fastembed-gpu 0.5.1__py3-none-any.whl

fastembed_gpu-0.5.1.dist-info/METADATA

@@ -0,0 +1,262 @@
+Metadata-Version: 2.3
+Name: fastembed-gpu
+Version: 0.5.1
+Summary: Fast, light, accurate library built for retrieval embedding generation
+License: Apache License
+Keywords: vector,embedding,neural,search,qdrant,sentence-transformers
+Author: Qdrant Team
+Author-email: info@qdrant.tech
+Requires-Python: >=3.9.0
+Classifier: License :: Other/Proprietary License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Dist: huggingface-hub (>=0.20,<1.0)
+Requires-Dist: loguru (>=0.7.2,<0.8.0)
+Requires-Dist: mmh3 (>=4.1.0,<5.0.0)
+Requires-Dist: numpy (>=1.21) ; python_version >= "3.10" and python_version < "3.12"
+Requires-Dist: numpy (>=1.21,<2.1.0) ; python_version < "3.10"
+Requires-Dist: numpy (>=1.26) ; python_version >= "3.12" and python_version < "3.13"
+Requires-Dist: numpy (>=2.1.0) ; python_version >= "3.13"
+Requires-Dist: onnxruntime-gpu (>1.20.0) ; python_version >= "3.13"
+Requires-Dist: onnxruntime-gpu (>=1.17.0,!=1.20.0) ; python_version >= "3.10" and python_version < "3.13"
+Requires-Dist: onnxruntime-gpu (>=1.17.0,<1.20.0) ; python_version < "3.10"
+Requires-Dist: pillow (>=10.3.0,<11.0.0)
+Requires-Dist: py-rust-stemmers (>=0.1.0,<0.2.0)
+Requires-Dist: requests (>=2.31,<3.0)
+Requires-Dist: tokenizers (>=0.15,<1.0)
+Requires-Dist: tqdm (>=4.66,<5.0)
+Project-URL: Homepage, https://github.com/qdrant/fastembed
+Project-URL: Repository, https://github.com/qdrant/fastembed
+Description-Content-Type: text/markdown
+
+# ⚡️ What is FastEmbed?
+
+FastEmbed is a lightweight, fast, Python library built for embedding generation. We [support popular text models](https://qdrant.github.io/fastembed/examples/Supported_Models/). Please [open a GitHub issue](https://github.com/qdrant/fastembed/issues/new) if you want us to add a new model.
+
+The default text embedding (`TextEmbedding`) model is Flag Embedding, presented in the [MTEB](https://huggingface.co/spaces/mteb/leaderboard) leaderboard. It supports "query" and "passage" prefixes for the input text. Here is an example for [Retrieval Embedding Generation](https://qdrant.github.io/fastembed/qdrant/Retrieval_with_FastEmbed/) and how to use [FastEmbed with Qdrant](https://qdrant.github.io/fastembed/qdrant/Usage_With_Qdrant/).
+
+## 📈 Why FastEmbed?
+
+1. Light: FastEmbed is a lightweight library with few external dependencies. We don't require a GPU and don't download GBs of PyTorch dependencies, and instead use the ONNX Runtime. This makes it a great candidate for serverless runtimes like AWS Lambda. 
+
+2. Fast: FastEmbed is designed for speed. We use the ONNX Runtime, which is faster than PyTorch. We also use data parallelism for encoding large datasets.
+
+3. Accurate: FastEmbed is better than OpenAI Ada-002. We also [support](https://qdrant.github.io/fastembed/examples/Supported_Models/) an ever-expanding set of models, including a few multilingual models.
+
+## 🚀 Installation
+
+To install the FastEmbed library, pip works best. You can install it with or without GPU support:
+
+```bash
+pip install fastembed
+
+# or with GPU support
+
+pip install fastembed-gpu
+```
+
+## 📖 Quickstart
+
+```python
+from fastembed import TextEmbedding
+
+
+# Example list of documents
+documents: list[str] = [
+    "This is built to be faster and lighter than other embedding libraries e.g. Transformers, Sentence-Transformers, etc.",
+    "fastembed is supported by and maintained by Qdrant.",
+]
+
+# This will trigger the model download and initialization
+embedding_model = TextEmbedding()
+print("The model BAAI/bge-small-en-v1.5 is ready to use.")
+
+embeddings_generator = embedding_model.embed(documents)  # reminder this is a generator
+embeddings_list = list(embedding_model.embed(documents))
+  # you can also convert the generator to a list, and that to a numpy array
+len(embeddings_list[0]) # Vector of 384 dimensions
+```
+
+Fastembed supports a variety of models for different tasks and modalities.
+The list of all the available models can be found [here](https://qdrant.github.io/fastembed/examples/Supported_Models/)
+### 🎒 Dense text embeddings
+
+```python
+from fastembed import TextEmbedding
+
+model = TextEmbedding(model_name="BAAI/bge-small-en-v1.5")
+embeddings = list(model.embed(documents))
+
+# [
+#   array([-0.1115,  0.0097,  0.0052,  0.0195, ...], dtype=float32),
+#   array([-0.1019,  0.0635, -0.0332,  0.0522, ...], dtype=float32)
+# ]
+
+```
+
+
+
+### 🔱 Sparse text embeddings
+
+* SPLADE++
+
+```python
+from fastembed import SparseTextEmbedding
+
+model = SparseTextEmbedding(model_name="prithivida/Splade_PP_en_v1")
+embeddings = list(model.embed(documents))
+
+# [
+#   SparseEmbedding(indices=[ 17, 123, 919, ... ], values=[0.71, 0.22, 0.39, ...]),
+#   SparseEmbedding(indices=[ 38,  12,  91, ... ], values=[0.11, 0.22, 0.39, ...])
+# ]
+```
+
+<!--
+* BM42 - ([link](ToDo))
+
+```
+from fastembed import SparseTextEmbedding
+
+model = SparseTextEmbedding(model_name="Qdrant/bm42-all-minilm-l6-v2-attentions")
+embeddings = list(model.embed(documents))
+
+# [
+#   SparseEmbedding(indices=[ 17, 123, 919, ... ], values=[0.71, 0.22, 0.39, ...]),
+#   SparseEmbedding(indices=[ 38,  12,  91, ... ], values=[0.11, 0.22, 0.39, ...])
+# ]
+```
+-->
+
+### 🦥 Late interaction models (aka ColBERT)
+
+
+```python
+from fastembed import LateInteractionTextEmbedding
+
+model = LateInteractionTextEmbedding(model_name="colbert-ir/colbertv2.0")
+embeddings = list(model.embed(documents))
+
+# [
+#   array([
+#       [-0.1115,  0.0097,  0.0052,  0.0195, ...],
+#       [-0.1019,  0.0635, -0.0332,  0.0522, ...],
+#   ]),
+#   array([
+#       [-0.9019,  0.0335, -0.0032,  0.0991, ...],
+#       [-0.2115,  0.8097,  0.1052,  0.0195, ...],
+#   ]),  
+# ]
+```
+
+### 🖼️ Image embeddings
+
+```python
+from fastembed import ImageEmbedding
+
+images = [
+    "./path/to/image1.jpg",
+    "./path/to/image2.jpg",
+]
+
+model = ImageEmbedding(model_name="Qdrant/clip-ViT-B-32-vision")
+embeddings = list(model.embed(images))
+
+# [
+#   array([-0.1115,  0.0097,  0.0052,  0.0195, ...], dtype=float32),
+#   array([-0.1019,  0.0635, -0.0332,  0.0522, ...], dtype=float32)
+# ]
+```
+
+### 🔄 Rerankers
+```python
+from fastembed.rerank.cross_encoder import TextCrossEncoder
+
+query = "Who is maintaining Qdrant?"
+documents: list[str] = [
+    "This is built to be faster and lighter than other embedding libraries e.g. Transformers, Sentence-Transformers, etc.",
+    "fastembed is supported by and maintained by Qdrant.",
+]
+encoder = TextCrossEncoder(model_name="Xenova/ms-marco-MiniLM-L-6-v2")
+scores = list(encoder.rerank(query, documents))
+
+# [-11.48061752319336, 5.472434997558594]
+```
+
+## ⚡️ FastEmbed on a GPU
+
+FastEmbed supports running on GPU devices.
+It requires installation of the `fastembed-gpu` package.
+
+```bash
+pip install fastembed-gpu
+```
+
+Check our [example](https://qdrant.github.io/fastembed/examples/FastEmbed_GPU/) for detailed instructions, CUDA 12.x support and troubleshooting of the common issues.
+
+```python
+from fastembed import TextEmbedding
+
+embedding_model = TextEmbedding(
+    model_name="BAAI/bge-small-en-v1.5", 
+    providers=["CUDAExecutionProvider"]
+)
+print("The model BAAI/bge-small-en-v1.5 is ready to use on a GPU.")
+
+```
+
+## Usage with Qdrant
+
+Installation with Qdrant Client in Python:
+
+```bash
+pip install qdrant-client[fastembed]
+```
+
+or 
+
+```bash
+pip install qdrant-client[fastembed-gpu]
+```
+
+You might have to use quotes ```pip install 'qdrant-client[fastembed]'``` on zsh.
+
+```python
+from qdrant_client import QdrantClient
+
+# Initialize the client
+client = QdrantClient("localhost", port=6333) # For production
+# client = QdrantClient(":memory:") # For small experiments
+
+# Prepare your documents, metadata, and IDs
+docs = ["Qdrant has Langchain integrations", "Qdrant also has Llama Index integrations"]
+metadata = [
+    {"source": "Langchain-docs"},
+    {"source": "Llama-index-docs"},
+]
+ids = [42, 2]
+
+# If you want to change the model:
+# client.set_model("sentence-transformers/all-MiniLM-L6-v2")
+# List of supported models: https://qdrant.github.io/fastembed/examples/Supported_Models
+
+# Use the new add() instead of upsert()
+# This internally calls embed() of the configured embedding model
+client.add(
+    collection_name="demo_collection",
+    documents=docs,
+    metadata=metadata,
+    ids=ids
+)
+
+search_result = client.query(
+    collection_name="demo_collection",
+    query_text="This is a query document"
+)
+print(search_result)
+```
+

fastembed_gpu-0.5.1.dist-info/NOTICE

@@ -0,0 +1,14 @@
+Copyright 2024 Qdrant
+
+This product includes software developed by Qdrant
+
+This distribution includes the following Jina AI models, each with its respective license:
+- jinaai/jina-colbert-v2
+    - License: cc-by-nc-4.0
+- jinaai/jina-reranker-v2-base-multilingual
+    - License: cc-by-nc-4.0
+
+These models are developed by Jina (https://jina.ai/) and are subject to Jina AI's licensing terms.
+
+Additional Notes:
+This project also includes third-party libraries with their respective licenses. Please refer to the documentation of each library for details regarding its usage and licensing terms.

fastembed_gpu-0.5.1.dist-info/RECORD

@@ -0,0 +1,47 @@
+fastembed/__init__.py,sha256=yvbEcZ02gISaHABht6wKK-vNrXKJs_w0dNPJzU6ZJCw,582
+fastembed/common/__init__.py,sha256=iD2VNgUkOTWLDtqrM3m5ZO_cMv4uqJ2hmEoGOYfU2h8,148
+fastembed/common/model_management.py,sha256=M_CZ3qEHRr7ODlhLHhBu9421tTUzzoD8M7neUjW8GNw,10752
+fastembed/common/onnx_model.py,sha256=XlUVmIjW-JuCeNtyCQ-hWWszMLUAQ8yCnx4MA4Q8634,4681
+fastembed/common/preprocessor_utils.py,sha256=7AtbogjuKUqOJjpLV_rbPHBdHRB8gje2HrewQGj0Nek,3174
+fastembed/common/types.py,sha256=MKNVj2YEHnNgea0QYWTHsYs_AYdZ6E29-xW0fnnBMDw,450
+fastembed/common/utils.py,sha256=PXGYQC3FzAQZXZAeAkN_cWj4KWVH4GdP5q9TBT5EfHQ,1539
+fastembed/embedding.py,sha256=HeG031cG03UebIstWRDxjYwCq3oqK_JHFHlyeMAroSw,604
+fastembed/image/__init__.py,sha256=YQ3NHSIW1ufR5iEaBzzJ1cVeOIFE5O6TpfdNKtWrbvg,89
+fastembed/image/image_embedding.py,sha256=svqrJn0Jp8mw2SMp0F6ZHek8NI1oNpJiDu5nZgu6olo,3565
+fastembed/image/image_embedding_base.py,sha256=zf5jYw9TEQbu-4eaQLBF_NFLya52KUU8ZO--Zxhvb18,1408
+fastembed/image/onnx_embedding.py,sha256=Jx48aS55sKHlJTkIWVeJNxCmSRaoAevs1iFLARUQEyk,7691
+fastembed/image/onnx_image_model.py,sha256=AgQyeYd_nteXeyXqhOiJysgph5h7CXf2nCcBLOMgtuQ,4570
+fastembed/image/transform/functional.py,sha256=Uk1Ps3w0FYMVHoBVpngt881oILCUvPLeeesVhvjkir8,4296
+fastembed/image/transform/operators.py,sha256=1Amzd-OlYLKZ_BZb60JbMtbgoxqFz98mHJRiMFMOCIw,9854
+fastembed/late_interaction/__init__.py,sha256=-Bi1ZtgzgpbFm9bpd5V3QcJROF4cOgyiZlEHl--zQSg,153
+fastembed/late_interaction/colbert.py,sha256=Zkjw6_jj2ubWosMtd2RX-Xb2dvbNjIwCelHQ_3dk0EM,10292
+fastembed/late_interaction/jina_colbert.py,sha256=flmLSbFtR3wJikN9s4_eaW4EQL5dffl2F7VpZxxznlc,1959
+fastembed/late_interaction/late_interaction_embedding_base.py,sha256=U_yrFurIX_CC2KdKjprCxtksxNSH1ywmsBqsW_ovrs8,1919
+fastembed/late_interaction/late_interaction_text_embedding.py,sha256=B_tW1wMwbu9IyEQ-1jh3DP5zcbaZ3HGqYrOcaK34B10,4217
+fastembed/parallel_processor.py,sha256=A050kBiKlfGGAc3-jB7fhUpCY5kEChFtR9ynaeYvYzk,9045
+fastembed/rerank/cross_encoder/__init__.py,sha256=3AS7tS1WALEOJmNId9Xxk1BwI-x0fJKHFSVyJpSJvkc,111
+fastembed/rerank/cross_encoder/onnx_text_cross_encoder.py,sha256=aLCyDbkogwQ53fYODaB3azkUj4BJinXaqsCYks908vk,8384
+fastembed/rerank/cross_encoder/onnx_text_model.py,sha256=UwWPrTwNj8UamYN6sTLjGzBK2yhJWqfG7MFTOJ5WzmA,5445
+fastembed/rerank/cross_encoder/text_cross_encoder.py,sha256=m3Rcnoim95ms5RTPMyxRIFX5EA3xI7fLwFqtnub4JFY,4702
+fastembed/rerank/cross_encoder/text_cross_encoder_base.py,sha256=XP7XRnM2bgPhqFQYIF_FLWKguNHZrR3YCulvDctP-0o,2121
+fastembed/sparse/__init__.py,sha256=GeUoN_fpiBPoqkO1cOITxf8po0lVdcPV07CEfELsUI0,192
+fastembed/sparse/bm25.py,sha256=JYvXGg2-_M2cFjddGicM442JR5YGDh0_l8jWb_2KGTk,11571
+fastembed/sparse/bm42.py,sha256=p1o9IrJc0skwqHwlyRsn3oPcc9nkteD9rclc6ygXrVs,13288
+fastembed/sparse/sparse_embedding_base.py,sha256=pBDgKmLd90h3ShAdi0pOzUE3OdHhSibFIPmQYpL9mo4,2607
+fastembed/sparse/sparse_text_embedding.py,sha256=RCLqNZQy_VLT441cZniA4l-ris0yse141rzBvkrBrFw,4466
+fastembed/sparse/splade_pp.py,sha256=hc67-oB-_TyG-2LawBmH6E0aibZ1Y_I2vryTtjOtNvo,7041
+fastembed/sparse/utils/tokenizer.py,sha256=5bgI72YyqolTYufXxsCiuZP1jcIXMqD1oCaNaAxrPwY,3868
+fastembed/text/__init__.py,sha256=5_J8_ASHoG-LrVFvJ_F5ow56PHv5i9j4sziAyxMqKdk,85
+fastembed/text/clip_embedding.py,sha256=xbqj508dXXdKoaby15s4Y7xFndw1A6fKGLDDiOGwPBQ,1611
+fastembed/text/e5_onnx_embedding.py,sha256=F_uJD3OL5VMpT5QcmZhioyBwBPB1DRn9kWQgyQ8lGoQ,2361
+fastembed/text/onnx_embedding.py,sha256=0sonH355K7zvXuxXE9I7BlHMWFQButiRngLxin0WUek,13186
+fastembed/text/onnx_text_model.py,sha256=ZRwAhSB4rsM9KhNq6pbZZgkfgndDNbqtKzNrhrQduvc,5169
+fastembed/text/pooled_embedding.py,sha256=h91VqsEaAkb0sSdEJqvvYNWaF7lh8vBCT2How5aA4eU,3390
+fastembed/text/pooled_normalized_embedding.py,sha256=ZdWNYVswdyn9z2RGfMKhPJTM3EW3V1ou70w09sh3Hiw,5189
+fastembed/text/text_embedding.py,sha256=fGw07_vabsuEdC6r1tJUaDvD-fuc05YGaW1vWf0ir1w,4130
+fastembed/text/text_embedding_base.py,sha256=eMz-3FOSv8gP2eRylAtfJD-Duc6n7lbZQEw7giY61gM,1904
+fastembed_gpu-0.5.1.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+fastembed_gpu-0.5.1.dist-info/METADATA,sha256=HUPqlLMn4Ut2zamUYyVknpvmhGCc32_J42LG8n2S2xQ,8538
+fastembed_gpu-0.5.1.dist-info/NOTICE,sha256=9YiH-TydSDnhGoP8pxZZpHa0kdEEoeAfggFq9qO4TmM,595
+fastembed_gpu-0.5.1.dist-info/WHEEL,sha256=IYZQI976HJqqOpQU6PHkJ8fb3tMNBFjg-Cn-pwAbaFM,88
+fastembed_gpu-0.5.1.dist-info/RECORD,,

fastembed_gpu-0.5.1.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: poetry-core 2.0.1
+Root-Is-Purelib: true
+Tag: py3-none-any