# chatbot using conversation memory + pinecone

**URL:** <https://community.n8n.io/t/chatbot-using-conversation-memory-pinecone/34148>\
**Category:** Questions\
**Tags:** workflow-building\
**Created:** [December 13, 2023, 7:09am UTC](https://community.n8n.io/t/chatbot-using-conversation-memory-pinecone/34148 "2023-12-13T07:09:17Z")\
**Posts on this page:** 7\
**Page:** 1

<div class="post-metadata">

**Author:** ![Samuel\_Lautert\_Jardi](https://dub1.discourse-cdn.com/n8n/user_avatar/community.n8n.io/samuel_lautert_jardi/32/33099_2.png) [@Samuel\_Lautert\_Jardi](https://community.n8n.io/u/Samuel_Lautert_Jardi)\
**Post date:** [December 13, 2023, 7:09am UTC](https://community.n8n.io/t/chatbot-using-conversation-memory-pinecone/34148/1 "2023-12-13T07:09:17Z")

</div>

Hi, I’m looking to build a chatbot using langchain+chatgto+pinecone. This chat must take into account what the user has already typed in the conversation and pinecone vector data. everything would be handled with chatGTP 3.5. What would the template look like to call memory+pinecone+chatgtp? thanks.

---

<div class="post-metadata">

**Author:** ![n8n](https://dub1.discourse-cdn.com/n8n/user_avatar/community.n8n.io/n8n/32/26906_2.png) [@n8n](https://community.n8n.io/u/n8n)\
**Post date:** [December 13, 2023, 7:09am UTC](https://community.n8n.io/t/chatbot-using-conversation-memory-pinecone/34148/2 "2023-12-13T07:09:18Z")

</div>

It looks like your topic is missing some important information. Could you provide the following if applicable.

- **n8n version:**
- **Database (default: SQLite):**
- **n8n EXECUTIONS\_PROCESS setting (default: own, main):**
- **Running n8n via (Docker, npm, n8n cloud, desktop app):**
- **Operating system:**

---

<div class="post-metadata">

**Author:** ![Samuel\_Lautert\_Jardi](https://dub1.discourse-cdn.com/n8n/user_avatar/community.n8n.io/samuel_lautert_jardi/32/33099_2.png) [@Samuel\_Lautert\_Jardi](https://community.n8n.io/u/Samuel_Lautert_Jardi)\
**Post date:** [December 13, 2023, 1:39pm UTC](https://community.n8n.io/t/chatbot-using-conversation-memory-pinecone/34148/3 "2023-12-13T13:39:20Z")

</div>

Version N8N: 1.19.0  
Database: Pinetone  
main  
Running n8n via: n8n cloud

---

<div class="post-metadata">

**Author:** ![Joachim\_Brindeau](https://dub1.discourse-cdn.com/n8n/user_avatar/community.n8n.io/joachim_brindeau/32/13995_2.png) [@Joachim\_Brindeau](https://community.n8n.io/u/Joachim_Brindeau)\
**Post date:** [December 17, 2023, 11:09am UTC](https://community.n8n.io/t/chatbot-using-conversation-memory-pinecone/34148/4 "2023-12-17T11:09:37Z")

</div>

Hello,

Something like this ?

> **[Ask questions about a PDF using AI | n8n workflow template](https://n8n.io/workflows/1960-ask-questions-about-a-pdf-using-ai/)**
>
> The workflow first populates a Pinecone index with vectors from a Bitcoin whitepaper. Then, it waits for a manual chat message. When received, the chat message

Cheers,  
Joachim

---

<div class="post-metadata">

**Author:** ![Samuel\_Lautert\_Jardi](https://dub1.discourse-cdn.com/n8n/user_avatar/community.n8n.io/samuel_lautert_jardi/32/33099_2.png) [@Samuel\_Lautert\_Jardi](https://community.n8n.io/u/Samuel_Lautert_Jardi)\
**Post date:** [December 18, 2023, 2:19pm UTC](https://community.n8n.io/t/chatbot-using-conversation-memory-pinecone/34148/5 "2023-12-18T14:19:02Z")

</div>

Almost that, it would be necessary to use a temporary memory with the user’s messages and forward them to OPEN.AI so that it knows the complete context of the conversation. And send the information to the pinecone together.

---

<div class="post-metadata">

**Author:** ![Samuel\_Lautert\_Jardi](https://dub1.discourse-cdn.com/n8n/user_avatar/community.n8n.io/samuel_lautert_jardi/32/33099_2.png) [@Samuel\_Lautert\_Jardi](https://community.n8n.io/u/Samuel_Lautert_Jardi)\
**Post date:** [December 18, 2023, 2:35pm UTC](https://community.n8n.io/t/chatbot-using-conversation-memory-pinecone/34148/6 "2023-12-18T14:35:25Z")

</div>

Almost that, it would be necessary to use a temporary memory with the user’s messages and forward them to OPEN.AI so that it knows the complete context of the conversation. And send the information to the pinecone together.

---

<div class="post-metadata">

**Author:** ![system](https://dub1.discourse-cdn.com/n8n/user_avatar/community.n8n.io/system/32/195824_2.png) [@system](https://community.n8n.io/u/system)\
**Post date:** [March 17, 2024, 2:36pm UTC](https://community.n8n.io/t/chatbot-using-conversation-memory-pinecone/34148/7 "2024-03-17T14:36:14Z")

</div>

This topic was automatically closed 90 days after the last reply. New replies are no longer allowed.