1 GB 1.8 MB/s eta 0:00:00
Requirement already satisfied: cuda-python<13.0a0,>=12.0 in /usr/local/lib/python3.10/dist-packages (from cuvs-cu12) (12.2.1)
Requirement already satisfied: numpy<2.0a0,>=1.23 in /usr/local/lib/python3.10/dist-packages (from cuvs-cu12) (1.26.4)
Collecting pylibraft-cu12==24.8.* (from cuvs-cu12)
Using cached https://pypi.nvidia.com/pylibraft-cu12/pylibraft_cu12-24.8.1-cp310-cp310-manylinux_2_28_x86_64.whl (783.8 MB)
Collecting rmm-cu12==24.8.* (from pylibraft-cu12==24.8.*->cuvs-cu12)
Downloading https://pypi.nvidia.com/rmm-cu12/rmm_cu12-24.8.2-cp310-cp310-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl (1.7 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.7/1.7 MB 33.4 MB/s eta 0:00:00
Requirement already satisfied: numba>=0.57 in /usr/local/lib/python3.10/dist-packages (from rmm-cu12==24.8.*->pylibraft-cu12==24.8.*->cuvs-cu12) (0.60.0)
Requirement already satisfied: cython in /usr/local/lib/python3.10/dist-packages (from cuda-python<13.0a0,>=12.0->cuvs-cu12) (3.0.11)
Requirement already satisfied: llvmlite<0.44,>=0.43.0dev0 in /usr/local/lib/python3.10/dist-packages (from numba>=0.57->rmm-cu12==24.8.*->pylibraft-cu12==24.8.*->cuvs-cu12) (0.43.0)
Installing collected packages: rmm-cu12, pylibraft-cu12, cuvs-cu12
Attempting uninstall: rmm-cu12
Found existing installation: rmm-cu12 24.4.0
Uninstalling rmm-cu12-24.4.0:
Successfully uninstalled rmm-cu12-24.4.0
ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
cudf-cu12 24.4.1 requires rmm-cu12==24.4.*, but you have rmm-cu12 24.8.2 which is incompatible.
Successfully installed cuvs-cu12-24.8.0 pylibraft-cu12-24.8.1 rmm-cu12-24.8.2
Collecting cupy==13.2.0
Downloading cupy-13.2.0.tar.gz (3.5 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 3.5/3.5 MB 46.9 MB/s eta 0:00:00
Preparing metadata (setup.py) ... done
Requirement already satisfied: numpy<2.3,>=1.22 in /usr/local/lib/python3.10/dist-packages (from cupy==13.2.0) (1.26.4)
Requirement already satisfied: fastrlock>=0.5 in /usr/local/lib/python3.10/dist-packages (from cupy==13.2.0) (0.8.2)
Building wheels for collected packages: cupy
error: subprocess-exited-with-error
× python setup.py bdist_wheel did not run successfully.
│ exit code: 1
╰─> See above for output.
note: This error originates from a subprocess, and is likely not a problem with pip.
Building wheel for cupy (setup.py) ... error
ERROR: Failed building wheel for cupy
Running setup.py clean for cupy
Failed to build cupy
ERROR: ERROR: Failed to build installable wheels for some pyproject.toml based projects (cupy)
Collecting sentence-transformers==3.0.1
Using cached sentence_transformers-3.0.1-py3-none-any.whl.metadata (10 kB)
Requirement already satisfied: transformers<5.0.0,>=4.34.0 in /usr/local/lib/python3.10/dist-packages (from sentence-transformers==3.0.1) (4.42.4)
Requirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from sentence-transformers==3.0.1) (4.66.5)
Requirement already satisfied: torch>=1.11.0 in /usr/local/lib/python3.10/dist-packages (from sentence-transformers==3.0.1) (2.3.1+cu121)
Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from sentence-transformers==3.0.1) (1.26.4)
Requirement already satisfied: scikit-learn in /usr/local/lib/python3.10/dist-packages (from sentence-transformers==3.0.1) (1.3.2)
Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from sentence-transformers==3.0.1) (1.13.1)
Requirement already satisfied: huggingface-hub>=0.15.1 in /usr/local/lib/python3.10/dist-packages (from sentence-transformers==3.0.1) (0.23.5)
Requirement already satisfied: Pillow in /usr/local/lib/python3.10/dist-packages (from sentence-transformers==3.0.1) (9.4.0)
Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.15.1->sentence-transformers==3.0.1) (3.15.4)
Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.15.1->sentence-transformers==3.0.1) (2024.6.1)
Requirement already satisfied: packaging>=20.9 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.15.1->sentence-transformers==3.0.1) (24.1)
Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.15.1->sentence-transformers==3.0.1) (6.0.1)
Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.15.1->sentence-transformers==3.0.1) (2.32.3)
Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.15.1->sentence-transformers==3.0.1) (4.12.2)
Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch>=1.11.0->sentence-transformers==3.0.1) (1.13.1)
Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.11.0->sentence-transformers==3.0.1) (3.3)
Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.11.0->sentence-transformers==3.0.1) (3.1.4)
Collecting nvidia-cuda-nvrtc-cu12==12.1.105 (from torch>=1.11.0->sentence-transformers==3.0.1)
Using cached nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)
Collecting nvidia-cuda-runtime-cu12==12.1.105 (from torch>=1.11.0->sentence-transformers==3.0.1)
Using cached nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)
Collecting nvidia-cuda-cupti-cu12==12.1.105 (from torch>=1.11.0->sentence-transformers==3.0.1)
Using cached nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl.metadata (1.6 kB)
Collecting nvidia-cudnn-cu12==8.9.2.26 (from torch>=1.11.0->sentence-transformers==3.0.1)
Using cached nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl.metadata (1.6 kB)
Collecting nvidia-cublas-cu12==12.1.3.1 (from torch>=1.11.0->sentence-transformers==3.0.1)
Using cached nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)
Collecting nvidia-cufft-cu12==11.0.2.54 (from torch>=1.11.0->sentence-transformers==3.0.1)
Using cached nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)
Collecting nvidia-curand-cu12==10.3.2.106 (from torch>=1.11.0->sentence-transformers==3.0.1)
Using cached nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)
Collecting nvidia-cusolver-cu12==11.4.5.107 (from torch>=1.11.0->sentence-transformers==3.0.1)
Using cached nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl.metadata (1.6 kB)
Collecting nvidia-cusparse-cu12==12.1.0.106 (from torch>=1.11.0->sentence-transformers==3.0.1)
Using cached nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl.metadata (1.6 kB)
Collecting nvidia-nccl-cu12==2.20.5 (from torch>=1.11.0->sentence-transformers==3.0.1)
Using cached nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_x86_64.whl.metadata (1.8 kB)
Collecting nvidia-nvtx-cu12==12.1.105 (from torch>=1.11.0->sentence-transformers==3.0.1)
Using cached nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl.metadata (1.7 kB)
Requirement already satisfied: triton==2.3.1 in /usr/local/lib/python3.10/dist-packages (from torch>=1.11.0->sentence-transformers==3.0.1) (2.3.1)
Collecting nvidia-nvjitlink-cu12 (from nvidia-cusolver-cu12==11.4.5.107->torch>=1.11.0->sentence-transformers==3.0.1)
Using cached nvidia_nvjitlink_cu12-12.6.20-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)
Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers<5.0.0,>=4.34.0->sentence-transformers==3.0.1) (2024.5.15)
Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.10/dist-packages (from transformers<5.0.0,>=4.34.0->sentence-transformers==3.0.1) (0.4.4)
Requirement already satisfied: tokenizers<0.20,>=0.19 in /usr/local/lib/python3.10/dist-packages (from transformers<5.0.0,>=4.34.0->sentence-transformers==3.0.1) (0.19.1)
Requirement already satisfied: joblib>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from scikit-learn->sentence-transformers==3.0.1) (1.4.2)
Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn->sentence-transformers==3.0.1) (3.5.0)
Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch>=1.11.0->sentence-transformers==3.0.1) (2.1.5)
Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub>=0.15.1->sentence-transformers==3.0.1) (3.3.2)
Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub>=0.15.1->sentence-transformers==3.0.1) (3.7)
Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub>=0.15.1->sentence-transformers==3.0.1) (2.0.7)
Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub>=0.15.1->sentence-transformers==3.0.1) (2024.7.4)
Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from sympy->torch>=1.11.0->sentence-transformers==3.0.1) (1.3.0)
Using cached sentence_transformers-3.0.1-py3-none-any.whl (227 kB)
Using cached nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl (410.6 MB)
Using cached nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (14.1 MB)
Using cached nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (23.7 MB)
Using cached nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (823 kB)
Using cached nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl (731.7 MB)
Using cached nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl (121.6 MB)
Using cached nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl (56.5 MB)
Using cached nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl (124.2 MB)
Using cached nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl (196.0 MB)
Using cached nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_x86_64.whl (176.2 MB)
Using cached nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (99 kB)
Using cached nvidia_nvjitlink_cu12-12.6.20-py3-none-manylinux2014_x86_64.whl (19.7 MB)
Installing collected packages: nvidia-nvtx-cu12, nvidia-nvjitlink-cu12, nvidia-nccl-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, nvidia-cusparse-cu12, nvidia-cudnn-cu12, nvidia-cusolver-cu12, sentence-transformers
Successfully installed nvidia-cublas-cu12-12.1.3.1 nvidia-cuda-cupti-cu12-12.1.105 nvidia-cuda-nvrtc-cu12-12.1.105 nvidia-cuda-runtime-cu12-12.1.105 nvidia-cudnn-cu12-8.9.2.26 nvidia-cufft-cu12-11.0.2.54 nvidia-curand-cu12-10.3.2.106 nvidia-cusolver-cu12-11.4.5.107 nvidia-cusparse-cu12-12.1.0.106 nvidia-nccl-cu12-2.20.5 nvidia-nvjitlink-cu12-12.6.20 nvidia-nvtx-cu12-12.1.105 sentence-transformers-3.0.1
Dataset
[3]
--2024-08-08 21:19:52-- https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/nfcorpus.zip Resolving public.ukp.informatik.tu-darmstadt.de (public.ukp.informatik.tu-darmstadt.de)... 130.83.167.186 Connecting to public.ukp.informatik.tu-darmstadt.de (public.ukp.informatik.tu-darmstadt.de)|130.83.167.186|:443... connected. HTTP request sent, awaiting response... 200 OK Length: 2448432 (2.3M) [application/zip] Saving to: ‘nfcorpus.zip’ nfcorpus.zip 100%[===================>] 2.33M 2.27MB/s in 1.0s 2024-08-08 21:19:54 (2.27 MB/s) - ‘nfcorpus.zip’ saved [2448432/2448432]
[4]
Archive: nfcorpus.zip creating: nfcorpus/ creating: nfcorpus/qrels/ inflating: nfcorpus/qrels/train.tsv inflating: nfcorpus/qrels/test.tsv inflating: nfcorpus/qrels/dev.tsv inflating: nfcorpus/corpus.jsonl inflating: nfcorpus/queries.jsonl
[5]
3633
[6]
3237
[7]
/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_token.py:89: UserWarning: The secret `HF_TOKEN` does not exist in your Colab secrets. To authenticate with the Hugging Face Hub, create a token in your settings tab (https://huggingface.co/settings/tokens), set it as secret in your Google Colab and restart your session. You will be able to reuse this secret in all of your notebooks. Please note that authentication is recommended but still optional to access public models or datasets. warnings.warn(
config.json: 0%| | 0.00/615 [00:00<?, ?B/s]
model.safetensors: 0%| | 0.00/133M [00:00<?, ?B/s]
tokenizer_config.json: 0%| | 0.00/352 [00:00<?, ?B/s]
vocab.txt: 0%| | 0.00/232k [00:00<?, ?B/s]
tokenizer.json: 0%| | 0.00/466k [00:00<?, ?B/s]
special_tokens_map.json: 0%| | 0.00/112 [00:00<?, ?B/s]
WARNING:sentence_transformers.SentenceTransformer:No sentence-transformers model found with name all-MiniLM-L12-v2. Creating a new one with mean pooling.
[8]
[9]
[13]
CPU times: user 926 ms, sys: 330 ms, total: 1.26 s Wall time: 1.73 s
[18]
[19]
Results (after 0.001 seconds): Input question: What does taking supplemental B12 vitamins help with? CAGRA Search Results: 20.404 Vitamin B12 deficiency anemia may have psychiatric manifestations preceding the hematological symptoms. Although a variety of symptoms are described, there are only sparse data on the role of vitamin B12 in depression. We report a case of vitamin B12 deficiency presenting with recurrent episodes of depression. 20.468 Elevated total plasma homocysteine has been linked to the development of cognitive impairment and dementia in later life and this can be reliably lowered by the daily supplementation of vitamin B6, B12, and folic acid. We performed a systematic review and meta-analysis of 19 English language randomized, placebo-controlled trials of homocysteine lowering B-vitamin supplementation of individuals with and without cognitive impairment at the time of study entry. We standardized scores to facilitate comparison between studies and to enable us to complete a meta-analysis of randomized trials. In addition, we stratified our analyses according to the folate status of the country of origin. B-vitamin supplementation did not show an improvement in cognitive function for individuals with (SMD = 0.10, 95%CI -0.08 to 0.28) or without (SMD = -0.03, 95%CI -0.1 to 0.04) significant cognitive impairment. This was irrespective of study duration (SMD = 0.05, 95%CI -0.10 to 0.20 and SMD = 0, 95%CI -0.08 to 0.08), study size (SMD = 0.05, 95%CI -0.09 to 0.19 and SMD = -0.02, 95%CI -0.10 to 0.05), and whether participants came from countries with low folate status (SMD = 0.14, 95%CI -0.12 to 0.40 and SMD = -0.10, 95%CI -0.23 to 0.04). Supplementation of vitamins B12, B6, and folic acid alone or in combination does not appear to improve cognitive function in individuals with or without existing cognitive impairment. It remains to be established if prolonged treatment with B-vitamins can reduce the risk of dementia in later life. 21.161 BACKGROUND: Pure vegetarian diets might cause cobalamin deficiency due to lack of dietary intake. It was hypothesized that a population following a vegan diet consuming mostly raw fruits and vegetables, carrot juice, and dehydrated barley grass juice would be able to avoid vitamin B12 deficiency naturally. METHODS: Subjects were recruited at a health ministers' reunion based on adherence to the Hallelujah diet for at least 2 years. Serum cobalamin and urinary methylmalonic acid (MMA) assays were performed. Follow-up with sublingual tablets, nutritional yeast, or probiotic supplements was carried out on subjects with abnormal MMA results. RESULTS: 49 subjects were tested. Most subjects (10th to 90th percentile) had followed this diet 23-49 months. 6 subjects had serum B12 concentrations <147 pmol/l (200 pg/ml). 37 subjects (76%) had serum B12 concentrations <221 pmol/l (300 pg/ml). 23 subjects (47%) had abnormal urinary MMA concentrations above or equal to 4.0 microg/mg creatinine. Sublingual cyanocobalamin and nutritional yeast, but not probiotic supplements, significantly reduced group mean MMA concentrations (tablet p < 0.01; yeast p < 0.05, probiotic > 0.20). CONCLUSIONS: The urinary MMA assay is effective for identifying early metabolic cobalamin deficiency. People following the Hallelujah diet and other raw-food vegetarian diets should regularly monitor their urinary MMA levels, consume a sublingual cobalamin supplement, or consume cobalamin in their food. 21.611 AIMS: Serum cobalamin (cbl, vitamin B(12)) tests are routinely ordered for investigating conditions potentially amenable to cbl supplementation. This study aimed to systematically assess the evidence of diagnostic accuracy for serum cbl tests across patient subgroups. METHODS: Seven medical databases were searched (1990 to November 2009). Studies were included that compared serum cbl to a reference standard (all reference standards employed). Study quality was assessed using QUADAS. Summary estimates of test performance were determined using the bivariate model and hierarchical summary receiver operating characteristic curves (HSROC). RESULTS: Of 2878 identified studies, 54 were included. Studies rated poorly against QUADAS criteria. Positive (PLR) and negative likelihood ratios (NLR) were 2.72 [95% confidence interval (CI) 1.95, 3.81] and 0.59 (0.49, 0.72), respectively (studies employing methylmalonic acid as the referent). In studies employing a clinical reference standard, PLR was 3.33 (0.92, 12.10) and NLR 0.34 (0.13, 0.89). Test performance did not vary by clinical indication, test method or age. CONCLUSION: This review was limited by the quality of the evidence base and lack of a gold standard. From the available evidence, diagnosis of conditions amenable to cbl supplementation on the basis of serum cbl level alone cannot be considered a reliable approach to investigating suspected vitamin deficiency. 21.734 BACKGROUND: Vitamin B(12) deficiency can occur in individuals with dietary patterns that exclude animal foods and patients who are unable to absorb vitamin B(12 )in food. MATERIAL AND METHOD: Our clinic serves a high-income population living in Southern Israel. We hypothesize that a tendency to decrease of level of vitamin B(12) in our population is caused by a premeditated decrease in consumption of animal products. We analyzed 512 medical histories of patients undergoing blood tests for vitamin B(12) level for various reasons. RESULT: The level of vitamin B(12) in 192 patients (37.5%) was less than 250 pg/ml. CONCLUSION: As a result of media information disseminating the relationship between meat, cholesterol and cardiovascular diseases, consumption of meat, particularly beef, has decreased. Changes in life style among segments of the population with high socioeconomic level, on one hand, and the existence of poverty, on the other, are two main factors in the decreasing consumption of animal products. This causes a decrease in the level of vitamin B(12) in the general population, and as a consequence, this will increase pathology due to vitamin B(12) deficiency. In lieu of these possible developments and in order to prevent serious health problems, vitamin B(12) fortification should be seriously considered and discussed. (c) 2007 S. Karger AG, Basel. CPU times: user 26.6 ms, sys: 0 ns, total: 26.6 ms Wall time: 32.9 ms
[ ]