diff --git a/README.md b/README.md
index 33f8a32..d912ec5 100644
--- a/README.md
+++ b/README.md
@@ -1,2 +1,107 @@
-# BLIP
+# Image-Text Retrieval Embdding with BLIP
+
+*author: David Wang*
+
+
+<br />
+
+
+
+## Description
+
+This operator extracts features for image or text with [BLIP](https://arxiv.org/abs/2201.12086) which can generate embeddings for text and image by jointly training an image encoder and text encoder to maximize the cosine similarity. This is a adaptation from [salesforce/BLIP](https://github.com/salesforce/BLIP).
+
+
+<br />
+
+
+## Code Example
+
+Load an image from path './teddy.jpg' to generate an image embedding. 
+
+Read the text 'A teddybear on a skateboard in Times Square.' to generate an text embedding. 
+
+ *Write the pipeline in simplified style*:
+
+```python
+import towhee
+
+towhee.glob('./teddy.jpg') \
+      .image_decode() \
+      .image_text_embedding.blip(model_name='blip_base', modality='image') \
+      .show()
+
+towhee.dc(["A teddybear on a skateboard in Times Square."]) \
+      .image_text_embedding.blip(model_name='blip_base', modality='text') \
+      .show()
+```
+<img src="https://towhee.io/image-text-embedding/blip/raw/branch/main/vec1.png" alt="result1" style="height:20px;"/>
+<img src="https://towhee.io/image-text-embedding/blip/raw/branch/main/vec2.png" alt="result2" style="height:20px;"/>
+
+*Write a same pipeline with explicit inputs/outputs name specifications:*
+
+```python
+import towhee
+
+towhee.glob['path']('./teddy.jpg') \
+      .image_decode['path', 'img']() \
+      .image_text_embedding.blip['img', 'vec'](model_name='blip_base', modality='image') \
+      .select['img', 'vec']() \
+      .show()
+
+towhee.dc['text'](["A teddybear on a skateboard in Times Square."]) \
+      .image_text_embedding.blip['text','vec'](model_name='blip_base', modality='text') \
+      .select['text', 'vec']() \
+      .show()
+```
+<img src="https://towhee.io/image-text-embedding/blip/raw/branch/main/tabular1.png" alt="result1" style="height:60px;"/>
+<img src="https://towhee.io/image-text-embedding/blip/raw/branch/main/tabular2.png" alt="result2" style="height:60px;"/>
+
+
+<br />
+
+
+
+## Factory Constructor
+
+Create the operator via the following factory method
+
+***clip(model_name, modality)***
+
+**Parameters:**
+
+​   ***model_name:*** *str*
+
+​   The model name of BLIP. Supported model names: 
+- blip_base     
+
+
+​   ***modality:*** *str*
+
+​   Which modality(*image* or *text*) is used to generate the embedding. 
+
+<br />
+
+
+
+## Interface
+
+An image-text embedding operator takes a [towhee image](link/to/towhee/image/api/doc) or string as input and generate an embedding in ndarray.
+
+
+**Parameters:**
+
+​	***data:*** *towhee.types.Image (a sub-class of numpy.ndarray)*  or *str*
+
+​  The data (image or text based on specified modality) to generate embedding.	
+
+
+
+**Returns:** *numpy.ndarray*
+
+​   The data embedding extracted by model.
+
+
+
+
 
diff --git a/blip.py b/blip.py
index ec5c904..ae4847d 100644
--- a/blip.py
+++ b/blip.py
@@ -33,7 +33,7 @@ class Blip(NNOperator):
         sys.path.append(str(Path(__file__).parent))
         from models.blip import blip_feature_extractor
         image_size = 224
-        model_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/models/model_base.pth'
+        model_url = self._configs()[model_name]['weights']
         self.model = blip_feature_extractor(pretrained=model_url, image_size=image_size, vit='base')
 
         self._modality = modality
@@ -73,4 +73,10 @@ class Blip(NNOperator):
         img = to_pil(img)
         processed_img = self.tfms(img).unsqueeze(0).to(self.device)
         return processed_img
+
+    def _configs():
+        config = {}
+        config['blip_base'] = {} 
+        config['blip_base']['weights'] = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/models/model_base.pth'
+        return config