github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-15 06:26:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

experimental[minor]: upgrade the prompt injection model (#20783)

Browse Source 
- **Description:** In January, Laiyer.ai became part of ProtectAI, which
means the model became owned by ProtectAI. In addition to that,
yesterday, we released a new version of the model addressing issues the
Langchain's community and others mentioned to us about false-positives.
The new model has a better accuracy compared to the previous version,
and we thought the Langchain community would benefit from using the
[latest version of the
model](https://huggingface.co/protectai/deberta-v3-base-prompt-injection-v2).
- **Issue:** N/A
- **Dependencies:** N/A
- **Twitter handle:** @alex_yaremchuk
This commit is contained in:
Oleksandr Yaremchuk
2024-04-23 16:23:39 +02:00
committed by GitHub
parent 645b1e142e
commit 9428923bab
3 changed files with 13 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/api_reference/guide_imports.json
View File

File diff suppressed because one or more lines are too long

16
docs/docs/guides/productionization/safety/hugging_face_prompt_injection.ipynb
View File

@@ -9,7 +9,7 @@
"\n",
"This notebook shows how to prevent prompt injection attacks using the text classification model from `HuggingFace`.\n",
"\n",
"By default, it uses a *[laiyer/deberta-v3-base-prompt-injection](https://huggingface.co/laiyer/deberta-v3-base-prompt-injection)* model trained to identify prompt injections. \n",
"By default, it uses a *[protectai/deberta-v3-base-prompt-injection-v2](https://huggingface.co/protectai/deberta-v3-base-prompt-injection-v2)* model trained to identify prompt injections. \n",
"\n",
"In this notebook, we will use the ONNX version of the model to speed up the inference. "
]
@@ -49,11 +49,15 @@
"from optimum.onnxruntime import ORTModelForSequenceClassification\n",
"from transformers import AutoTokenizer, pipeline\n",
"\n",
"# Using https://huggingface.co/laiyer/deberta-v3-base-prompt-injection\n",
"model_path = \"laiyer/deberta-v3-base-prompt-injection\"\n",
"tokenizer = AutoTokenizer.from_pretrained(model_path)\n",
"tokenizer.model_input_names = [\"input_ids\", \"attention_mask\"] # Hack to run the model\n",
"model = ORTModelForSequenceClassification.from_pretrained(model_path, subfolder=\"onnx\")\n",
"# Using https://huggingface.co/protectai/deberta-v3-base-prompt-injection-v2\n",
"model_path = \"laiyer/deberta-v3-base-prompt-injection-v2\"\n",
"revision = None # We recommend specifiying the revision to avoid breaking changes or supply chain attacks\n",
"tokenizer = AutoTokenizer.from_pretrained(\n",
" model_path, revision=revision, model_input_names=[\"input_ids\", \"attention_mask\"]\n",
")\n",
"model = ORTModelForSequenceClassification.from_pretrained(\n",
" model_path, revision=revision, subfolder=\"onnx\"\n",
")\n",
"\n",
"classifier = pipeline(\n",
" \"text-classification\",\n",