andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-09 08:08:32 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

feat(memory): adds support for customizable memory interface (#1339)

Browse Source 
* feat(memory): adds support for customizing crew storage

* chore: allow overwriting the crew memory configuration

* docs: update custom storage usage

* fix(lint): use correct syntax

* fix: type check warning

* fix: type check warnings

* fix(test): address agent default failing test

* fix(lint). address type checker error

* Update crew.py

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
This commit is contained in:
Ayo Ayibiowu
2024-09-22 22:03:23 +02:00
committed by GitHub
parent e3c7c0185d
commit 91ff331fec
5 changed files with 71 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

41
docs/core-concepts/Memory.md
View File

@@ -28,7 +28,7 @@ description: Leveraging memory systems in the crewAI framework to enhance agent
## Implementing Memory in Your Crew
When configuring a crew, you can enable and customize each memory component to suit the crew's objectives and the nature of tasks it will perform.
By default, the memory system is disabled, and you can ensure it is active by setting `memory=True` in the crew configuration. The memory will use OpenAI embeddings by default, but you can change it by setting `embedder` to a different model.
By default, the memory system is disabled, and you can ensure it is active by setting `memory=True` in the crew configuration. The memory will use OpenAI embeddings by default, but you can change it by setting `embedder` to a different model. It's also possible to initialize the memory instance with your own instance.
The 'embedder' only applies to **Short-Term Memory** which uses Chroma for RAG using the EmbedChain package.
The **Long-Term Memory** uses SQLite3 to store task results. Currently, there is no way to override these storage implementations.
@@ -50,6 +50,45 @@ my_crew = Crew(
)
```
### Example: Use Custom Memory Instances e.g FAISS as the VectorDB
```python
from crewai import Crew, Agent, Task, Process
# Assemble your crew with memory capabilities
my_crew = Crew(
agents=[...],
tasks=[...],
process="Process.sequential",
memory=True,
long_term_memory=EnhanceLongTermMemory(
storage=LTMSQLiteStorage(
db_path="/my_data_dir/my_crew1/long_term_memory_storage.db"
)
),
short_term_memory=EnhanceShortTermMemory(
storage=CustomRAGStorage(
crew_name="my_crew",
storage_type="short_term",
data_dir="//my_data_dir",
model=embedder["model"],
dimension=embedder["dimension"],
),
),
entity_memory=EnhanceEntityMemory(
storage=CustomRAGStorage(
crew_name="my_crew",
storage_type="entities",
data_dir="//my_data_dir",
model=embedder["model"],
dimension=embedder["dimension"],
),
),
verbose=True,
)
```
## Additional Embedding Providers
### Using OpenAI embeddings (already default)