I think #graphrag with LLMs is too expensive for private use. Especially for documents tasks with #ragflow.

The token output costs of Gemini are too high, and it's among the cheapest these days.

DeepSeek still has an edge here. But it doesn't perform well for English imho.

#RAGflow is a very interesting knowledge management engine for #GenAI workflows.

https://because-security.atlassian.net/wiki/spaces/LML/pages/621641933/RAGflow+local+MCP+server+to+connect+Claude+Desktop+to+your+expert+Knowledge+Base

Many use cases related to Context Engineering to provide the data to a LLM / tool to process it.

#DeepDoc, #GraphRAG with OCR models (Mistral or other models). Cutting-edge stuff.

Sadly, the #Anthropic API costs for output tokens are expensive, but Chat models from Google can fill this gap.

๐Ÿง  Il progetto #RAGflow continua ad evolversi, con diverse novitร  dedicate al recupero sempre piรน efficiente delle informazioni. 
๐Ÿค– E introduce la possibilitร  di creare #AI Agent strutturati in grado di orchestrate flussi anche molto complessi. 
๐Ÿ’ก Il tutto realizzabile attraverso un'interfaccia grafica a blocchi che mette a disposizione modelli, azioni e tool esterni. 

#AI #GenAI #GenerativeAI #IntelligenzaArtificiale

๐Ÿง  #RagFlow continua ad evolversi, introducendo nuove funzionalitร .
๐Ÿ‘‰ Supporto del flusso di lavoro basato sui grafi. 
๐Ÿ‘‰ Aggiunta di nuovi componenti come Wikipedia, PubMed, Baidu e Duckduckgo.
๐Ÿ‘‰ Supporto dell'analisi dei file audio.
๐Ÿ‘‰ Supporto di #GraphRAG e mappe mentali.

๐Ÿ”— Il progetto: https://github.com/infiniflow/ragflow 

___ 

โœ‰๏ธ ๐—ฆ๐—ฒ ๐˜ƒ๐˜‚๐—ผ๐—ถ ๐—ฟ๐—ถ๐—บ๐—ฎ๐—ป๐—ฒ๐—ฟ๐—ฒ ๐—ฎ๐—ด๐—ด๐—ถ๐—ผ๐—ฟ๐—ป๐—ฎ๐˜๐—ผ/๐—ฎ ๐˜€๐˜‚ ๐—พ๐˜‚๐—ฒ๐˜€๐˜๐—ฒ ๐˜๐—ฒ๐—บ๐—ฎ๐˜๐—ถ๐—ฐ๐—ต๐—ฒ, ๐—ถ๐˜€๐—ฐ๐—ฟ๐—ถ๐˜ƒ๐—ถ๐˜๐—ถ ๐—ฎ๐—น๐—น๐—ฎ ๐—บ๐—ถ๐—ฎ ๐—ป๐—ฒ๐˜„๐˜€๐—น๐—ฒ๐˜๐˜๐—ฒ๐—ฟ: https://bit.ly/newsletter-alessiopomaro 

#AI #GenAI #GenerativeAI  #IntelligenzaArtificiale 

GitHub - infiniflow/ragflow: RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding. - infiniflow/ragflow

GitHub

๐Ÿง  Ho provato #RAGFlow, un framework #RAG open source dotato di un'interfaccia web based che permette di configurare completamente il sistema. 
๐Ÿš€ Pur usando un modello di #embeddings e un LLM non estremamente evoluti, i risultati sono giร  molto interessanti.
๐Ÿ‘‰ Il progetto รจ su GitHub, e puรฒ essere installato ovunque: https://github.com/infiniflow/ragflow

___

โœ‰๏ธ ๐—ฆ๐—ฒ ๐˜ƒ๐˜‚๐—ผ๐—ถ ๐—ฟ๐—ถ๐—บ๐—ฎ๐—ป๐—ฒ๐—ฟ๐—ฒ ๐—ฎ๐—ด๐—ด๐—ถ๐—ผ๐—ฟ๐—ป๐—ฎ๐˜๐—ผ/๐—ฎ ๐˜€๐˜‚ ๐—พ๐˜‚๐—ฒ๐˜€๐˜๐—ฒ ๐˜๐—ฒ๐—บ๐—ฎ๐˜๐—ถ๐—ฐ๐—ต๐—ฒ, ๐—ถ๐˜€๐—ฐ๐—ฟ๐—ถ๐˜ƒ๐—ถ๐˜๐—ถ ๐—ฎ๐—น๐—น๐—ฎ ๐—บ๐—ถ๐—ฎ ๐—ป๐—ฒ๐˜„๐˜€๐—น๐—ฒ๐˜๐˜๐—ฒ๐—ฟ: https://bit.ly/newsletter-alessiopomaro 

#AI #GenAI #GenerativeAI

GitHub - infiniflow/ragflow: RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding. - infiniflow/ragflow

GitHub