Comments (5)
Hey @gustavz , thanks for reaching out. RAG is the scope of the next release introducing more examples and features related to that. One of them can be a support of the batch.
Probably one thing we should explore is latency because there are a few ways to run it:
- Sequentially like now
- Using multiprocessing or threading libraries
- Pass multiple texts in transformers and let them handle concurrency
I will keep you updated on the progress
from llm-guard.
In our Slack, you can engage in discussions, share your feedback and get latest updates.
from llm-guard.
Any more information? I work on RAG now, try to introduce guard
in RAG process and I adopt ray to do the concurrency.
but the result is not good enough...
from llm-guard.
Maybe something like this(add scan_batch
to prompt injection
):
def scan_batch(self, prompts: list[str]) -> list[(str, bool, float)]:
if len(prompts) == 0:
return []
prompt_batch: list[str] = []
for prompt in prompts:
prompt_batch.extend(self._match_type.get_inputs(prompt))
highest_score = 0.0
results_all = self._pipeline(prompt_batch)
result_batch: list[(bool, float)] = []
for result in results_all:
injection_score = round(
result["score"] if result["label"] == self._model["label"] else 1 - result["score"],
2,
)
if injection_score > highest_score:
highest_score = injection_score
if injection_score > self._threshold:
logger.warning(f"Detected prompt injection with score: {injection_score}")
result_batch.append((False, calculate_risk_score(injection_score, self._threshold)))
else:
result_batch.append((True, 0.0))
return [(prompts[i],) + result_batch[i] for i in range(0, len(result_batch))]
from llm-guard.
Hey @vincent-pli ,
On one side, it makes sense to have prompts
as a list. However, we are planning to improve accuracy by sending chunks of prompts instead to the pipeline. It might make things a bit more complex.
In the next version, we are planning to kick off the refactoring of inputs and outputs.
from llm-guard.
Related Issues (20)
- Broken roadmap link in README HOT 1
- Support inference URLs for models used by scanners HOT 2
- llm-guard package installation with poetry. HOT 13
- Poor Metrics when running Prompt Injection Scanner HOT 4
- Toxicity Scanner to return the type of content HOT 1
- How to Use Custom SpaCy Model (beki/en_spacy_pii_distilbert) with Anonymize and Sensitive Scanners HOT 1
- Bias Prompt Injection HOT 1
- torch installation error HOT 1
- RuntimeError: Numpy is not available HOT 1
- Thread safety of using Anonymize/Deanonymize
- Callback error in Llama Index RAG pipeline integration for Node post processors HOT 1
- Sentence print along with the toxicity score. HOT 2
- Security layer for API HOT 2
- Detecting code from free flow text prompt HOT 3
- Stream support HOT 3
- The LLM-Guard API docker instance running on podman return the following error while using swagger UI and testing methods. HOT 8
- BanCompetitors constructor `model` argument is unintuitive HOT 4
- LLM_GUARD_API not working HOT 1
- Request for the API interface definition and sample implmentation codes HOT 1
- Scanners' speed, pulling up packages at execution HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from llm-guard.