27 results found Sort:

iterative
dvc iterative
1.2k
13.9k
apache-2.0
136
🦉 Data Versioning and ML Experiments
ai data-science developer-tools reproducibility machine-learning unstructured-data data-version-control
Created 2017-03-04
9,355 commits to main branch, last one a day ago
voxel51
fiftyone voxel51
558
8.8k
apache-2.0
60
Refine high-quality datasets and visual AI models
python data-quality data-science data-cleaning data-curation deep-learning vector-search visualization active-learning computer-vision data-centric-ai developer-tools machine-learning object-detection unstructured-data image-classification artificial-intelligence
Created 2020-04-22
21,609 commits to develop branch, last one 8 hours ago
towhee-io
towhee towhee-io
248
3.2k
apache-2.0
29
Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.
llm vit milvus towhee pipeline embeddings transformer feature-vector computer-vision image-retrieval image-processing machine-learning video-processing embedding-vectors unstructured-data feature-extraction vision-transformer convolutional-networks
Created 2021-07-13
1,586 commits to main branch, last one 20 days ago
Zipstack
unstract Zipstack
150
2.4k
agpl-3.0
21
No-code LLM Platform to launch APIs and ETL Pipelines to structure unstructured documents
etl-pipeline llm-platform unstructured-data
Created 2024-02-21
763 commits to main branch, last one 23 hours ago
neo4j-labs
llm-graph-builder neo4j-labs
372
2.3k
apache-2.0
26
Neo4j graph construction from unstructured data using LLMs
rag genai graph neo4j graphdb graphrag vectordb graph-rag langchain data-import graph-search knowledge-graph unstructured-data
Created 2024-01-11
1,302 commits to main branch, last one 9 days ago
instill-ai
instill-core instill-ai
105
2.1k
other
30
🔮 Instill Core is a full-stack AI infrastructure tool for data, model and pipeline orchestration, designed to streamline every aspect of building versatile AI-first applications
ai api cli etl gpt llm golang python no-code low-code pipeline typescript open-source generative-ai hacktoberfest developer-tools stable-diffusion unstructured-data
Created 2022-01-13
837 commits to main branch, last one a day ago
milvus-io
bootcamp milvus-io
577
1.9k
apache-2.0
35
Dealing with all unstructured data, such as reverse image search, audio search, molecular search, video analysis, question and answer systems, NLP, etc.
nlp milvus python audio-search image-search deep-learning hacktoberfest benchmark-testing image-recognition unstructured-data question-answering image-classification
Created 2019-08-09
3,280 commits to master branch, last one a day ago
dingodb
dingo dingodb
270
1.6k
apache-2.0
163
A multi-modal vector database that supports upserts and vector queries using unified SQL (MySQL-Compatible) on structured and unstructured data, while meeting the requirements of high concurrency and ...
serving unified-sql vector-ocean embedding-store structured-data vector-database embedding-search unstructured-data mysql-compatibility real-time-semantic-search key-value-distributed-store
Created 2021-10-14
1,218 commits to develop branch, last one 24 hours ago
nomic-ai
nomic nomic-ai
172
1.3k
unknown
28
Interact, analyze and structure massive text, image, embedding, audio and video datasets
text python clustering embeddings topic-modeling unstructured-data duplicate-detection
Created 2022-07-21
1,062 commits to main branch, last one 7 days ago
tstanislawek
awesome-document-understanding tstanislawek
151
1.3k
unknown
37
A curated list of resources for Document Understanding (DU) topic
nlp ocr pdf rpa awesome document-ai awesome-list deep-learning pdf-documents machine-learning document-analysis unstructured-data document-intelligence document-understanding information-extraction intelligent-processing document-layout-analysis key-information-extraction robotic-process-automation natural-language-processing
Created 2021-04-06
76 commits to main branch, last one about a year ago
Renumics
spotlight Renumics
83
1.1k
mit
19
Interactively explore unstructured datasets from your dataframe.
audio video images meshes timeseries data-curation hacktoberfest computer-vision data-centric-ai machine-learning unstructured-data data-visualization exploratory-data-analysis
Created 2023-01-29
1,481 commits to main branch, last one 3 months ago
databricks
lilac databricks
89
953
apache-2.0
13
Curate better data for LLMs
data-analysis dataset-analysis unstructured-data artificial-intelligence
Created 2023-03-23
950 commits to main branch, last one 8 months ago
amphi-ai
amphi-etl amphi-ai
43
889
other
9
Visual Data Transformation with Python Code Generation. Low-Code Python-based ETL.
etl data data-science data-analysis data-pipelines structured-data unstructured-data datatransformation
Created 2024-03-20
221 commits to main branch, last one 21 hours ago
nuclia
nucliadb nuclia
51
661
other
19
NucliaDB, The AI Search database for RAG
rust mlops nuclia python search vectors database semantic search-engine vector-search language-model search-engines machine-learning ai-powered-search unstructured-data text-classification vector-search-engine semantic-search-engine
Created 2022-04-05
2,734 commits to main branch, last one 2 days ago
EulerSearch
embedding_studio EulerSearch
5
377
apache-2.0
6
Embedding Studio is a framework which allows you transform your Vector Database into a feature-rich Search Engine.
embeddings fine-tuning query-parser llm-inference search-engine vector-database search-algorithm unstructured-data search-query-parser semantic-similarity unstructured-search embeddings-similarity
Created 2023-10-31
32 commits to main branch, last one 7 months ago
garyelephant
pygrok garyelephant
74
276
mit
16
python implementation of jordansissel's grok regular expression library
grok python parse-strings unstructured-data extract-information
Created 2014-07-17
93 commits to master branch, last one 6 years ago
fzliu
radient fzliu
11
268
bsd-2-clause
3
Radient turns many data types (not just text) into vectors for similarity search, RAG, regression analysis, and more.
etl text audio graphs images milvus vectors molecules embeddings image-search multimodal-rag fraud-detection semantic-search vector-database molecular-search similarity-search unstructured-data recommender-system unstructured-data-processing retrieval-augmented-generation
Created 2024-02-16
37 commits to main branch, last one about a month ago
automorphic-ai
trex automorphic-ai
8
241
mit
3
Enforce structured output from LLMs 100% of the time
etl llm json regex unstructured-data large-language-models
Created 2023-07-12
1 commits to main branch, last one 3 months ago
RelevanceAI
relevanceai RelevanceAI
24
159
apache-2.0
12
Home of the AI workforce - Multi-agent system, AI agents & tools
nlp python search clustering embeddings search-engine vector-search computer-vision vector-database unstructured-data natural-language-processing
Created 2021-07-05
5,729 commits to main branch, last one 2 days ago
CambioML
any-parser CambioML
7
129
unknown
4
Accurate, private and configurable document retrieval LLM
llm pdf privacy document data-extraction structured-data unstructured-data
Created 2024-03-14
204 commits to main branch, last one 3 days ago
marly-ai
marly marly-ai
7
107
mit
4
The open-source, model-agnostic alternative to OpenAI's structured outputs for your own documents or the web.
ai etl llm rag crewai openai autogen langchain langgraph agent-tools etl-framework etl-automation unstructured-data structured-outputs
Created 2024-07-11
104 commits to master branch, last one 2 days ago
jostmey
dkm jostmey
6
95
other
5
Dynamic Kernel Matching (DKM) for Classifying Data with Non-conforming Features
dkm genomics repertoire tcell-receptors machine-learning unstructured-data nonconforming-data statistical-classifiers
Created 2020-01-01
246 commits to master branch, last one about a year ago
yobix-ai
extractous yobix-ai
5
84
apache-2.0
4
Fast and efficient unstructured data extraction. Written in Rust with bindings for many languages.
etl llm nlp ocr pdf rag docx rust tika extraction pdf-parser unstructured etl-pipelines data-pipelines machine-learning unstructured-data natural-language-processing
Created 2024-06-04
219 commits to main branch, last one 2 days ago
DerwenAI
strwythura DerwenAI
8
83
mit
5
How to construct knowledge graphs from unstructured data sources
nlp textgraphs entity-linking knowledge-graph vector-database machine-learning entity-resolution unstructured-data relation-extraction named-entity-recognition
Created 2024-07-31
18 commits to main branch, last one about a month ago
instill-ai
console instill-ai
10
35
other
11
📺 Instill Console for 🔮 Instill Core: https://github.com/instill-ai/instill-core
ui vdp console no-code frontend vision-ai data-pipeline deep-learning hacktoberfest model-serving data-connector computer-vision structured-data object-detection unstructured-data image-classification versatile-data-pipeline
Created 2022-03-18
1,244 commits to main branch, last one a day ago
ScrapeGraphAI
Scrapontologies ScrapeGraphAI
2
30
mit
1
Python library for Entities, relationships and schemas extraction from documents
ai llm library db-schema documents ontologies documentsearch extract-schema knowledge-graph structured-data unstructured-data automatic-ontologies
Created 2024-08-29
95 commits to main branch, last one 21 days ago
wangxb96
RAG-QA-Generator wangxb96
3
27
apache-2.0
2
RAG-QA-Generator 是一个用于检索增强生成（RAG）系统的自动化知识库构建与管理工具。该工具通过读取文档数据，利用大规模语言模型生成高质量的问答对（QA对），并将这些数据插入数据库中，实现RAG系统知识库的自动化构建和管理。
vector-database unstructured-data question-answering large-language-models retrieval-augmented-generation
Created 2024-07-17
10 commits to main branch, last one about a month ago