# Chatting with pdf (with reasoning capabilities)
**URL:**
**Author:**  [@zoghiboy](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fzoghiboy)%5C
**Post date:** [February 4, 2025, 7:26am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fchatting-with-pdf-with-reasoning-capabilities%2F138883%2F1 "2025-02-04T07:26:14Z")
Hi everyone
i want to build a RAG for chatting with PDFs, running solely on CPU, accessible via web for multiple users, with reasoning capability (like DeepSeek-R1)
i appreciate your helps and comments \<3
(update)
i want something easy to deploy and easy to use
i saw a video on youtube ([https://www.youtube.com/watch?v=M6vZ6b75p9k](https://www.youtube.com/watch?v=M6vZ6b75p9k))
that explains it very well but
its not working well with only cpu
i want something like that doable.
---
**Author:**  [@Alanturner2](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FAlanturner2)%5C
**Post date:** [February 4, 2025, 7:28am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fchatting-with-pdf-with-reasoning-capabilities%2F138883%2F2 "2025-02-04T07:28:55Z")
Hi, @zoghiboy
First, I will appreciate your effort.
And RAG and LoRA are both good methods to chat with your document.
If you don’t satisfy the result, I recommend you to use RAG.
In RAG you can use vector database. This is very effective way to chat with your document.
But you should consider the response time. Which db service you choose, the time limit is different.
And you can also use some APIs like deepseek or openai free apis.
You can also view my examples.
> **[Langchain agent 1](https://www.kaggle.com/code/amunsentom/langchain-agent-1)**
>
> Explore and run machine learning code with Kaggle Notebooks | Using data from No attached data sources
> **[Arxiv Pdf Summarization - a Hugging Face Space by Alanturner2](https://huggingface.co/spaces/Alanturner2/Arxiv-pdf-summarization)**
>
> This is the project for arxiv pdf summarization
If you want to help from me, I will be here anytime for you.
---
**Author:**  [@zoghiboy](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fzoghiboy)%5C
**Post date:** [February 4, 2025, 7:35am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fchatting-with-pdf-with-reasoning-capabilities%2F138883%2F3 "2025-02-04T07:35:43Z")
thank you @Alanturner2