diff --git a/Tutorials/1_Embedding/1.2.6_BGE_VL.ipynb b/Tutorials/1_Embedding/1.2.6_BGE_VL.ipynb
new file mode 100644
index 0000000..263b896
--- /dev/null
+++ b/Tutorials/1_Embedding/1.2.6_BGE_VL.ipynb
@@ -0,0 +1,366 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# BGE-VL"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "In this tutorial, we will go through the multimodel retrieval models BGE-VL series, which achieved state-of-the-art performance on four popular zero-shot composed image retrieval benchmarks and the massive multimodal embedding benchmark (MMEB)."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 0. Installation"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Install the required packages in your environment."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install numpy torch transformers pillow"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 1. BGE-VL-CLIP"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "| Model  | Language |   Parameters   |   Model Size   |    Description    |   Base Model     |\n",
+    "|:-------|:--------:|:--------------:|:--------------:|:-----------------:|:----------------:|\n",
+    "| [BAAI/bge-vl-base](https://huggingface.co/BAAI/BGE-VL-base)       | English |    150M    |    299 MB    |          Light weight multimodel embedder among image and text                   |  CLIP-base   |\n",
+    "| [BAAI/bge-vl-large](https://huggingface.co/BAAI/BGE-VL-large)     | English |    428M    |    855 MB    |          Large scale multimodel embedder among image and text                    |  CLIP-large  |"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "BGE-VL-base and BGE-VL-large are trained based on CLIP base and CLIP large, which both contain a vision transformer and a text transformer:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/share/project/xzy/Envs/ft/lib/python3.11/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n",
+      "/share/project/xzy/Envs/ft/lib/python3.11/site-packages/_distutils_hack/__init__.py:54: UserWarning: Reliance on distutils from stdlib is deprecated. Users must rely on setuptools to provide the distutils module. Avoid importing distutils or import setuptools first, and avoid setting SETUPTOOLS_USE_DISTUTILS=stdlib. Register concerns at https://github.com/pypa/setuptools/issues/new?template=distutils-deprecation.yml\n",
+      "  warnings.warn(\n",
+      "/share/project/xzy/Envs/ft/lib/python3.11/site-packages/transformers/tokenization_utils_base.py:1601: FutureWarning: `clean_up_tokenization_spaces` was not set. It will be set to `True` by default. This behavior will be depracted in transformers v4.45, and will be then set to `False` by default. For more details check this issue: https://github.com/huggingface/transformers/issues/31884\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "CLIPModel(\n",
+       "  (text_model): CLIPTextTransformer(\n",
+       "    (embeddings): CLIPTextEmbeddings(\n",
+       "      (token_embedding): Embedding(49408, 512)\n",
+       "      (position_embedding): Embedding(77, 512)\n",
+       "    )\n",
+       "    (encoder): CLIPEncoder(\n",
+       "      (layers): ModuleList(\n",
+       "        (0-11): 12 x CLIPEncoderLayer(\n",
+       "          (self_attn): CLIPSdpaAttention(\n",
+       "            (k_proj): Linear(in_features=512, out_features=512, bias=True)\n",
+       "            (v_proj): Linear(in_features=512, out_features=512, bias=True)\n",
+       "            (q_proj): Linear(in_features=512, out_features=512, bias=True)\n",
+       "            (out_proj): Linear(in_features=512, out_features=512, bias=True)\n",
+       "          )\n",
+       "          (layer_norm1): LayerNorm((512,), eps=1e-05, elementwise_affine=True)\n",
+       "          (mlp): CLIPMLP(\n",
+       "            (activation_fn): QuickGELUActivation()\n",
+       "            (fc1): Linear(in_features=512, out_features=2048, bias=True)\n",
+       "            (fc2): Linear(in_features=2048, out_features=512, bias=True)\n",
+       "          )\n",
+       "          (layer_norm2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)\n",
+       "        )\n",
+       "      )\n",
+       "    )\n",
+       "    (final_layer_norm): LayerNorm((512,), eps=1e-05, elementwise_affine=True)\n",
+       "  )\n",
+       "  (vision_model): CLIPVisionTransformer(\n",
+       "    (embeddings): CLIPVisionEmbeddings(\n",
+       "      (patch_embedding): Conv2d(3, 768, kernel_size=(16, 16), stride=(16, 16), bias=False)\n",
+       "      (position_embedding): Embedding(197, 768)\n",
+       "    )\n",
+       "    (pre_layrnorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
+       "    (encoder): CLIPEncoder(\n",
+       "      (layers): ModuleList(\n",
+       "        (0-11): 12 x CLIPEncoderLayer(\n",
+       "          (self_attn): CLIPSdpaAttention(\n",
+       "            (k_proj): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (v_proj): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (q_proj): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (out_proj): Linear(in_features=768, out_features=768, bias=True)\n",
+       "          )\n",
+       "          (layer_norm1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
+       "          (mlp): CLIPMLP(\n",
+       "            (activation_fn): QuickGELUActivation()\n",
+       "            (fc1): Linear(in_features=768, out_features=3072, bias=True)\n",
+       "            (fc2): Linear(in_features=3072, out_features=768, bias=True)\n",
+       "          )\n",
+       "          (layer_norm2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
+       "        )\n",
+       "      )\n",
+       "    )\n",
+       "    (post_layernorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
+       "  )\n",
+       "  (visual_projection): Linear(in_features=768, out_features=512, bias=False)\n",
+       "  (text_projection): Linear(in_features=512, out_features=512, bias=False)\n",
+       ")"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import numpy as np\n",
+    "import torch\n",
+    "from transformers import AutoModel\n",
+    "\n",
+    "MODEL_NAME = \"BAAI/BGE-VL-base\" # or \"BAAI/BGE-VL-base\"\n",
+    "\n",
+    "model = AutoModel.from_pretrained(MODEL_NAME, trust_remote_code=True) # You must set trust_remote_code=True\n",
+    "model.set_processor(MODEL_NAME)\n",
+    "model.eval()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "tensor([[0.2647, 0.1242]])\n"
+     ]
+    }
+   ],
+   "source": [
+    "with torch.no_grad():\n",
+    "    query = model.encode(\n",
+    "        images = \"../../imgs/cir_query.png\", \n",
+    "        text = \"Make the background dark, as if the camera has taken the photo at night\"\n",
+    "    )\n",
+    "\n",
+    "    candidates = model.encode(\n",
+    "        images = [\"../../imgs/cir_candi_1.png\", \"../../imgs/cir_candi_2.png\"]\n",
+    "    )\n",
+    "    \n",
+    "    scores = query @ candidates.T\n",
+    "print(scores)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 2. BGE-VL-MLLM"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "| Model  | Language |   Parameters   |   Model Size   |    Description    |   Base Model     |\n",
+    "|:-------|:--------:|:--------------:|:--------------:|:-----------------:|:----------------:|\n",
+    "| [BAAI/bge-vl-MLLM-S1](https://huggingface.co/BAAI/BGE-VL-MLLM-S1)       | English |    7.57B    |    15.14 GB    |   SOTA in composed image retrieval, trained on MegaPairs dataset      |  LLaVA-1.6   |\n",
+    "| [BAAI/bge-vl-MLLM-S2](https://huggingface.co/BAAI/BGE-VL-MLLM-S2)       | English |    7.57B    |    15.14 GB    |   Finetune BGE-VL-MLLM-S1 with one epoch on MMEB training set         |  LLaVA-1.6   |"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/share/project/xzy/Envs/ft/lib/python3.11/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n",
+      "/share/project/xzy/Envs/ft/lib/python3.11/site-packages/_distutils_hack/__init__.py:54: UserWarning: Reliance on distutils from stdlib is deprecated. Users must rely on setuptools to provide the distutils module. Avoid importing distutils or import setuptools first, and avoid setting SETUPTOOLS_USE_DISTUTILS=stdlib. Register concerns at https://github.com/pypa/setuptools/issues/new?template=distutils-deprecation.yml\n",
+      "  warnings.warn(\n",
+      "Loading checkpoint shards: 100%|██████████| 4/4 [00:03<00:00,  1.28it/s]\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "LLaVANextForEmbedding(\n",
+       "  (vision_tower): CLIPVisionModel(\n",
+       "    (vision_model): CLIPVisionTransformer(\n",
+       "      (embeddings): CLIPVisionEmbeddings(\n",
+       "        (patch_embedding): Conv2d(3, 1024, kernel_size=(14, 14), stride=(14, 14), bias=False)\n",
+       "        (position_embedding): Embedding(577, 1024)\n",
+       "      )\n",
+       "      (pre_layrnorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)\n",
+       "      (encoder): CLIPEncoder(\n",
+       "        (layers): ModuleList(\n",
+       "          (0-23): 24 x CLIPEncoderLayer(\n",
+       "            (self_attn): CLIPSdpaAttention(\n",
+       "              (k_proj): Linear(in_features=1024, out_features=1024, bias=True)\n",
+       "              (v_proj): Linear(in_features=1024, out_features=1024, bias=True)\n",
+       "              (q_proj): Linear(in_features=1024, out_features=1024, bias=True)\n",
+       "              (out_proj): Linear(in_features=1024, out_features=1024, bias=True)\n",
+       "            )\n",
+       "            (layer_norm1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)\n",
+       "            (mlp): CLIPMLP(\n",
+       "              (activation_fn): QuickGELUActivation()\n",
+       "              (fc1): Linear(in_features=1024, out_features=4096, bias=True)\n",
+       "              (fc2): Linear(in_features=4096, out_features=1024, bias=True)\n",
+       "            )\n",
+       "            (layer_norm2): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)\n",
+       "          )\n",
+       "        )\n",
+       "      )\n",
+       "      (post_layernorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)\n",
+       "    )\n",
+       "  )\n",
+       "  (multi_modal_projector): LlavaNextMultiModalProjector(\n",
+       "    (linear_1): Linear(in_features=1024, out_features=4096, bias=True)\n",
+       "    (act): GELUActivation()\n",
+       "    (linear_2): Linear(in_features=4096, out_features=4096, bias=True)\n",
+       "  )\n",
+       "  (language_model): MistralForCausalLM(\n",
+       "    (model): MistralModel(\n",
+       "      (embed_tokens): Embedding(32005, 4096)\n",
+       "      (layers): ModuleList(\n",
+       "        (0-31): 32 x MistralDecoderLayer(\n",
+       "          (self_attn): MistralSdpaAttention(\n",
+       "            (q_proj): Linear(in_features=4096, out_features=4096, bias=False)\n",
+       "            (k_proj): Linear(in_features=4096, out_features=1024, bias=False)\n",
+       "            (v_proj): Linear(in_features=4096, out_features=1024, bias=False)\n",
+       "            (o_proj): Linear(in_features=4096, out_features=4096, bias=False)\n",
+       "            (rotary_emb): MistralRotaryEmbedding()\n",
+       "          )\n",
+       "          (mlp): MistralMLP(\n",
+       "            (gate_proj): Linear(in_features=4096, out_features=14336, bias=False)\n",
+       "            (up_proj): Linear(in_features=4096, out_features=14336, bias=False)\n",
+       "            (down_proj): Linear(in_features=14336, out_features=4096, bias=False)\n",
+       "            (act_fn): SiLU()\n",
+       "          )\n",
+       "          (input_layernorm): MistralRMSNorm((4096,), eps=1e-05)\n",
+       "          (post_attention_layernorm): MistralRMSNorm((4096,), eps=1e-05)\n",
+       "        )\n",
+       "      )\n",
+       "      (norm): MistralRMSNorm((4096,), eps=1e-05)\n",
+       "    )\n",
+       "    (lm_head): Linear(in_features=4096, out_features=32005, bias=False)\n",
+       "  )\n",
+       ")"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import torch\n",
+    "from transformers import AutoModel\n",
+    "from PIL import Image\n",
+    "\n",
+    "MODEL_NAME= \"BAAI/BGE-VL-MLLM-S1\"\n",
+    "\n",
+    "model = AutoModel.from_pretrained(MODEL_NAME, trust_remote_code=True)\n",
+    "model.eval()\n",
+    "model.cuda()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "tensor([[0.4109, 0.1807]], device='cuda:0')\n"
+     ]
+    }
+   ],
+   "source": [
+    "with torch.no_grad():\n",
+    "    model.set_processor(MODEL_NAME)\n",
+    "\n",
+    "    query_inputs = model.data_process(\n",
+    "        text=\"Make the background dark, as if the camera has taken the photo at night\", \n",
+    "        images=\"../../imgs/cir_query.png\",\n",
+    "        q_or_c=\"q\",\n",
+    "        task_instruction=\"Retrieve the target image that best meets the combined criteria by using both the provided image and the image retrieval instructions: \"\n",
+    "    )\n",
+    "\n",
+    "    candidate_inputs = model.data_process(\n",
+    "        images=[\"../../imgs/cir_candi_1.png\", \"../../imgs/cir_candi_2.png\"],\n",
+    "        q_or_c=\"c\",\n",
+    "    )\n",
+    "\n",
+    "    query_embs = model(**query_inputs, output_hidden_states=True)[:, -1, :]\n",
+    "    candi_embs = model(**candidate_inputs, output_hidden_states=True)[:, -1, :]\n",
+    "    \n",
+    "    query_embs = torch.nn.functional.normalize(query_embs, dim=-1)\n",
+    "    candi_embs = torch.nn.functional.normalize(candi_embs, dim=-1)\n",
+    "\n",
+    "    scores = torch.matmul(query_embs, candi_embs.T)\n",
+    "print(scores)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/docs/source/Introduction/index.rst b/docs/source/Introduction/index.rst
index f7ea3c3..17c7b19 100644
--- a/docs/source/Introduction/index.rst
+++ b/docs/source/Introduction/index.rst
@@ -27,4 +27,5 @@ Quickly get started with:
    IR
    embedder
    reranker
+   similarity
    retrieval_demo
\ No newline at end of file
diff --git a/docs/source/Introduction/similarity.rst b/docs/source/Introduction/similarity.rst
new file mode 100644
index 0000000..5e1b61b
--- /dev/null
+++ b/docs/source/Introduction/similarity.rst
@@ -0,0 +1,60 @@
+Similarity
+==========
+
+A primary goal of retrieval is to find the most relevant documents in response to a user's query. 
+One of the core components of this process is measuring similarity between the query and candidates.
+Similarity metrics quantify how closely related two pieces of data are, and guide the retrieval system in ranking results.
+
+Jaccard Similarity
+------------------
+
+.. math::
+
+    J(A,B)=\frac{|A\cap B|}{|A\cup B|}
+
+The Jaccard similarity or Jaccard index is commonly used for set-based similarity, particularly in binary data (e.g., whether a term appears in a document or not). 
+It is calculated as the size of the intersection of two sets divided by the size of their union. 
+In information retrieval, it's often used to compare sets of keywords or phrases, with higher values indicating more similarity.
+
+Euclidean Distance
+------------------
+
+.. math::
+
+    d(A, B) = \|A-B\|_2 = \sqrt{\sum_{i=1}^n (A_i-B_i)^2}
+
+Euclidean distance measures the straight-line distance between two points in a vector space. 
+In IR, this can be used to assess the difference between document or query vectors. 
+A smaller distance indicates greater similarity. 
+This metric is intuitive but can sometimes be sensitive to the scale of the data, especially in high-dimensional spaces like text embeddings.
+
+Cosine Similarity
+-----------------
+
+.. math::
+
+    \cos(\theta)=\frac{A\cdot B}{\|A\|\|B\|}
+
+Cosine similarity is one of the most widely used metrics in information retrieval, especially for text. 
+It measures the cosine of the angle between two vectors in a multi-dimensional space (typically representing term frequency vectors of documents and queries). 
+If the cosine similarity is closer to 1, the vectors are more similar. 
+A value of 0 indicates orthogonality, meaning no similarity. 
+It's a simple yet effective measure for text-based retrieval, as it considers the orientation but not the magnitude of vectors.
+
+Dot Product
+-----------
+
+Coordinate definition:
+.. math::
+
+    A\cdot B = \sum_{i=1}^{i=n}A_i B_i
+
+Geometric definition:
+.. math::
+
+    A\cdot B = \|A\|\|B\|\cos(\theta)
+
+The dot product between two vectors provides a measure of how similar the vectors are in terms of direction and magnitude. 
+In information retrieval, the dot product is often used in vector space models, particularly when dealing with pre-trained word or sentence embeddings. 
+A higher dot product indicates that the query and document are closely aligned in the vector space.
+
diff --git a/docs/source/bge/bge_vl.rst b/docs/source/bge/bge_vl.rst
new file mode 100644
index 0000000..5076ff0
--- /dev/null
+++ b/docs/source/bge/bge_vl.rst
@@ -0,0 +1,110 @@
+BGE-VL
+======
+
+BGE-VL is a series of multimodel retrieval models training on `MegaPairs <https://github.com/VectorSpaceLab/MegaPairs>`_ 
+
+BGE-VL contains light weight CLIP based models as well as more powerful LLAVA-NeXT based MLLM models:
+
++----------------------------------------------------------------------+-----------+------------+--------------+-----------------------------------------------------------------------+
+|                                  Model                               |  Language | Parameters |  Model Size  |                              Description                              |
++======================================================================+===========+============+==============+=======================================================================+
+| `BAAI/bge-vl-base <https://huggingface.co/BAAI/BGE-VL-base>`_        |  English  |    150M    |    299 MB    |        Light weight multimodel embedder among image and text          |
++----------------------------------------------------------------------+-----------+------------+--------------+-----------------------------------------------------------------------+
+| `BAAI/bge-vl-large <https://huggingface.co/BAAI/BGE-VL-large>`_      |  English  |    428M    |    855 MB    |         Large scale multimodel embedder among image and text          |
++----------------------------------------------------------------------+-----------+------------+--------------+-----------------------------------------------------------------------+
+| `BAAI/bge-vl-MLLM-S1 <https://huggingface.co/BAAI/BGE-VL-MLLM-S1>`_  |  English  |    7.57B   |   15.14 GB   |   SOTA in composed image retrieval, trained on MegaPairs dataset      |
++----------------------------------------------------------------------+-----------+------------+--------------+-----------------------------------------------------------------------+
+| `BAAI/bge-vl-MLLM-S2 <https://huggingface.co/BAAI/BGE-VL-MLLM-S2>`_  |  English  |    7.57B   |   15.14 GB   |   Finetune BGE-VL-MLLM-S1 with one epoch on MMEB training set         |
++----------------------------------------------------------------------+-----------+------------+--------------+-----------------------------------------------------------------------+
+
+
+BGE-VL-CLIP
+-----------
+
+The base and large model are trained based on CLIP-vit-base-patch16 and CLIP-vit-large-patch14. 
+For composed image-text data, the model directly use score-fusion to sum up the outputs of visual encoder and text encoder and get the final embedding.
+
+.. tip::
+
+    Our code works well on transformers==4.45.2, and we recommend using this version.
+
+You can easily use BGE-VL-CLIP models based on transformers:
+
+.. code:: python
+
+    import torch
+    from transformers import AutoModel
+
+    MODEL_NAME = "BAAI/BGE-VL-base" # or "BAAI/BGE-VL-large"
+    model = AutoModel.from_pretrained(MODEL_NAME, trust_remote_code=True) # You must set trust_remote_code=True
+    model.set_processor(MODEL_NAME)
+    model.eval()
+
+    with torch.no_grad():
+        query = model.encode(
+            images = "./assets/cir_query.png", 
+            text = "Make the background dark, as if the camera has taken the photo at night"
+        )
+        candidates = model.encode(
+            images = ["./assets/cir_candi_1.png", "./assets/cir_candi_2.png"]
+        )
+        
+        scores = query @ candidates.T
+    print(scores)
+
+
+BGE-VL-MLLM
+-----------
+
+The multimodal large language models (MLLMs) incorporate a visual encoder, typically based on a vision transformer, into a large language model (LLM). 
+This integration allows image tokens to be directly processed by the LLM. 
+Consequently, MLLMs can effectively handle diverse multimodal inputs by converting any type of input into a sequence of tokens.
+
+BGE-VL-MLLM builds upon the LLaVA1.6. In both training and inference stages, MMRet uses task-specific instructions for query inputs to improve generalization, aligning
+with standard practices in LLM-based embedding models. 
+A typical multimodal query input is structured as follows:
+
+.. math:: 
+
+    ⟨\text{instruct}⟩{\{task\_ inst\}} \space⟨\text{query}⟩\{q_t\} \{q_i\}\space[\text{EOS}]
+
+where :math:`{task_inst}` represents the task-specific instruction, :math:`{qt}` denotes the input query text, and
+:math:`{qi}` is the input query image. 
+The normalized last hidden state of the [EOS] token in the MLLM is used as the embedding of any given input sequence.
+
+.. code:: python
+
+    import torch
+    from transformers import AutoModel
+    from PIL import Image
+
+    MODEL_NAME= "BAAI/BGE-VL-MLLM-S1"
+    model = AutoModel.from_pretrained(MODEL_NAME, trust_remote_code=True)
+    model.eval()
+    model.cuda()
+
+    with torch.no_grad():
+        model.set_processor(MODEL_NAME)
+
+        query_inputs = model.data_process(
+            text="Make the background dark, as if the camera has taken the photo at night", 
+            images="./assets/cir_query.png",
+            q_or_c="q",
+            task_instruction="Retrieve the target image that best meets the combined criteria by using both the provided image and the image retrieval instructions: "
+        )
+        candidate_inputs = model.data_process(
+            images=["./assets/cir_candi_1.png", "./assets/cir_candi_2.png"],
+            q_or_c="c",
+        )
+
+        query_embs = model(**query_inputs, output_hidden_states=True)[:, -1, :]
+        candi_embs = model(**candidate_inputs, output_hidden_states=True)[:, -1, :]
+        
+        query_embs = torch.nn.functional.normalize(query_embs, dim=-1)
+        candi_embs = torch.nn.functional.normalize(candi_embs, dim=-1)
+
+        scores = torch.matmul(query_embs, candi_embs.T)
+    print(scores)
+
+
+For more details, check out the repo of `MegaPairs <https://github.com/VectorSpaceLab/MegaPairs>`_
\ No newline at end of file
diff --git a/docs/source/bge/index.rst b/docs/source/bge/index.rst
index 7e83c92..82c31be 100644
--- a/docs/source/bge/index.rst
+++ b/docs/source/bge/index.rst
@@ -14,6 +14,7 @@ BGE
    bge_v1_v1.5
    bge_m3
    bge_icl
+   bge_vl
 
 .. toctree::
    :maxdepth: 1
diff --git a/imgs/cir_candi_1.png b/imgs/cir_candi_1.png
new file mode 100644
index 0000000..d44fabf
Binary files /dev/null and b/imgs/cir_candi_1.png differ
diff --git a/imgs/cir_candi_2.png b/imgs/cir_candi_2.png
new file mode 100644
index 0000000..143a39d
Binary files /dev/null and b/imgs/cir_candi_2.png differ
diff --git a/imgs/cir_query.png b/imgs/cir_query.png
new file mode 100644
index 0000000..4a28de6
Binary files /dev/null and b/imgs/cir_query.png differ