AnswerDotAI/ModernBERT
Bringing BERT into modernity via both architecture changes and scaling
Language:Python
Total stars: 194
Stars trend:
#python
#bert, #embeddings, #llm, #nlp
Bringing BERT into modernity via both architecture changes and scaling
Language:Python
Total stars: 194
Stars trend:
19 Dec 2024
7pm ▋ +5
8pm ▋ +5
9pm ▉ +7
10pm ▊ +6
11pm ▋ +5
20 Dec 2024
12am ▌ +4
1am ▍ +3
2am █ +8
3am █▍ +11
4am █ +8
5am ▉ +7
6am █ +8#python
#bert, #embeddings, #llm, #nlp
facebookresearch/large_concept_model
Large Concept Models: Language modeling in a sentence representation space
Language:Python
Total stars: 671
Stars trend:
#python
#languagemodels, #nlp, #pytorch, #seq2seq, #sequencetosequence
Large Concept Models: Language modeling in a sentence representation space
Language:Python
Total stars: 671
Stars trend:
23 Dec 2024
8pm ▋ +5
9pm ▌ +4
10pm ▍ +3
11pm ▋ +5
24 Dec 2024
12am █ +8
1am █ +8
2am ▉ +7
3am ▉ +7
4am █ +8
5am █ +8
6am ▍ +3
7am █▏ +9#python
#languagemodels, #nlp, #pytorch, #seq2seq, #sequencetosequence
infiniflow/ragflow
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
Language:Python
Total stars: 28162
Stars trend:
#python
#agent, #agents, #aisearch, #chatbot, #chatgpt, #datapipelines, #deeplearning, #documentparser, #documentunderstanding, #genai, #graph, #graphrag, #llm, #nlp, #pdftotext, #preprocessing, #rag, #retrievalaugmentedgeneration, #tablestructurerecognition, #text2sql
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
Language:Python
Total stars: 28162
Stars trend:
13 Jan 2025
11pm ▏ +1
14 Jan 2025
12am ▍ +3
1am █▎ +10
2am █▍ +11
3am █▍ +11
4am ▊ +6
5am ▋ +5
6am █▏ +9
7am █▌ +12
8am █▊ +14
9am ▊ +6#python
#agent, #agents, #aisearch, #chatbot, #chatgpt, #datapipelines, #deeplearning, #documentparser, #documentunderstanding, #genai, #graph, #graphrag, #llm, #nlp, #pdftotext, #preprocessing, #rag, #retrievalaugmentedgeneration, #tablestructurerecognition, #text2sql
stanford-oval/storm
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
Language:Python
Total stars: 20319
Stars trend:
#python
#agenticrag, #emnlp2024, #knowledgecuration, #largelanguagemodels, #naacl, #nlp, #reportgeneration, #retrievalaugmentedgeneration
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
Language:Python
Total stars: 20319
Stars trend:
17 Jan 2025
6pm ██▏ +17
7pm ██▎ +18
8pm ▍ +3
9pm █▏ +9
10pm ▉ +7
11pm ▌ +4
18 Jan 2025
12am ▌ +4
1am ▍ +3
2am ▎ +2
3am █▎ +10
4am ▍ +3
5am ▌ +4#python
#agenticrag, #emnlp2024, #knowledgecuration, #largelanguagemodels, #naacl, #nlp, #reportgeneration, #retrievalaugmentedgeneration
HqWu-HITCS/Awesome-Chinese-LLM
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
Language:
Total stars: 17747
Stars trend:
#awesomelists, #chatglm, #chinese, #llama, #llm, #nlp
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
Language:
Total stars: 17747
Stars trend:
21 Jan 2025
8pm ▍ +3
9pm ▎ +2
10pm ▍ +3
11pm ▏ +1
22 Jan 2025
12am ▌ +4
1am █▍ +11
2am █▎ +10
3am █▎ +10
4am ▉ +7
5am █ +8
6am ▊ +6
7am █▍ +11#awesomelists, #chatglm, #chinese, #llama, #llm, #nlp
yobix-ai/extractous
Fast and efficient unstructured data extraction. Written in Rust with bindings for many languages.
Language:Rust
Total stars: 777
Stars trend:
#rust
#datapipelines, #docx, #etl, #etlpipelines, #extraction, #llm, #machinelearning, #naturallanguageprocessing, #nlp, #ocr, #pdf, #pdfparser, #rag, #rust, #tika, #unstructured, #unstructureddata
Fast and efficient unstructured data extraction. Written in Rust with bindings for many languages.
Language:Rust
Total stars: 777
Stars trend:
29 Jan 2025
10pm █▏ +9
11pm ▌ +4
30 Jan 2025
12am █▎ +10
1am ▋ +5
2am █▏ +9
3am ▊ +6
4am ▉ +7
5am █ +8
6am ▉ +7
7am █ +8
8am ▋ +5
9am █ +8#rust
#datapipelines, #docx, #etl, #etlpipelines, #extraction, #llm, #machinelearning, #naturallanguageprocessing, #nlp, #ocr, #pdf, #pdfparser, #rag, #rust, #tika, #unstructured, #unstructureddata
ml-tooling/best-of-ml-python
🏆 A ranked list of awesome machine learning Python libraries. Updated weekly.
Language:
Total stars: 19202
Stars trend:
#automl, #chatgpt, #dataanalysis, #datascience, #datavisualization, #datavisualizations, #deeplearning, #gpt, #gpt3, #jax, #keras, #machinelearning, #ml, #nlp, #python, #pytorch, #scikitlearn, #tensorflow, #transformer
🏆 A ranked list of awesome machine learning Python libraries. Updated weekly.
Language:
Total stars: 19202
Stars trend:
31 Jan 2025
4pm █ +8
5pm ▍ +3
6pm ▉ +7
7pm ▊ +6
8pm █▏ +9
9pm ▎ +2
10pm ▍ +3
11pm +0
1 Feb 2025
12am ▌ +4
1am ▏ +1
2am █████ +40
3am ███▊ +30#automl, #chatgpt, #dataanalysis, #datascience, #datavisualization, #datavisualizations, #deeplearning, #gpt, #gpt3, #jax, #keras, #machinelearning, #ml, #nlp, #python, #pytorch, #scikitlearn, #tensorflow, #transformer
👍1
typedgrammar/typed-japanese
Learn Japanese grammar with TypeScript
Language:TypeScript
Total stars: 1107
Stars trend:
#typescript
#computationallinguistics, #dsl, #grammar, #japanese, #japanesegrammar, #languagelearning, #languageverification, #nlp, #typelevelprogramming, #typesystem, #typescript, #typescripttypes
Learn Japanese grammar with TypeScript
Language:TypeScript
Total stars: 1107
Stars trend:
29 Mar 2025
11pm ██ +16
30 Mar 2025
12am ███▏ +25
1am ██▋ +21
2am ██▊ +22
3am ██▊ +22
4am █▌ +12
5am ██▉ +23
6am ███▏ +25
7am ███▍ +27
8am ██▎ +18
9am ██▍ +19
10am ██▉ +23#typescript
#computationallinguistics, #dsl, #grammar, #japanese, #japanesegrammar, #languagelearning, #languageverification, #nlp, #typelevelprogramming, #typesystem, #typescript, #typescripttypes
shcherbak-ai/contextgem
ContextGem: Effortless LLM extraction from documents
Language:Python
Total stars: 674
Stars trend:
#python
#ai, #contractanalysis, #dataextraction, #documentintelligence, #docx, #docx2md, #docx2txt, #generativeai, #legaltech, #llm, #llmextraction, #llmframework, #llmpipeline, #llms, #nlp, #promptengineering, #textanalysis, #unstructureddata
ContextGem: Effortless LLM extraction from documents
Language:Python
Total stars: 674
Stars trend:
11 May 2025
1pm █▏ +9
2pm █▍ +11
3pm █ +8
4pm ▊ +6
5pm █ +8
6pm ▍ +3
7pm ▍ +3
8pm ▍ +3
9pm ▍ +3
10pm ▌ +4
11pm █▎ +10
12 May 2025
12am ▉ +7#python
#ai, #contractanalysis, #dataextraction, #documentintelligence, #docx, #docx2md, #docx2txt, #generativeai, #legaltech, #llm, #llmextraction, #llmframework, #llmpipeline, #llms, #nlp, #promptengineering, #textanalysis, #unstructureddata
infiniflow/ragflow
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
Language:TypeScript
Total stars: 52811
Stars trend:
#typescript
#agent, #agents, #aisearch, #chatbot, #chatgpt, #deeplearning, #deepseek, #deepseekr1, #documentparser, #documentunderstanding, #graphrag, #llm, #nlp, #ollama, #pdftotext, #rag, #retrievalaugmentedgeneration, #tablestructurerecognition, #text2sql
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
Language:TypeScript
Total stars: 52811
Stars trend:
18 May 2025
10pm ▏ +1
11pm ▏ +1
19 May 2025
12am ▋ +5
1am █▍ +11
2am █▊ +14
3am █ +8
4am ▍ +3
5am ▊ +6
6am █▉ +15
7am ▉ +7
8am ██▏ +17
9am █ +8#typescript
#agent, #agents, #aisearch, #chatbot, #chatgpt, #deeplearning, #deepseek, #deepseekr1, #documentparser, #documentunderstanding, #graphrag, #llm, #nlp, #ollama, #pdftotext, #rag, #retrievalaugmentedgeneration, #tablestructurerecognition, #text2sql
Olow304/memvid
Video-based AI memory library. Store millions of text chunks in MP4 files with lightning-fast semantic search. No database needed.
Language:Python
Total stars: 930
Stars trend:
#python
#ai, #context, #embedded, #faiss, #knowledgebase, #knowledgegraph, #llm, #machinelearning, #memory, #nlp, #offlinefirst, #opencv, #python, #rag, #retrievalaugmentedgeneration, #semanticsearch, #vectordatabase, #videoprocessing
Video-based AI memory library. Store millions of text chunks in MP4 files with lightning-fast semantic search. No database needed.
Language:Python
Total stars: 930
Stars trend:
4 Jun 2025
2pm ▊ +6
3pm ▍ +3
4pm █▌ +12
5pm ▋ +5
6pm ▎ +2
7pm ▍ +3
8pm ▌ +4
9pm ▍ +3
10pm ▍ +3
11pm ▉ +7
5 Jun 2025
12am █▊ +14
1am ██▏ +17#python
#ai, #context, #embedded, #faiss, #knowledgebase, #knowledgegraph, #llm, #machinelearning, #memory, #nlp, #offlinefirst, #opencv, #python, #rag, #retrievalaugmentedgeneration, #semanticsearch, #vectordatabase, #videoprocessing
stanford-oval/storm
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
Language:Python
Total stars: 24983
Stars trend:
#python
#agenticrag, #deepresearch, #emnlp2024, #knowledgecuration, #largelanguagemodels, #naacl, #nlp, #reportgeneration, #retrievalaugmentedgeneration
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
Language:Python
Total stars: 24983
Stars trend:
29 Jun 2025
5am ▋ +5
6am ▍ +3
7am ▌ +4
8am ▊ +6
9am ▊ +6
10am ▊ +6
11am █▊ +14
12pm █▋ +13
1pm ██▏ +17
2pm █▉ +15
3pm ██▉ +23
4pm ███▍ +27#python
#agenticrag, #deepresearch, #emnlp2024, #knowledgecuration, #largelanguagemodels, #naacl, #nlp, #reportgeneration, #retrievalaugmentedgeneration
google/langextract
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
Language:Python
Total stars: 445
Stars trend:
#python
#gemini, #geminiai, #geminiapi, #geminiflash, #geminipro, #informationextration, #largelanguagemodels, #llm, #nlp, #python, #structureddata
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
Language:Python
Total stars: 445
Stars trend:
30 Jul 2025
7pm █ +8
8pm █▍ +11
9pm █▍ +11
10pm ██▊ +22
11pm ██▋ +21
31 Jul 2025
12am █▏ +9
1am █▍ +11
2am ██▌ +20
3am ██▊ +22
4am ████ +32
5am ████▍ +35
6am ████▊ +38#python
#gemini, #geminiai, #geminiapi, #geminiflash, #geminipro, #informationextration, #largelanguagemodels, #llm, #nlp, #python, #structureddata