community[patch]: Add grammar support for node-llama-cpp LLM #5310
+95
−2
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
…SON schema for node-llama-cpp
…SON schema for node-llama-cpp
dosubot
bot
added
the
size:M
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎
|
dosubot
bot
added
the
auto:improvement
bracesproul
reviewed
May 7, 2024
There was a problem hiding this comment.
This looks really good! I left one comment, and I believe you'll need to run yarn format && yarn lint:fix to resolve any prettier/eslint issues.
Also, if you could add an integration test for this that would be much appreciated!
Please re-request my review once those changes have been pushed so I can get this merged
Comment on lines
78
to
84
| this.jsonSchema = inputs?.jsonSchema; | ||
| this.gbnf = inputs?.gbnf; | ||
| this._model = createLlamaModel(inputs); | ||
| this._context = createLlamaContext(this._model, inputs); | ||
| this._session = createLlamaSession(this._context); | ||
| this._jsonSchema = createLlamaJsonSchemaGrammar(this.jsonSchema); | ||
| this._gbnf = createCustomGrammar(this.gbnf); |
There was a problem hiding this comment.
Can we drop this.jsonSchema and this.gbnf since they appear to only be used inside this constructor?
Suggested change
| this.jsonSchema = inputs?.jsonSchema; | |
| this.gbnf = inputs?.gbnf; | |
| this._model = createLlamaModel(inputs); | |
| this._context = createLlamaContext(this._model, inputs); | |
| this._session = createLlamaSession(this._context); | |
| this._jsonSchema = createLlamaJsonSchemaGrammar(this.jsonSchema); | |
| this._gbnf = createCustomGrammar(this.gbnf); | |
| this._model = createLlamaModel(inputs); | |
| this._context = createLlamaContext(this._model, inputs); | |
| this._session = createLlamaSession(this._context); | |
| this._jsonSchema = createLlamaJsonSchemaGrammar(inputs?.jsonSchema); | |
| this._gbnf = createCustomGrammar(inputs?.gbnf); |
There was a problem hiding this comment.
Yes, I will do this! Thank you for responding. Sorry I didn't see your comments before my last update.
dosubot
bot
added
size:L
bracesproul
approved these changes
May 10, 2024
dosubot
bot
removed
the
size:L
dosubot
bot
added
the
size:M
bracesproul
changed the title
This was referenced Jun 11, 2024
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.
Hello, I am attempting to add a configuration to langchainjs node-llama-cpp implementation that will make it respond in a specific format like JSON or a list. This is a functionality that the python langchain has for llama. The functionality for this is documented here: https://withcatai.github.io/node-llama-cpp/guide/grammar .