Currently CrewAI provides a concept of Short-Term Memory which uses Chroma vector database as a default (which allows for performing RAG using EmbedChain package). Enable the use of Vector search as a short term memory.
 
The current use of short term memory is enabled by `memory = True ` while initializing the main class (Crew) and this defaults to use of ChromaDB as the vector DB.
{{}}

from crewai import Crew, Agent, Task, Process  

my_crew = Crew(  agents=[...],  
tasks=[...],  
process=Process.sequential,  
memory=True,  
verbose=True,  
embedder={  "provider": "openai",  "config":{  "model": 'text-embedding-3-small'  }  } 

) 

The future state we want to drive is where the MongoDB Vector Search can be specified and used easily while initializing the agent via the Crew class

https://github.com/crewAIInc/crewAI/tree/main/src/crewai/memory

Acceptance criteria:

• Investigate and write a mini Design doc / Scope doc for how the MongoDB can be used a short term memory in CrewAI. Since this can require changes in the core framework design  the CrewAI team is willing to work with us on the design of this feature.
• Obtain an LGTM from the stakeholders (engineering, AI product, crewAI team POC)
• Implement the feature