# How to use multiple independant "memory" and RAG database for different crews? **URL:** \ **Category:** CrewAI Community Support\ **Tags:** memory\ **Created:** [September 21, 2024, 3:47pm UTC](https://community.crewai.com/t/how-to-use-multiple-independant-memory-and-rag-database-for-different-crews/494 "2024-09-21T15:47:29Z")\ **Posts on this page:** 11\ **Page:** 1
**Author:** ![Yannick](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/yannick/32/313_2.png) [@Yannick](https://community.crewai.com/u/Yannick)\ **Post date:** [September 21, 2024, 3:47pm UTC](https://community.crewai.com/t/how-to-use-multiple-independant-memory-and-rag-database-for-different-crews/494/1 "2024-09-21T15:47:29Z")
Hello, Is there a way to have multiple crews that use fully independent “memory” and rag tools, i.e. that have separate ./db folders I guess. I tried updating the CREWAI\_STORAGE\_DIR and CHROMA\_DB\_FOLDER variables before creating each crew but it does not seem to work and I have only one ./db in my root project folder… What I want is multiple fully different crew1/db crew2/db etc… so there is absolutely no mixup of data between the crews… I guess that should be possible… how? ---
**Author:** ![Yannick](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/yannick/32/313_2.png) [@Yannick](https://community.crewai.com/u/Yannick)\ **Post date:** [September 22, 2024, 4:27am UTC](https://community.crewai.com/t/how-to-use-multiple-independant-memory-and-rag-database-for-different-crews/494/2 "2024-09-22T04:27:29Z")
well it seems to work if I just chdir() to a different path before creating new crews… ---
**Author:** ![moto](https://avatars.discourse-cdn.com/v4/letter/m/2bfe46/32.png) [@moto](https://community.crewai.com/u/moto)\ **Post date:** [September 22, 2024, 5:18am UTC](https://community.crewai.com/t/how-to-use-multiple-independant-memory-and-rag-database-for-different-crews/494/3 "2024-09-22T05:18:28Z")
Where in the code are you doing the chdir? ---
**Author:** ![matt](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/matt/32/3_2.png) [@matt](https://community.crewai.com/u/matt)\ **Post date:** [September 22, 2024, 7:46am UTC](https://community.crewai.com/t/how-to-use-multiple-independant-memory-and-rag-database-for-different-crews/494/4 "2024-09-22T07:46:22Z")
```auto pdf_search_tool = PDFSearchTool( config=dict( embedder={ "provider": "openai", "config": { "model": 'text-embedding-3-small' } }, vectordb=dict( provider="chroma", config=dict( dir=f'crew-db-{uuid.uuid4()}' ... ) ) ) ``` Something like this, note the UUID creating the dir so its distinct ---
**Author:** ![Yannick](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/yannick/32/313_2.png) [@Yannick](https://community.crewai.com/u/Yannick)\ **Post date:** [September 22, 2024, 4:29pm UTC](https://community.crewai.com/t/how-to-use-multiple-independant-memory-and-rag-database-for-different-crews/494/5 "2024-09-22T16:29:00Z")
Just “os.chdir('a speific path for each crew”)"… I want to be able to “reset the memory” of a specifc crew and not some others. Using _crewai reset\_memories_ does not give any flexibilty to pick which part of the memory to reset. If each crew that needs to be indpendant has a completly different “home” folder with a fully different ./db etc… then I am sure I can manage each crew memory and everything else autonomously… and also be certain that any rag query will not mix up data. It’s not a very a very sophisticated design but it seems to work… ---
**Author:** ![moto](https://avatars.discourse-cdn.com/v4/letter/m/2bfe46/32.png) [@moto](https://community.crewai.com/u/moto)\ **Post date:** [September 22, 2024, 5:27pm UTC](https://community.crewai.com/t/how-to-use-multiple-independant-memory-and-rag-database-for-different-crews/494/6 "2024-09-22T17:27:51Z")
are you pipelining the crews? ---
**Author:** ![Yannick](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/yannick/32/313_2.png) [@Yannick](https://community.crewai.com/u/Yannick)\ **Post date:** [September 22, 2024, 6:34pm UTC](https://community.crewai.com/t/how-to-use-multiple-independant-memory-and-rag-database-for-different-crews/494/7 "2024-09-22T18:34:24Z")
No, simple crew with one agent and one task, default openai key… plain and standard… But why pipeline would make any difference related to memory or rag ?? ---
**Author:** ![moto](https://avatars.discourse-cdn.com/v4/letter/m/2bfe46/32.png) [@moto](https://community.crewai.com/u/moto)\ **Post date:** [September 23, 2024, 12:21am UTC](https://community.crewai.com/t/how-to-use-multiple-independant-memory-and-rag-database-for-different-crews/494/8 "2024-09-23T00:21:48Z")
I was just curious and wondering how memory and context got dragged along or not when pipelining crews. ---
**Author:** ![Clinbay\_Ltd](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/clinbay_ltd/32/917_2.png) [@Clinbay\_Ltd](https://community.crewai.com/u/Clinbay_Ltd)\ **Post date:** [November 14, 2024, 1:18pm UTC](https://community.crewai.com/t/how-to-use-multiple-independant-memory-and-rag-database-for-different-crews/494/9 "2024-11-14T13:18:20Z")
Great tip when processing multiple items having a different knowledge base using the same crew (eg: what is the color of my cat? with pdf1 = cat is blue, pdf2 = cat is red, …). When I store all PDFs in the same vector store, the retriever tends to mix things up between various data sources. Is there any alternative to using a different db? For instance, with metadata? ---
**Author:** ![cristian\_di\_febo](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/cristian_di_febo/32/3639_2.png) [@cristian\_di\_febo](https://community.crewai.com/u/cristian_di_febo)\ **Post date:** [July 2, 2025, 10:21am UTC](https://community.crewai.com/t/how-to-use-multiple-independant-memory-and-rag-database-for-different-crews/494/11 "2025-07-02T10:21:51Z")
> [@matt](#): > > ```auto > pdf_search_tool = PDFSearchTool( > config=dict( > embedder={ > "provider": "openai", > "config": { > "model": 'text-embedding-3-small' > } > }, > vectordb=dict( > provider="chroma", > config=dict( > dir=f'crew-db-{uuid.uuid4()}' > ... > ) > ) > ) > > ``` Thanks! This “vectordb” conf did the trick. But I would like to know where in documentation I should find this informations? I hope @CrewAI team will improve the documentation. ---
**Author:** ![Yannick](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/yannick/32/313_2.png) [@Yannick](https://community.crewai.com/u/Yannick)\ **Post date:** [July 3, 2025, 8:19am UTC](https://community.crewai.com/t/how-to-use-multiple-independant-memory-and-rag-database-for-different-crews/494/12 "2025-07-03T08:19:23Z")
no. I am not using Crewai memory. I built my own app specific memory to have more control.