TextMemorySkill: Recall Can Return Many Memories, added Keyed Lookup Functions Retrieve() and Remove() #35
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
…ded logging for long string result in RecallAsync
awharrison-28
added
the
PR: ready for review
awharrison-28
changed the title
|
@awharrison-28 if there are any breaking changes, can we also get them reflected in the memory notebook? |
|
@alexchaomander great call out. Will update shortly. |
awharrison-28
added
PR: feedback to address
awharrison-28
added
PR: ready for review
|
@alexchaomander I updated the notebook to address breaking changes as is. We should update notebook 6 to reflect new TextMemorySkill features, but I believe that should be a separate PR. |
awharrison-28
changed the title
lemillermicrosoft
previously approved these changes
Mar 16, 2023
glahaye
reviewed
Mar 16, 2023
glahaye
reviewed
Mar 16, 2023
glahaye
reviewed
Mar 16, 2023
glahaye
reviewed
Mar 16, 2023
glahaye
reviewed
Mar 16, 2023
glahaye
reviewed
Mar 16, 2023
glahaye
reviewed
Mar 16, 2023
glahaye
requested changes
Mar 16, 2023
glahaye
approved these changes
Mar 17, 2023
lemillermicrosoft
approved these changes
Mar 20, 2023
dluc
approved these changes
Mar 20, 2023
dehoward
pushed a commit
to lemillermicrosoft/semantic-kernel
that referenced
this pull request
Jun 1, 2023
…Functions Retrieve() and Remove() (microsoft#35) ### Motivation and Context Currently, TextMemorySkill `Recall` only returns the most relevant memory despite being reliant on methods that support returning N relevant memories. Additionally, users should be able to `Remove` memories. ### Description This PR introduces new terminology to TextMemorySkill: `Remove` and `Retrieve`. `Remove` and 'Retrieve' allows the TextMemorySkill get and delete memories from storage by unique key (since memories are stored as key-value pairs). Users may Retrieve/Remove a single memory using the unique key associated with the memory. Redefined function: - `Recall` -> look up a number of memories relevant to a given idea string. The number of results depends on a `LimitParam` and `RelevanceParam` provided by the SKContext. The results text records are concatenated to a single Json string. New functions: - `RetrieveAsync` -> look up a specific memory associated with a unique key. - `RemoveAsync` -> delete a specific memory associated with a unique key. Additional Changes: - Modified KernelSyntaxExample `Example15_MemorySkill` to use the new functions and features. - Added `RemoveAsync` to `ISemanticTextMemory` and its implementors `SemanticTextMemory` and `NullMemory` **Note:** If the result of 'Recall' will be used for a completion skill, this could result in unexpected behavior if the text for N memories exceeds the model's token limit. Addressing input chunking to a completion model is not in scope for this PR.
golden-aries
pushed a commit
to golden-aries/semantic-kernel
that referenced
this pull request
Oct 10, 2023
### Motivation and Context <!-- Thank you for your contribution to the copilot-chat repo! Please help reviewers and future users, providing the following information: 1. Why is this change required? 2. What problem does it solve? 3. What scenario does it contribute to? 4. If it fixes an open issue, please link to the issue here. --> Add a persona tab to show/enable the following: 1. Meta prompt. 2. Meta prompt editing, 3. Memory (long term & short term) content. 4. Memory bias slider. ### Description 1. Webapi support for editing the meta prompt. 2. Webapi support for retrieving memory content (ChatMemoryController). 3. Webapi support for setting memory bias. 4. Webapp support for showing and enabling the features. 5. Update the initial bot greeting message.  <!-- Describe your changes, the overall approach, the underlying design. These notes will help understanding how your code works. Thanks! --> ### Contribution Checklist <!-- Before submitting this PR, please make sure: --> - [ ] The code builds clean without any errors or warnings - [ ] The PR follows the [Contribution Guidelines](https://github.com/microsoft/copilot-chat/blob/main/CONTRIBUTING.md) and the [pre-submission formatting script](https://github.com/microsoft/copilot-chat/blob/main/CONTRIBUTING.md#development-scripts) raises no violations - [ ] All unit tests pass, and I have added new tests where possible - [ ] I didn't break anyone 😄
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.
Motivation and Context
Currently, TextMemorySkill
Recallonly returns the most relevant memory despite being reliant on methods that support returning N relevant memories.Additionally, users should be able to
Removememories.Description
This PR introduces new terminology to TextMemorySkill:
RemoveandRetrieve.Removeand 'Retrieve' allows the TextMemorySkill get and delete memories from storage by unique key (since memories are stored as key-value pairs).Users may Retrieve/Remove a single memory using the unique key associated with the memory.
Redefined function:
Recall-> look up a number of memories relevant to a given idea string. The number of results depends on aLimitParamandRelevanceParamprovided by the SKContext. The results text records are concatenated to a single Json string.New functions:
RetrieveAsync-> look up a specific memory associated with a unique key.RemoveAsync-> delete a specific memory associated with a unique key.Additional Changes:
Example15_MemorySkillto use the new functions and features.RemoveAsynctoISemanticTextMemoryand its implementorsSemanticTextMemoryandNullMemoryNote: If the result of 'Recall' will be used for a completion skill, this could result in unexpected behavior if the text for N memories exceeds the model's token limit. Addressing input chunking to a completion model is not in scope for this PR.