Firestore memory #1975
Open
Firestore memory #1975
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Can you please add a corresponding cookbook and add the steps to setup firestore and get the required env variables at the top of the cookbook? |
|
Hi @manthanguptaa I've added the cookbook |
Comment on lines
+1
to
+17
| from typing import Optional, List | ||
| from datetime import datetime, timezone | ||
|
|
||
| try: | ||
| from google.cloud import firestore | ||
| from google.cloud.firestore import Client | ||
| from google.cloud.firestore import CollectionReference | ||
| from google.cloud.firestore_v1.base_query import FieldFilter, BaseQuery | ||
| import google.auth | ||
| except ImportError: | ||
| raise ImportError( | ||
| "`firestore` not installed. Please install it with `pip install google-cloud-firestore`" | ||
| ) | ||
|
|
||
| from agno.memory.db import MemoryDb | ||
| from agno.memory.row import MemoryRow | ||
| from agno.utils.log import logger |
There was a problem hiding this comment.
Suggested change
| from typing import Optional, List | |
| from datetime import datetime, timezone | |
| try: | |
| from google.cloud import firestore | |
| from google.cloud.firestore import Client | |
| from google.cloud.firestore import CollectionReference | |
| from google.cloud.firestore_v1.base_query import FieldFilter, BaseQuery | |
| import google.auth | |
| except ImportError: | |
| raise ImportError( | |
| "`firestore` not installed. Please install it with `pip install google-cloud-firestore`" | |
| ) | |
| from agno.memory.db import MemoryDb | |
| from agno.memory.row import MemoryRow | |
| from agno.utils.log import logger | |
| from typing import Optional, List | |
| from datetime import datetime, timezone | |
| from agno.memory.db import MemoryDb | |
| from agno.memory.row import MemoryRow | |
| from agno.utils.log import logger | |
| try: | |
| from google.cloud import firestore | |
| from google.cloud.firestore import Client | |
| from google.cloud.firestore import CollectionReference | |
| from google.cloud.firestore_v1.base_query import FieldFilter, BaseQuery | |
| import google.auth | |
| except ImportError: | |
| raise ImportError( | |
| "`firestore` not installed. Please install it with `pip install google-cloud-firestore`" | |
| ) | |
| def __init__( | ||
| self, | ||
| collection_name: str = "memory", | ||
| db_name: Optional[str] = "(default)", |
There was a problem hiding this comment.
Suggested change
| db_name: Optional[str] = "(default)", | |
| db_name: Optional[str] = "agno", |
Comment on lines
+55
to
+66
| def create(self) -> None: | ||
| """Create the collection index | ||
| Avoiding index creation by using a user/memory model | ||
|
|
||
| Returns: | ||
| None | ||
| """ | ||
| try: | ||
| logger.info(f"Mocked call to create index for '{self.collection_name}'") | ||
| except Exception as e: | ||
| logger.error(f"Error creating collection: {e}") | ||
| raise |
There was a problem hiding this comment.
I noticed this doesn’t seem to be doing anything. Was that intentional? Just wanted to check.
Comment on lines
+1
to
+8
| """ | ||
| This recipe shows how to store agent sessions in a MongoDB database. | ||
| Steps: | ||
| 1. Run: `pip install openai google-cloud-firestore agno` to install dependencies | ||
| 2. Make sure your gcloud project is set up and you have the necessary permissions to access Firestore | ||
| 3. Run: `python cookbook/memory/09_persistent_memory_firestore.py` to run the agent | ||
| """ | ||
|
|
There was a problem hiding this comment.
can you please also mention steps on how to set up gcloud locally and set up the project?
Comment on lines
+195
to
+205
| def drop_table(self) -> None: | ||
| """Drop the collection | ||
| Returns: | ||
| None | ||
| """ | ||
| try: | ||
| # todo https://firebase.google.com/docs/firestore/solutions/delete-collections | ||
| # no easy way | ||
| logger.info("call to drop table") | ||
| except Exception as e: | ||
| logger.error(f"Error dropping collection: {e}") |
There was a problem hiding this comment.
we will need to implement this as it is an important function
Comment on lines
+215
to
+226
| def clear(self) -> bool: | ||
| """Clear the collection | ||
| Returns: | ||
| bool: True if the collection was cleared, False otherwise | ||
| """ | ||
| try: | ||
| # todo https://firebase.google.com/docs/firestore/solutions/delete-collections | ||
| logger.info("call to clear the collection") | ||
| return True | ||
| except Exception as e: | ||
| logger.error(f"Error clearing collection: {e}") | ||
| return False |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
Adds firestore memory to solve #1974
Fixes # (issue)
[Feature Request] firestore agent memory #1974
Type of change
Checklist
./scripts/format.shand./scripts/validate.shto ensure code is formatted and linted.Additional Notes
firestore works best without having to create indexes. The data model collection_name/user_id/memories allows for selecting all memories and using an orderby without having to create a composite index which is a bit tricky in firestore (requires async calls, no callback when completed, not ready immediately).