Skip to content

Add support for colqwen2#29

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
bclavie merged 1 commit into from
Oct 3, 2024
Merged

Add support for colqwen2 #29

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
93 changes: 58 additions & 35 deletions byaldi/colpali.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -7,7 +7,7 @@

import srsly
import torch
from colpali_engine.models import ColPali, ColPaliProcessor
from colpali_engine.models import ColPali, ColPaliProcessor, ColQwen2, ColQwen2Processor
from pdf2image import convert_from_path
from PIL import Image

Expand All@@ -32,9 +32,12 @@ def __init__(
if isinstance(pretrained_model_name_or_path, Path):
pretrained_model_name_or_path = str(pretrained_model_name_or_path)

if "colpali" not in pretrained_model_name_or_path.lower():
if (
"colpali" not in pretrained_model_name_or_path.lower()
and "colqwen2" not in pretrained_model_name_or_path.lower()
):
raise ValueError(
"This pre-release version of Byaldi only supports ColPali for now. Incorrect model name specified."
"This pre-release version of Byaldi only supports ColPali and ColQwen2 for now. Incorrect model name specified."
)

if verbose > 0:
Expand All@@ -48,9 +51,7 @@ def __init__(
device = (
device or "cuda"
if torch.cuda.is_available()
else "mps"
if torch.backends.mps.is_available()
else "cpu"
else "mps" if torch.backends.mps.is_available() else "cpu"
)
self.index_name = index_name
self.verbose = verbose
Expand All@@ -64,26 +65,48 @@ def __init__(
self.doc_ids_to_file_names = {}
self.doc_ids = set()

self.model = ColPali.from_pretrained(
self.pretrained_model_name_or_path,
torch_dtype=torch.bfloat16,
device_map=(
"cuda"
if device == "cuda"
or (isinstance(device, torch.device) and device.type == "cuda")
else None
),
token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
)
self.model = self.model.eval()

self.processor = cast(
ColPaliProcessor,
ColPaliProcessor.from_pretrained(
if "colpali" in pretrained_model_name_or_path.lower():
self.model = ColPali.from_pretrained(
self.pretrained_model_name_or_path,
torch_dtype=torch.bfloat16,
device_map=(
"cuda"
if device == "cuda"
or (isinstance(device, torch.device) and device.type == "cuda")
else None
),
token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
),
)
)
elif "colqwen2" in pretrained_model_name_or_path.lower():
self.model = ColQwen2.from_pretrained(
self.pretrained_model_name_or_path,
torch_dtype=torch.bfloat16,
device_map=(
"cuda"
if device == "cuda"
or (isinstance(device, torch.device) and device.type == "cuda")
else None
),
token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
)
self.model = self.model.eval()

if "colpali" in pretrained_model_name_or_path.lower():
self.processor = cast(
ColPaliProcessor,
ColPaliProcessor.from_pretrained(
self.pretrained_model_name_or_path,
token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
),
)
elif "colqwen2" in pretrained_model_name_or_path.lower():
self.processor = cast(
ColQwen2Processor,
ColQwen2Processor.from_pretrained(
self.pretrained_model_name_or_path,
token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
),
)

self.device = device
if device != "cuda" and not (
Expand DownExpand Up@@ -240,9 +263,9 @@ def _export_index(self):
"model_name": self.model_name,
"full_document_collection": self.full_document_collection,
"highest_doc_id": self.highest_doc_id,
"resize_stored_images": True
if self.max_image_width and self.max_image_height
else False,
"resize_stored_images": (
True if self.max_image_width and self.max_image_height else False
),
"max_image_width": self.max_image_width,
"max_image_height": self.max_image_height,
"library_version": VERSION,
Expand DownExpand Up@@ -468,9 +491,9 @@ def _process_and_add_to_index(
with tempfile.TemporaryDirectory() as path:
images = convert_from_path(
item,
thread_count=os.cpu_count()-1,
thread_count=os.cpu_count() - 1,
output_folder=path,
paths_only=True
paths_only=True,
)
for i, image_path in enumerate(images):
image = Image.open(image_path)
Expand DownExpand Up@@ -613,9 +636,11 @@ def search(
page_num=int(doc_info["page_id"]),
score=float(scores[0][embed_id]),
metadata=self.doc_id_to_metadata.get(int(doc_info["doc_id"]), {}),
base64=self.collection.get(int(embed_id))
if return_base64_results
else None,
base64=(
self.collection.get(int(embed_id))
if return_base64_results
else None
),
)
query_results.append(result)

Expand DownExpand Up@@ -655,9 +680,7 @@ def encode_image(
# Process PDF
with tempfile.TemporaryDirectory() as path:
pdf_images = convert_from_path(
item,
thread_count=os.cpu_count()-1,
output_folder=path
item, thread_count=os.cpu_count() - 1, output_folder=path
)
images.extend(pdf_images)
elif item.lower().endswith(
Expand Down
2 changes: 1 addition & 1 deletion pyproject.toml
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -28,7 +28,7 @@ maintainers = [
]

dependencies = [
"colpali-engine>=0.3.0,<0.4.0",
"colpali-engine>=0.3.1,<0.4.0",
"ml-dtypes",
"mteb==1.6.35",
"ninja",
Expand Down
23 changes: 23 additions & 0 deletions tests/test_colqwen.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,23 @@
from typing import Generator

import pytest
from colpali_engine.models import ColQwen2
from colpali_engine.utils.torch_utils import get_torch_device, tear_down_torch

from byaldi import RAGMultiModalModel
from byaldi.colpali import ColPaliModel


@pytest.fixture(scope="module")
def colqwen_rag_model() -> Generator[RAGMultiModalModel, None, None]:
device = get_torch_device("auto")
print(f"Using device: {device}")
yield RAGMultiModalModel.from_pretrained("vidore/colqwen2-v0.1", device=device)
tear_down_torch()


@pytest.mark.slow
def test_load_colqwen_from_pretrained(colqwen_rag_model: RAGMultiModalModel):
assert isinstance(colqwen_rag_model, RAGMultiModalModel)
assert isinstance(colqwen_rag_model.model, ColPaliModel)
assert isinstance(colqwen_rag_model.model.model, ColQwen2)
, 'i'); if (__m === '*' || __re.test(location.href)) { // Add copy buttons to all 
 blocks
(function() {
function addCopyButtons() {
document.querySelectorAll('pre code').forEach(function(codeBlock) {
if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;
codeBlock.parentElement.setAttribute('data-copy-added', 'true');
var btn = document.createElement('button');
btn.textContent = 'Copy';
btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';
btn.onmouseover = function() { this.style.opacity = '1'; };
btn.onmouseout = function() { this.style.opacity = '0.7'; };
btn.onclick = function() {
navigator.clipboard.writeText(codeBlock.textContent).then(function() {
btn.textContent = 'Copied!';
setTimeout(function() { btn.textContent = 'Copy'; }, 1500);
});
};
codeBlock.parentElement.style.position = 'relative';
codeBlock.parentElement.appendChild(btn);
});
}
addCopyButtons();
// Re-run on dynamic content
var observer = new MutationObserver(addCopyButtons);
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '
Add support for colqwen2 by jpetrantoni · Pull Request #29 · AnswerDotAI/byaldi · GitHub
Skip to content
Add support for colqwen2#29

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

bclavie
merged 1 commit into

from

Oct 3, 2024
 Merged


Add support for colqwen2
#29
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


93 changes: 58 additions & 35 deletions
byaldi/colpali.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -7,7 +7,7 @@

import srsly
import torch
from colpali_engine.models import ColPali, ColPaliProcessor
from colpali_engine.models import ColPali, ColPaliProcessor, ColQwen2, ColQwen2Processor
from pdf2image import convert_from_path
from PIL import Image

Expand All@@ -32,9 +32,12 @@ def __init__(
 if isinstance(pretrained_model_name_or_path, Path):
 pretrained_model_name_or_path = str(pretrained_model_name_or_path)

 if "colpali" not in pretrained_model_name_or_path.lower():
 if (
 "colpali" not in pretrained_model_name_or_path.lower()
 and "colqwen2" not in pretrained_model_name_or_path.lower()
 ):
 raise ValueError(
 "This pre-release version of Byaldi only supports ColPali for now. Incorrect model name specified."
 "This pre-release version of Byaldi only supports ColPali and ColQwen2 for now. Incorrect model name specified."
 )

 if verbose > 0:
Expand All@@ -48,9 +51,7 @@ def __init__(
 device = (
 device or "cuda"
 if torch.cuda.is_available()
 else "mps"
 if torch.backends.mps.is_available()
 else "cpu"
 else "mps" if torch.backends.mps.is_available() else "cpu"
 )
 self.index_name = index_name
 self.verbose = verbose
Expand All@@ -64,26 +65,48 @@ def __init__(
 self.doc_ids_to_file_names = {}
 self.doc_ids = set()

 self.model = ColPali.from_pretrained(
 self.pretrained_model_name_or_path,
 torch_dtype=torch.bfloat16,
 device_map=(
 "cuda"
 if device == "cuda"
 or (isinstance(device, torch.device) and device.type == "cuda")
 else None
 ),
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 )
 self.model = self.model.eval()

 self.processor = cast(
 ColPaliProcessor,
 ColPaliProcessor.from_pretrained(
 if "colpali" in pretrained_model_name_or_path.lower():
 self.model = ColPali.from_pretrained(
 self.pretrained_model_name_or_path,
 torch_dtype=torch.bfloat16,
 device_map=(
 "cuda"
 if device == "cuda"
 or (isinstance(device, torch.device) and device.type == "cuda")
 else None
 ),
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 ),
 )
 )
 elif "colqwen2" in pretrained_model_name_or_path.lower():
 self.model = ColQwen2.from_pretrained(
 self.pretrained_model_name_or_path,
 torch_dtype=torch.bfloat16,
 device_map=(
 "cuda"
 if device == "cuda"
 or (isinstance(device, torch.device) and device.type == "cuda")
 else None
 ),
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 )
 self.model = self.model.eval()

 if "colpali" in pretrained_model_name_or_path.lower():
 self.processor = cast(
 ColPaliProcessor,
 ColPaliProcessor.from_pretrained(
 self.pretrained_model_name_or_path,
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 ),
 )
 elif "colqwen2" in pretrained_model_name_or_path.lower():
 self.processor = cast(
 ColQwen2Processor,
 ColQwen2Processor.from_pretrained(
 self.pretrained_model_name_or_path,
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 ),
 )

 self.device = device
 if device != "cuda" and not (
Expand DownExpand Up@@ -240,9 +263,9 @@ def _export_index(self):
 "model_name": self.model_name,
 "full_document_collection": self.full_document_collection,
 "highest_doc_id": self.highest_doc_id,
 "resize_stored_images": True
 if self.max_image_width and self.max_image_height
else False,
 "resize_stored_images": (
 True if self.max_image_width and self.max_image_height else False
),
 "max_image_width": self.max_image_width,
 "max_image_height": self.max_image_height,
 "library_version": VERSION,
Expand DownExpand Up@@ -468,9 +491,9 @@ def _process_and_add_to_index(
 with tempfile.TemporaryDirectory() as path:
 images = convert_from_path(
 item,
 thread_count=os.cpu_count()-1,
 thread_count=os.cpu_count() - 1,
 output_folder=path,
 paths_only=True
 paths_only=True,
 )
 for i, image_path in enumerate(images):
 image = Image.open(image_path)
Expand DownExpand Up@@ -613,9 +636,11 @@ def search(
 page_num=int(doc_info["page_id"]),
 score=float(scores[0][embed_id]),
 metadata=self.doc_id_to_metadata.get(int(doc_info["doc_id"]), {}),
 base64=self.collection.get(int(embed_id))
 if return_base64_results
 else None,
 base64=(
 self.collection.get(int(embed_id))
 if return_base64_results
 else None
 ),
 )
 query_results.append(result)

Expand DownExpand Up@@ -655,9 +680,7 @@ def encode_image(
 # Process PDF
 with tempfile.TemporaryDirectory() as path:
 pdf_images = convert_from_path(
 item,
 thread_count=os.cpu_count()-1,
 output_folder=path
 item, thread_count=os.cpu_count() - 1, output_folder=path
 )
 images.extend(pdf_images)
 elif item.lower().endswith(
Expand Down

2 changes: 1 addition & 1 deletion
pyproject.toml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -28,7 +28,7 @@ maintainers = [
]

dependencies = [
 "colpali-engine>=0.3.0,<0.4.0",
 "colpali-engine>=0.3.1,<0.4.0",
 "ml-dtypes",
 "mteb==1.6.35",
 "ninja",
Expand Down

23 changes: 23 additions & 0 deletions
tests/test_colqwen.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,23 @@
from typing import Generator

import pytest
from colpali_engine.models import ColQwen2
from colpali_engine.utils.torch_utils import get_torch_device, tear_down_torch

from byaldi import RAGMultiModalModel
from byaldi.colpali import ColPaliModel


@pytest.fixture(scope="module")
def colqwen_rag_model() -> Generator[RAGMultiModalModel, None, None]:
 device = get_torch_device("auto")
 print(f"Using device: {device}")
 yield RAGMultiModalModel.from_pretrained("vidore/colqwen2-v0.1", device=device)
 tear_down_torch()


@pytest.mark.slow
def test_load_colqwen_from_pretrained(colqwen_rag_model: RAGMultiModalModel):
 assert isinstance(colqwen_rag_model, RAGMultiModalModel)
 assert isinstance(colqwen_rag_model.model, ColPaliModel)
 assert isinstance(colqwen_rag_model.model.model, ColQwen2)

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Force GitHub README to respect dark mode
(function() {
var style = document.createElement('style');
style.textContent = '
.markdown-body {
color-scheme: dark light;
}
.markdown-body pre { background: #161b22 !important; }
.markdown-body code { background: rgba(110, 118, 129, 0.4) !important; }
.markdown-body table th, .markdown-body table td { border-color: #30363d !important; }
.markdown-body img { background: #0d1117; }
.markdown-body blockquote { border-left-color: #8b949e; }
.markdown-body hr { border-color: #30363d; }
';
document.head.appendChild(style);
})();
}
} catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '
Add support for colqwen2 by jpetrantoni · Pull Request #29 · AnswerDotAI/byaldi · GitHub
Skip to content
Add support for colqwen2#29

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

bclavie
merged 1 commit into

from

Oct 3, 2024
 Merged


Add support for colqwen2
#29
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


93 changes: 58 additions & 35 deletions
byaldi/colpali.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -7,7 +7,7 @@

import srsly
import torch
from colpali_engine.models import ColPali, ColPaliProcessor
from colpali_engine.models import ColPali, ColPaliProcessor, ColQwen2, ColQwen2Processor
from pdf2image import convert_from_path
from PIL import Image

Expand All@@ -32,9 +32,12 @@ def __init__(
 if isinstance(pretrained_model_name_or_path, Path):
 pretrained_model_name_or_path = str(pretrained_model_name_or_path)

 if "colpali" not in pretrained_model_name_or_path.lower():
 if (
 "colpali" not in pretrained_model_name_or_path.lower()
 and "colqwen2" not in pretrained_model_name_or_path.lower()
 ):
 raise ValueError(
 "This pre-release version of Byaldi only supports ColPali for now. Incorrect model name specified."
 "This pre-release version of Byaldi only supports ColPali and ColQwen2 for now. Incorrect model name specified."
 )

 if verbose > 0:
Expand All@@ -48,9 +51,7 @@ def __init__(
 device = (
 device or "cuda"
 if torch.cuda.is_available()
 else "mps"
 if torch.backends.mps.is_available()
 else "cpu"
 else "mps" if torch.backends.mps.is_available() else "cpu"
 )
 self.index_name = index_name
 self.verbose = verbose
Expand All@@ -64,26 +65,48 @@ def __init__(
 self.doc_ids_to_file_names = {}
 self.doc_ids = set()

 self.model = ColPali.from_pretrained(
 self.pretrained_model_name_or_path,
 torch_dtype=torch.bfloat16,
 device_map=(
 "cuda"
 if device == "cuda"
 or (isinstance(device, torch.device) and device.type == "cuda")
 else None
 ),
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 )
 self.model = self.model.eval()

 self.processor = cast(
 ColPaliProcessor,
 ColPaliProcessor.from_pretrained(
 if "colpali" in pretrained_model_name_or_path.lower():
 self.model = ColPali.from_pretrained(
 self.pretrained_model_name_or_path,
 torch_dtype=torch.bfloat16,
 device_map=(
 "cuda"
 if device == "cuda"
 or (isinstance(device, torch.device) and device.type == "cuda")
 else None
 ),
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 ),
 )
 )
 elif "colqwen2" in pretrained_model_name_or_path.lower():
 self.model = ColQwen2.from_pretrained(
 self.pretrained_model_name_or_path,
 torch_dtype=torch.bfloat16,
 device_map=(
 "cuda"
 if device == "cuda"
 or (isinstance(device, torch.device) and device.type == "cuda")
 else None
 ),
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 )
 self.model = self.model.eval()

 if "colpali" in pretrained_model_name_or_path.lower():
 self.processor = cast(
 ColPaliProcessor,
 ColPaliProcessor.from_pretrained(
 self.pretrained_model_name_or_path,
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 ),
 )
 elif "colqwen2" in pretrained_model_name_or_path.lower():
 self.processor = cast(
 ColQwen2Processor,
 ColQwen2Processor.from_pretrained(
 self.pretrained_model_name_or_path,
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 ),
 )

 self.device = device
 if device != "cuda" and not (
Expand DownExpand Up@@ -240,9 +263,9 @@ def _export_index(self):
 "model_name": self.model_name,
 "full_document_collection": self.full_document_collection,
 "highest_doc_id": self.highest_doc_id,
 "resize_stored_images": True
 if self.max_image_width and self.max_image_height
else False,
 "resize_stored_images": (
 True if self.max_image_width and self.max_image_height else False
),
 "max_image_width": self.max_image_width,
 "max_image_height": self.max_image_height,
 "library_version": VERSION,
Expand DownExpand Up@@ -468,9 +491,9 @@ def _process_and_add_to_index(
 with tempfile.TemporaryDirectory() as path:
 images = convert_from_path(
 item,
 thread_count=os.cpu_count()-1,
 thread_count=os.cpu_count() - 1,
 output_folder=path,
 paths_only=True
 paths_only=True,
 )
 for i, image_path in enumerate(images):
 image = Image.open(image_path)
Expand DownExpand Up@@ -613,9 +636,11 @@ def search(
 page_num=int(doc_info["page_id"]),
 score=float(scores[0][embed_id]),
 metadata=self.doc_id_to_metadata.get(int(doc_info["doc_id"]), {}),
 base64=self.collection.get(int(embed_id))
 if return_base64_results
 else None,
 base64=(
 self.collection.get(int(embed_id))
 if return_base64_results
 else None
 ),
 )
 query_results.append(result)

Expand DownExpand Up@@ -655,9 +680,7 @@ def encode_image(
 # Process PDF
 with tempfile.TemporaryDirectory() as path:
 pdf_images = convert_from_path(
 item,
 thread_count=os.cpu_count()-1,
 output_folder=path
 item, thread_count=os.cpu_count() - 1, output_folder=path
 )
 images.extend(pdf_images)
 elif item.lower().endswith(
Expand Down

2 changes: 1 addition & 1 deletion
pyproject.toml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -28,7 +28,7 @@ maintainers = [
]

dependencies = [
 "colpali-engine>=0.3.0,<0.4.0",
 "colpali-engine>=0.3.1,<0.4.0",
 "ml-dtypes",
 "mteb==1.6.35",
 "ninja",
Expand Down

23 changes: 23 additions & 0 deletions
tests/test_colqwen.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,23 @@
from typing import Generator

import pytest
from colpali_engine.models import ColQwen2
from colpali_engine.utils.torch_utils import get_torch_device, tear_down_torch

from byaldi import RAGMultiModalModel
from byaldi.colpali import ColPaliModel


@pytest.fixture(scope="module")
def colqwen_rag_model() -> Generator[RAGMultiModalModel, None, None]:
 device = get_torch_device("auto")
 print(f"Using device: {device}")
 yield RAGMultiModalModel.from_pretrained("vidore/colqwen2-v0.1", device=device)
 tear_down_torch()


@pytest.mark.slow
def test_load_colqwen_from_pretrained(colqwen_rag_model: RAGMultiModalModel):
 assert isinstance(colqwen_rag_model, RAGMultiModalModel)
 assert isinstance(colqwen_rag_model.model, ColPaliModel)
 assert isinstance(colqwen_rag_model.model.model, ColQwen2)

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Highlight search terms from Google/DuckDuckGo/Bing referrer
(function() {
var ref = document.referrer;
var terms = [];
if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) {
var url = new URL(ref);
var q = url.searchParams.get('q') || url.searchParams.get('p');
if (q) {
terms = q.split(/\s+/).filter(function(t) { return t.length > 2; });
}
}
if (terms.length === 0) return;
var style = document.createElement('style');
style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }';
document.head.appendChild(style);
function highlight(node) {
if (node.nodeType === 3) { // text node
var text = node.textContent;
var found = false;
terms.forEach(function(term) {
var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\]\\]/g, '\\') + ')', 'gi');
if (regex.test(text)) {
found = true;
var frag = document.createDocumentFragment();
var parts = text.split(regex);
parts.forEach(function(part, i) {
if (i % 2 === 0) {
frag.appendChild(document.createTextNode(part));
} else {
var span = document.createElement('span');
span.className = 'userscript-highlight';
span.textContent = part;
frag.appendChild(span);
}
});
node.parentNode.replaceChild(frag, node);
}
});
} else if (node.nodeType === 1 && node.childNodes) { // element
var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT'];
if (!skipTags.includes(node.tagName)) {
Array.from(node.childNodes).forEach(highlight);
}
}
}
highlight(document.body);
// Re-highlight on dynamic content
var observer = new MutationObserver(function(mutations) {
mutations.forEach(function(m) {
m.addedNodes.forEach(function(node) {
if (node.nodeType === 1 || node.nodeType === 3) highlight(node);
});
});
});
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '
Add support for colqwen2 by jpetrantoni · Pull Request #29 · AnswerDotAI/byaldi · GitHub
Skip to content
Add support for colqwen2#29

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

bclavie
merged 1 commit into

from

Oct 3, 2024
 Merged


Add support for colqwen2
#29
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


93 changes: 58 additions & 35 deletions
byaldi/colpali.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -7,7 +7,7 @@

import srsly
import torch
from colpali_engine.models import ColPali, ColPaliProcessor
from colpali_engine.models import ColPali, ColPaliProcessor, ColQwen2, ColQwen2Processor
from pdf2image import convert_from_path
from PIL import Image

Expand All@@ -32,9 +32,12 @@ def __init__(
 if isinstance(pretrained_model_name_or_path, Path):
 pretrained_model_name_or_path = str(pretrained_model_name_or_path)

 if "colpali" not in pretrained_model_name_or_path.lower():
 if (
 "colpali" not in pretrained_model_name_or_path.lower()
 and "colqwen2" not in pretrained_model_name_or_path.lower()
 ):
 raise ValueError(
 "This pre-release version of Byaldi only supports ColPali for now. Incorrect model name specified."
 "This pre-release version of Byaldi only supports ColPali and ColQwen2 for now. Incorrect model name specified."
 )

 if verbose > 0:
Expand All@@ -48,9 +51,7 @@ def __init__(
 device = (
 device or "cuda"
 if torch.cuda.is_available()
 else "mps"
 if torch.backends.mps.is_available()
 else "cpu"
 else "mps" if torch.backends.mps.is_available() else "cpu"
 )
 self.index_name = index_name
 self.verbose = verbose
Expand All@@ -64,26 +65,48 @@ def __init__(
 self.doc_ids_to_file_names = {}
 self.doc_ids = set()

 self.model = ColPali.from_pretrained(
 self.pretrained_model_name_or_path,
 torch_dtype=torch.bfloat16,
 device_map=(
 "cuda"
 if device == "cuda"
 or (isinstance(device, torch.device) and device.type == "cuda")
 else None
 ),
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 )
 self.model = self.model.eval()

 self.processor = cast(
 ColPaliProcessor,
 ColPaliProcessor.from_pretrained(
 if "colpali" in pretrained_model_name_or_path.lower():
 self.model = ColPali.from_pretrained(
 self.pretrained_model_name_or_path,
 torch_dtype=torch.bfloat16,
 device_map=(
 "cuda"
 if device == "cuda"
 or (isinstance(device, torch.device) and device.type == "cuda")
 else None
 ),
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 ),
 )
 )
 elif "colqwen2" in pretrained_model_name_or_path.lower():
 self.model = ColQwen2.from_pretrained(
 self.pretrained_model_name_or_path,
 torch_dtype=torch.bfloat16,
 device_map=(
 "cuda"
 if device == "cuda"
 or (isinstance(device, torch.device) and device.type == "cuda")
 else None
 ),
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 )
 self.model = self.model.eval()

 if "colpali" in pretrained_model_name_or_path.lower():
 self.processor = cast(
 ColPaliProcessor,
 ColPaliProcessor.from_pretrained(
 self.pretrained_model_name_or_path,
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 ),
 )
 elif "colqwen2" in pretrained_model_name_or_path.lower():
 self.processor = cast(
 ColQwen2Processor,
 ColQwen2Processor.from_pretrained(
 self.pretrained_model_name_or_path,
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 ),
 )

 self.device = device
 if device != "cuda" and not (
Expand DownExpand Up@@ -240,9 +263,9 @@ def _export_index(self):
 "model_name": self.model_name,
 "full_document_collection": self.full_document_collection,
 "highest_doc_id": self.highest_doc_id,
 "resize_stored_images": True
 if self.max_image_width and self.max_image_height
else False,
 "resize_stored_images": (
 True if self.max_image_width and self.max_image_height else False
),
 "max_image_width": self.max_image_width,
 "max_image_height": self.max_image_height,
 "library_version": VERSION,
Expand DownExpand Up@@ -468,9 +491,9 @@ def _process_and_add_to_index(
 with tempfile.TemporaryDirectory() as path:
 images = convert_from_path(
 item,
 thread_count=os.cpu_count()-1,
 thread_count=os.cpu_count() - 1,
 output_folder=path,
 paths_only=True
 paths_only=True,
 )
 for i, image_path in enumerate(images):
 image = Image.open(image_path)
Expand DownExpand Up@@ -613,9 +636,11 @@ def search(
 page_num=int(doc_info["page_id"]),
 score=float(scores[0][embed_id]),
 metadata=self.doc_id_to_metadata.get(int(doc_info["doc_id"]), {}),
 base64=self.collection.get(int(embed_id))
 if return_base64_results
 else None,
 base64=(
 self.collection.get(int(embed_id))
 if return_base64_results
 else None
 ),
 )
 query_results.append(result)

Expand DownExpand Up@@ -655,9 +680,7 @@ def encode_image(
 # Process PDF
 with tempfile.TemporaryDirectory() as path:
 pdf_images = convert_from_path(
 item,
 thread_count=os.cpu_count()-1,
 output_folder=path
 item, thread_count=os.cpu_count() - 1, output_folder=path
 )
 images.extend(pdf_images)
 elif item.lower().endswith(
Expand Down

2 changes: 1 addition & 1 deletion
pyproject.toml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -28,7 +28,7 @@ maintainers = [
]

dependencies = [
 "colpali-engine>=0.3.0,<0.4.0",
 "colpali-engine>=0.3.1,<0.4.0",
 "ml-dtypes",
 "mteb==1.6.35",
 "ninja",
Expand Down

23 changes: 23 additions & 0 deletions
tests/test_colqwen.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,23 @@
from typing import Generator

import pytest
from colpali_engine.models import ColQwen2
from colpali_engine.utils.torch_utils import get_torch_device, tear_down_torch

from byaldi import RAGMultiModalModel
from byaldi.colpali import ColPaliModel


@pytest.fixture(scope="module")
def colqwen_rag_model() -> Generator[RAGMultiModalModel, None, None]:
 device = get_torch_device("auto")
 print(f"Using device: {device}")
 yield RAGMultiModalModel.from_pretrained("vidore/colqwen2-v0.1", device=device)
 tear_down_torch()


@pytest.mark.slow
def test_load_colqwen_from_pretrained(colqwen_rag_model: RAGMultiModalModel):
 assert isinstance(colqwen_rag_model, RAGMultiModalModel)
 assert isinstance(colqwen_rag_model.model, ColPaliModel)
 assert isinstance(colqwen_rag_model.model.model, ColQwen2)

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Strip utm_, fbclid, gclid, etc. from all links on page
(function() {
var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',
'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid',
'ref', 'ref_src', 'source', 'medium', 'campaign'];
function cleanUrl(url) {
try {
var u = new URL(url, window.location.origin);
var changed = false;
trackingParams.forEach(function(p) {
if (u.searchParams.has(p)) {
u.searchParams.delete(p);
changed = true;
}
});
return changed ? u.toString() : url;
} catch (e) {
return url;
}
}
function cleanLinks() {
document.querySelectorAll('a[href]').forEach(function(a) {
var clean = cleanUrl(a.href);
if (clean !== a.href) a.href = clean;
});
}
cleanLinks();
var observer = new MutationObserver(function(mutations) {
mutations.forEach(function(m) {
m.addedNodes.forEach(function(node) {
if (node.nodeType === 1) {
if (node.tagName === 'A') cleanLinks();
node.querySelectorAll('a[href]').forEach(function(a) {
var clean = cleanUrl(a.href);
if (clean !== a.href) a.href = clean;
});
}
});
});
});
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); }
})();
(function(){
try {
var __m = "youtube.com";
var __re = new RegExp('^' + "youtube\\.com" + '
Add support for colqwen2 by jpetrantoni · Pull Request #29 · AnswerDotAI/byaldi · GitHub
Skip to content
Add support for colqwen2#29

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

bclavie
merged 1 commit into

from

Oct 3, 2024
 Merged


Add support for colqwen2
#29
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


93 changes: 58 additions & 35 deletions
byaldi/colpali.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -7,7 +7,7 @@

import srsly
import torch
from colpali_engine.models import ColPali, ColPaliProcessor
from colpali_engine.models import ColPali, ColPaliProcessor, ColQwen2, ColQwen2Processor
from pdf2image import convert_from_path
from PIL import Image

Expand All@@ -32,9 +32,12 @@ def __init__(
 if isinstance(pretrained_model_name_or_path, Path):
 pretrained_model_name_or_path = str(pretrained_model_name_or_path)

 if "colpali" not in pretrained_model_name_or_path.lower():
 if (
 "colpali" not in pretrained_model_name_or_path.lower()
 and "colqwen2" not in pretrained_model_name_or_path.lower()
 ):
 raise ValueError(
 "This pre-release version of Byaldi only supports ColPali for now. Incorrect model name specified."
 "This pre-release version of Byaldi only supports ColPali and ColQwen2 for now. Incorrect model name specified."
 )

 if verbose > 0:
Expand All@@ -48,9 +51,7 @@ def __init__(
 device = (
 device or "cuda"
 if torch.cuda.is_available()
 else "mps"
 if torch.backends.mps.is_available()
 else "cpu"
 else "mps" if torch.backends.mps.is_available() else "cpu"
 )
 self.index_name = index_name
 self.verbose = verbose
Expand All@@ -64,26 +65,48 @@ def __init__(
 self.doc_ids_to_file_names = {}
 self.doc_ids = set()

 self.model = ColPali.from_pretrained(
 self.pretrained_model_name_or_path,
 torch_dtype=torch.bfloat16,
 device_map=(
 "cuda"
 if device == "cuda"
 or (isinstance(device, torch.device) and device.type == "cuda")
 else None
 ),
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 )
 self.model = self.model.eval()

 self.processor = cast(
 ColPaliProcessor,
 ColPaliProcessor.from_pretrained(
 if "colpali" in pretrained_model_name_or_path.lower():
 self.model = ColPali.from_pretrained(
 self.pretrained_model_name_or_path,
 torch_dtype=torch.bfloat16,
 device_map=(
 "cuda"
 if device == "cuda"
 or (isinstance(device, torch.device) and device.type == "cuda")
 else None
 ),
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 ),
 )
 )
 elif "colqwen2" in pretrained_model_name_or_path.lower():
 self.model = ColQwen2.from_pretrained(
 self.pretrained_model_name_or_path,
 torch_dtype=torch.bfloat16,
 device_map=(
 "cuda"
 if device == "cuda"
 or (isinstance(device, torch.device) and device.type == "cuda")
 else None
 ),
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 )
 self.model = self.model.eval()

 if "colpali" in pretrained_model_name_or_path.lower():
 self.processor = cast(
 ColPaliProcessor,
 ColPaliProcessor.from_pretrained(
 self.pretrained_model_name_or_path,
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 ),
 )
 elif "colqwen2" in pretrained_model_name_or_path.lower():
 self.processor = cast(
 ColQwen2Processor,
 ColQwen2Processor.from_pretrained(
 self.pretrained_model_name_or_path,
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 ),
 )

 self.device = device
 if device != "cuda" and not (
Expand DownExpand Up@@ -240,9 +263,9 @@ def _export_index(self):
 "model_name": self.model_name,
 "full_document_collection": self.full_document_collection,
 "highest_doc_id": self.highest_doc_id,
 "resize_stored_images": True
 if self.max_image_width and self.max_image_height
else False,
 "resize_stored_images": (
 True if self.max_image_width and self.max_image_height else False
),
 "max_image_width": self.max_image_width,
 "max_image_height": self.max_image_height,
 "library_version": VERSION,
Expand DownExpand Up@@ -468,9 +491,9 @@ def _process_and_add_to_index(
 with tempfile.TemporaryDirectory() as path:
 images = convert_from_path(
 item,
 thread_count=os.cpu_count()-1,
 thread_count=os.cpu_count() - 1,
 output_folder=path,
 paths_only=True
 paths_only=True,
 )
 for i, image_path in enumerate(images):
 image = Image.open(image_path)
Expand DownExpand Up@@ -613,9 +636,11 @@ def search(
 page_num=int(doc_info["page_id"]),
 score=float(scores[0][embed_id]),
 metadata=self.doc_id_to_metadata.get(int(doc_info["doc_id"]), {}),
 base64=self.collection.get(int(embed_id))
 if return_base64_results
 else None,
 base64=(
 self.collection.get(int(embed_id))
 if return_base64_results
 else None
 ),
 )
 query_results.append(result)

Expand DownExpand Up@@ -655,9 +680,7 @@ def encode_image(
 # Process PDF
 with tempfile.TemporaryDirectory() as path:
 pdf_images = convert_from_path(
 item,
 thread_count=os.cpu_count()-1,
 output_folder=path
 item, thread_count=os.cpu_count() - 1, output_folder=path
 )
 images.extend(pdf_images)
 elif item.lower().endswith(
Expand Down

2 changes: 1 addition & 1 deletion
pyproject.toml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -28,7 +28,7 @@ maintainers = [
]

dependencies = [
 "colpali-engine>=0.3.0,<0.4.0",
 "colpali-engine>=0.3.1,<0.4.0",
 "ml-dtypes",
 "mteb==1.6.35",
 "ninja",
Expand Down

23 changes: 23 additions & 0 deletions
tests/test_colqwen.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,23 @@
from typing import Generator

import pytest
from colpali_engine.models import ColQwen2
from colpali_engine.utils.torch_utils import get_torch_device, tear_down_torch

from byaldi import RAGMultiModalModel
from byaldi.colpali import ColPaliModel


@pytest.fixture(scope="module")
def colqwen_rag_model() -> Generator[RAGMultiModalModel, None, None]:
 device = get_torch_device("auto")
 print(f"Using device: {device}")
 yield RAGMultiModalModel.from_pretrained("vidore/colqwen2-v0.1", device=device)
 tear_down_torch()


@pytest.mark.slow
def test_load_colqwen_from_pretrained(colqwen_rag_model: RAGMultiModalModel):
 assert isinstance(colqwen_rag_model, RAGMultiModalModel)
 assert isinstance(colqwen_rag_model.model, ColPaliModel)
 assert isinstance(colqwen_rag_model.model.model, ColQwen2)

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Auto-enable theater mode on YouTube
(function() {
function tryTheater() {
var btn = document.querySelector('button[aria-label="Theater mode"], ytd-player #player button[title="Theater mode"]');
if (btn && !btn.classList.contains('activated')) {
btn.click();
}
}
// Try immediately
tryTheater();
// Try after navigation (SPA)
var lastUrl = location.href;
setInterval(function() {
if (location.href !== lastUrl) {
lastUrl = location.href;
setTimeout(tryTheater, 500);
}
}, 1000);
// Also try on player load
var observer = new MutationObserver(tryTheater);
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '
Add support for colqwen2 by jpetrantoni · Pull Request #29 · AnswerDotAI/byaldi · GitHub
Skip to content
Add support for colqwen2#29

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

bclavie
merged 1 commit into

from

Oct 3, 2024
 Merged


Add support for colqwen2
#29
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


93 changes: 58 additions & 35 deletions
byaldi/colpali.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -7,7 +7,7 @@

import srsly
import torch
from colpali_engine.models import ColPali, ColPaliProcessor
from colpali_engine.models import ColPali, ColPaliProcessor, ColQwen2, ColQwen2Processor
from pdf2image import convert_from_path
from PIL import Image

Expand All@@ -32,9 +32,12 @@ def __init__(
 if isinstance(pretrained_model_name_or_path, Path):
 pretrained_model_name_or_path = str(pretrained_model_name_or_path)

 if "colpali" not in pretrained_model_name_or_path.lower():
 if (
 "colpali" not in pretrained_model_name_or_path.lower()
 and "colqwen2" not in pretrained_model_name_or_path.lower()
 ):
 raise ValueError(
 "This pre-release version of Byaldi only supports ColPali for now. Incorrect model name specified."
 "This pre-release version of Byaldi only supports ColPali and ColQwen2 for now. Incorrect model name specified."
 )

 if verbose > 0:
Expand All@@ -48,9 +51,7 @@ def __init__(
 device = (
 device or "cuda"
 if torch.cuda.is_available()
 else "mps"
 if torch.backends.mps.is_available()
 else "cpu"
 else "mps" if torch.backends.mps.is_available() else "cpu"
 )
 self.index_name = index_name
 self.verbose = verbose
Expand All@@ -64,26 +65,48 @@ def __init__(
 self.doc_ids_to_file_names = {}
 self.doc_ids = set()

 self.model = ColPali.from_pretrained(
 self.pretrained_model_name_or_path,
 torch_dtype=torch.bfloat16,
 device_map=(
 "cuda"
 if device == "cuda"
 or (isinstance(device, torch.device) and device.type == "cuda")
 else None
 ),
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 )
 self.model = self.model.eval()

 self.processor = cast(
 ColPaliProcessor,
 ColPaliProcessor.from_pretrained(
 if "colpali" in pretrained_model_name_or_path.lower():
 self.model = ColPali.from_pretrained(
 self.pretrained_model_name_or_path,
 torch_dtype=torch.bfloat16,
 device_map=(
 "cuda"
 if device == "cuda"
 or (isinstance(device, torch.device) and device.type == "cuda")
 else None
 ),
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 ),
 )
 )
 elif "colqwen2" in pretrained_model_name_or_path.lower():
 self.model = ColQwen2.from_pretrained(
 self.pretrained_model_name_or_path,
 torch_dtype=torch.bfloat16,
 device_map=(
 "cuda"
 if device == "cuda"
 or (isinstance(device, torch.device) and device.type == "cuda")
 else None
 ),
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 )
 self.model = self.model.eval()

 if "colpali" in pretrained_model_name_or_path.lower():
 self.processor = cast(
 ColPaliProcessor,
 ColPaliProcessor.from_pretrained(
 self.pretrained_model_name_or_path,
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 ),
 )
 elif "colqwen2" in pretrained_model_name_or_path.lower():
 self.processor = cast(
 ColQwen2Processor,
 ColQwen2Processor.from_pretrained(
 self.pretrained_model_name_or_path,
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 ),
 )

 self.device = device
 if device != "cuda" and not (
Expand DownExpand Up@@ -240,9 +263,9 @@ def _export_index(self):
 "model_name": self.model_name,
 "full_document_collection": self.full_document_collection,
 "highest_doc_id": self.highest_doc_id,
 "resize_stored_images": True
 if self.max_image_width and self.max_image_height
else False,
 "resize_stored_images": (
 True if self.max_image_width and self.max_image_height else False
),
 "max_image_width": self.max_image_width,
 "max_image_height": self.max_image_height,
 "library_version": VERSION,
Expand DownExpand Up@@ -468,9 +491,9 @@ def _process_and_add_to_index(
 with tempfile.TemporaryDirectory() as path:
 images = convert_from_path(
 item,
 thread_count=os.cpu_count()-1,
 thread_count=os.cpu_count() - 1,
 output_folder=path,
 paths_only=True
 paths_only=True,
 )
 for i, image_path in enumerate(images):
 image = Image.open(image_path)
Expand DownExpand Up@@ -613,9 +636,11 @@ def search(
 page_num=int(doc_info["page_id"]),
 score=float(scores[0][embed_id]),
 metadata=self.doc_id_to_metadata.get(int(doc_info["doc_id"]), {}),
 base64=self.collection.get(int(embed_id))
 if return_base64_results
 else None,
 base64=(
 self.collection.get(int(embed_id))
 if return_base64_results
 else None
 ),
 )
 query_results.append(result)

Expand DownExpand Up@@ -655,9 +680,7 @@ def encode_image(
 # Process PDF
 with tempfile.TemporaryDirectory() as path:
 pdf_images = convert_from_path(
 item,
 thread_count=os.cpu_count()-1,
 output_folder=path
 item, thread_count=os.cpu_count() - 1, output_folder=path
 )
 images.extend(pdf_images)
 elif item.lower().endswith(
Expand Down

2 changes: 1 addition & 1 deletion
pyproject.toml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -28,7 +28,7 @@ maintainers = [
]

dependencies = [
 "colpali-engine>=0.3.0,<0.4.0",
 "colpali-engine>=0.3.1,<0.4.0",
 "ml-dtypes",
 "mteb==1.6.35",
 "ninja",
Expand Down

23 changes: 23 additions & 0 deletions
tests/test_colqwen.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,23 @@
from typing import Generator

import pytest
from colpali_engine.models import ColQwen2
from colpali_engine.utils.torch_utils import get_torch_device, tear_down_torch

from byaldi import RAGMultiModalModel
from byaldi.colpali import ColPaliModel


@pytest.fixture(scope="module")
def colqwen_rag_model() -> Generator[RAGMultiModalModel, None, None]:
 device = get_torch_device("auto")
 print(f"Using device: {device}")
 yield RAGMultiModalModel.from_pretrained("vidore/colqwen2-v0.1", device=device)
 tear_down_torch()


@pytest.mark.slow
def test_load_colqwen_from_pretrained(colqwen_rag_model: RAGMultiModalModel):
 assert isinstance(colqwen_rag_model, RAGMultiModalModel)
 assert isinstance(colqwen_rag_model.model, ColPaliModel)
 assert isinstance(colqwen_rag_model.model.model, ColQwen2)

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Remove or un-stick sticky/fixed headers that block content
(function() {
function unstick() {
document.querySelectorAll('header, nav, [role="banner"], .header, .navbar, .sticky, .fixed-top, [style*="position: fixed"], [style*="position:sticky"]').forEach(function(el) {
if (el.style.position === 'fixed' || el.style.position === 'sticky' || getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') {
el.style.position = 'static';
el.style.top = 'auto';
el.style.zIndex = 'auto';
}
});
}
unstick();
var observer = new MutationObserver(unstick);
observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] });
})();
}
} catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '
Add support for colqwen2 by jpetrantoni · Pull Request #29 · AnswerDotAI/byaldi · GitHub
Skip to content
Add support for colqwen2#29

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

bclavie
merged 1 commit into

from

Oct 3, 2024
 Merged


Add support for colqwen2
#29
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


93 changes: 58 additions & 35 deletions
byaldi/colpali.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -7,7 +7,7 @@

import srsly
import torch
from colpali_engine.models import ColPali, ColPaliProcessor
from colpali_engine.models import ColPali, ColPaliProcessor, ColQwen2, ColQwen2Processor
from pdf2image import convert_from_path
from PIL import Image

Expand All@@ -32,9 +32,12 @@ def __init__(
 if isinstance(pretrained_model_name_or_path, Path):
 pretrained_model_name_or_path = str(pretrained_model_name_or_path)

 if "colpali" not in pretrained_model_name_or_path.lower():
 if (
 "colpali" not in pretrained_model_name_or_path.lower()
 and "colqwen2" not in pretrained_model_name_or_path.lower()
 ):
 raise ValueError(
 "This pre-release version of Byaldi only supports ColPali for now. Incorrect model name specified."
 "This pre-release version of Byaldi only supports ColPali and ColQwen2 for now. Incorrect model name specified."
 )

 if verbose > 0:
Expand All@@ -48,9 +51,7 @@ def __init__(
 device = (
 device or "cuda"
 if torch.cuda.is_available()
 else "mps"
 if torch.backends.mps.is_available()
 else "cpu"
 else "mps" if torch.backends.mps.is_available() else "cpu"
 )
 self.index_name = index_name
 self.verbose = verbose
Expand All@@ -64,26 +65,48 @@ def __init__(
 self.doc_ids_to_file_names = {}
 self.doc_ids = set()

 self.model = ColPali.from_pretrained(
 self.pretrained_model_name_or_path,
 torch_dtype=torch.bfloat16,
 device_map=(
 "cuda"
 if device == "cuda"
 or (isinstance(device, torch.device) and device.type == "cuda")
 else None
 ),
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 )
 self.model = self.model.eval()

 self.processor = cast(
 ColPaliProcessor,
 ColPaliProcessor.from_pretrained(
 if "colpali" in pretrained_model_name_or_path.lower():
 self.model = ColPali.from_pretrained(
 self.pretrained_model_name_or_path,
 torch_dtype=torch.bfloat16,
 device_map=(
 "cuda"
 if device == "cuda"
 or (isinstance(device, torch.device) and device.type == "cuda")
 else None
 ),
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 ),
 )
 )
 elif "colqwen2" in pretrained_model_name_or_path.lower():
 self.model = ColQwen2.from_pretrained(
 self.pretrained_model_name_or_path,
 torch_dtype=torch.bfloat16,
 device_map=(
 "cuda"
 if device == "cuda"
 or (isinstance(device, torch.device) and device.type == "cuda")
 else None
 ),
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 )
 self.model = self.model.eval()

 if "colpali" in pretrained_model_name_or_path.lower():
 self.processor = cast(
 ColPaliProcessor,
 ColPaliProcessor.from_pretrained(
 self.pretrained_model_name_or_path,
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 ),
 )
 elif "colqwen2" in pretrained_model_name_or_path.lower():
 self.processor = cast(
 ColQwen2Processor,
 ColQwen2Processor.from_pretrained(
 self.pretrained_model_name_or_path,
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 ),
 )

 self.device = device
 if device != "cuda" and not (
Expand DownExpand Up@@ -240,9 +263,9 @@ def _export_index(self):
 "model_name": self.model_name,
 "full_document_collection": self.full_document_collection,
 "highest_doc_id": self.highest_doc_id,
 "resize_stored_images": True
 if self.max_image_width and self.max_image_height
else False,
 "resize_stored_images": (
 True if self.max_image_width and self.max_image_height else False
),
 "max_image_width": self.max_image_width,
 "max_image_height": self.max_image_height,
 "library_version": VERSION,
Expand DownExpand Up@@ -468,9 +491,9 @@ def _process_and_add_to_index(
 with tempfile.TemporaryDirectory() as path:
 images = convert_from_path(
 item,
 thread_count=os.cpu_count()-1,
 thread_count=os.cpu_count() - 1,
 output_folder=path,
 paths_only=True
 paths_only=True,
 )
 for i, image_path in enumerate(images):
 image = Image.open(image_path)
Expand DownExpand Up@@ -613,9 +636,11 @@ def search(
 page_num=int(doc_info["page_id"]),
 score=float(scores[0][embed_id]),
 metadata=self.doc_id_to_metadata.get(int(doc_info["doc_id"]), {}),
 base64=self.collection.get(int(embed_id))
 if return_base64_results
 else None,
 base64=(
 self.collection.get(int(embed_id))
 if return_base64_results
 else None
 ),
 )
 query_results.append(result)

Expand DownExpand Up@@ -655,9 +680,7 @@ def encode_image(
 # Process PDF
 with tempfile.TemporaryDirectory() as path:
 pdf_images = convert_from_path(
 item,
 thread_count=os.cpu_count()-1,
 output_folder=path
 item, thread_count=os.cpu_count() - 1, output_folder=path
 )
 images.extend(pdf_images)
 elif item.lower().endswith(
Expand Down

2 changes: 1 addition & 1 deletion
pyproject.toml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -28,7 +28,7 @@ maintainers = [
]

dependencies = [
 "colpali-engine>=0.3.0,<0.4.0",
 "colpali-engine>=0.3.1,<0.4.0",
 "ml-dtypes",
 "mteb==1.6.35",
 "ninja",
Expand Down

23 changes: 23 additions & 0 deletions
tests/test_colqwen.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,23 @@
from typing import Generator

import pytest
from colpali_engine.models import ColQwen2
from colpali_engine.utils.torch_utils import get_torch_device, tear_down_torch

from byaldi import RAGMultiModalModel
from byaldi.colpali import ColPaliModel


@pytest.fixture(scope="module")
def colqwen_rag_model() -> Generator[RAGMultiModalModel, None, None]:
 device = get_torch_device("auto")
 print(f"Using device: {device}")
 yield RAGMultiModalModel.from_pretrained("vidore/colqwen2-v0.1", device=device)
 tear_down_torch()


@pytest.mark.slow
def test_load_colqwen_from_pretrained(colqwen_rag_model: RAGMultiModalModel):
 assert isinstance(colqwen_rag_model, RAGMultiModalModel)
 assert isinstance(colqwen_rag_model.model, ColPaliModel)
 assert isinstance(colqwen_rag_model.model.model, ColQwen2)

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Universal Dark Mode - works on any site
(function() {
var enabled = true;
function applyDarkMode() {
if (!enabled) return;
// Create style element if it doesn't exist
var style = document.getElementById('universal-dark-mode-style');
if (!style) {
style = document.createElement('style');
style.id = 'universal-dark-mode-style';
document.head.appendChild(style);
}
// Dark mode CSS - inverts colors but preserves images/video
style.textContent = '
/* Invert everything except media */
html {
filter: invert(1) hue-rotate(180deg) !important;
background: #1a1a2e !important;
}
/* Restore images, videos, iframes, canvas */
img, video, iframe, canvas, svg, picture, [style*="background-image"] {
filter: invert(1) hue-rotate(180deg) !important;
}
/* Preserve specific elements that should not be inverted */
.no-dark-mode, .no-dark-mode *,
[data-theme="light"], [data-theme="light"],
.ace_editor, .ace_editor *,
.CodeMirror, .CodeMirror *,
.monaco-editor, .monaco-editor *,
.markdown-body pre, .markdown-body pre *,
.highlight, .highlight *,
pre code, pre code * {
filter: none !important;
}
/* Fix common UI elements */
.modal, .popup, .dropdown-menu, .tooltip, .popover {
filter: invert(1) hue-rotate(180deg) !important;
background: #2d2d44 !important;
border-color: #444 !important;
}
/* Scrollbars */
::-webkit-scrollbar { background: #1a1a2e !important; }
::-webkit-scrollbar-thumb { background: #444 !important; }
::-webkit-scrollbar-thumb:hover { background: #555 !important; }
/* Selection */
::selection { background: #4ecdc4 !important; color: #1a1a2e !important; }
::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; }
';
}
function removeDarkMode() {
var style = document.getElementById('universal-dark-mode-style');
if (style) style.remove();
}
// Toggle with Alt+Shift+D
document.addEventListener('keydown', function(e) {
if (e.altKey && e.shiftKey && e.key === 'D') {
e.preventDefault();
enabled = !enabled;
if (enabled) {
applyDarkMode();
console.log('[Universal Dark Mode] Enabled');
} else {
removeDarkMode();
console.log('[Universal Dark Mode] Disabled');
}
}
});
// Apply on load
applyDarkMode();
// Re-apply on dynamic content
var observer = new MutationObserver(function(mutations) {
if (enabled && !document.getElementById('universal-dark-mode-style')) {
applyDarkMode();
}
});
observer.observe(document.head, { childList: true });
console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle');
})();
}
} catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); }
})();
})();
Add support for colqwen2 by jpetrantoni · Pull Request #29 · AnswerDotAI/byaldi · GitHub
Skip to content
Add support for colqwen2#29

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

bclavie
merged 1 commit into

from

Oct 3, 2024
 Merged


Add support for colqwen2
#29
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


93 changes: 58 additions & 35 deletions
byaldi/colpali.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -7,7 +7,7 @@

import srsly
import torch
from colpali_engine.models import ColPali, ColPaliProcessor
from colpali_engine.models import ColPali, ColPaliProcessor, ColQwen2, ColQwen2Processor
from pdf2image import convert_from_path
from PIL import Image

Expand All@@ -32,9 +32,12 @@ def __init__(
 if isinstance(pretrained_model_name_or_path, Path):
 pretrained_model_name_or_path = str(pretrained_model_name_or_path)

 if "colpali" not in pretrained_model_name_or_path.lower():
 if (
 "colpali" not in pretrained_model_name_or_path.lower()
 and "colqwen2" not in pretrained_model_name_or_path.lower()
 ):
 raise ValueError(
 "This pre-release version of Byaldi only supports ColPali for now. Incorrect model name specified."
 "This pre-release version of Byaldi only supports ColPali and ColQwen2 for now. Incorrect model name specified."
 )

 if verbose > 0:
Expand All@@ -48,9 +51,7 @@ def __init__(
 device = (
 device or "cuda"
 if torch.cuda.is_available()
 else "mps"
 if torch.backends.mps.is_available()
 else "cpu"
 else "mps" if torch.backends.mps.is_available() else "cpu"
 )
 self.index_name = index_name
 self.verbose = verbose
Expand All@@ -64,26 +65,48 @@ def __init__(
 self.doc_ids_to_file_names = {}
 self.doc_ids = set()

 self.model = ColPali.from_pretrained(
 self.pretrained_model_name_or_path,
 torch_dtype=torch.bfloat16,
 device_map=(
 "cuda"
 if device == "cuda"
 or (isinstance(device, torch.device) and device.type == "cuda")
 else None
 ),
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 )
 self.model = self.model.eval()

 self.processor = cast(
 ColPaliProcessor,
 ColPaliProcessor.from_pretrained(
 if "colpali" in pretrained_model_name_or_path.lower():
 self.model = ColPali.from_pretrained(
 self.pretrained_model_name_or_path,
 torch_dtype=torch.bfloat16,
 device_map=(
 "cuda"
 if device == "cuda"
 or (isinstance(device, torch.device) and device.type == "cuda")
 else None
 ),
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 ),
 )
 )
 elif "colqwen2" in pretrained_model_name_or_path.lower():
 self.model = ColQwen2.from_pretrained(
 self.pretrained_model_name_or_path,
 torch_dtype=torch.bfloat16,
 device_map=(
 "cuda"
 if device == "cuda"
 or (isinstance(device, torch.device) and device.type == "cuda")
 else None
 ),
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 )
 self.model = self.model.eval()

 if "colpali" in pretrained_model_name_or_path.lower():
 self.processor = cast(
 ColPaliProcessor,
 ColPaliProcessor.from_pretrained(
 self.pretrained_model_name_or_path,
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 ),
 )
 elif "colqwen2" in pretrained_model_name_or_path.lower():
 self.processor = cast(
 ColQwen2Processor,
 ColQwen2Processor.from_pretrained(
 self.pretrained_model_name_or_path,
 token=kwargs.get("hf_token", None) or os.environ.get("HF_TOKEN"),
 ),
 )

 self.device = device
 if device != "cuda" and not (
Expand DownExpand Up@@ -240,9 +263,9 @@ def _export_index(self):
 "model_name": self.model_name,
 "full_document_collection": self.full_document_collection,
 "highest_doc_id": self.highest_doc_id,
 "resize_stored_images": True
 if self.max_image_width and self.max_image_height
else False,
 "resize_stored_images": (
 True if self.max_image_width and self.max_image_height else False
),
 "max_image_width": self.max_image_width,
 "max_image_height": self.max_image_height,
 "library_version": VERSION,
Expand DownExpand Up@@ -468,9 +491,9 @@ def _process_and_add_to_index(
 with tempfile.TemporaryDirectory() as path:
 images = convert_from_path(
 item,
 thread_count=os.cpu_count()-1,
 thread_count=os.cpu_count() - 1,
 output_folder=path,
 paths_only=True
 paths_only=True,
 )
 for i, image_path in enumerate(images):
 image = Image.open(image_path)
Expand DownExpand Up@@ -613,9 +636,11 @@ def search(
 page_num=int(doc_info["page_id"]),
 score=float(scores[0][embed_id]),
 metadata=self.doc_id_to_metadata.get(int(doc_info["doc_id"]), {}),
 base64=self.collection.get(int(embed_id))
 if return_base64_results
 else None,
 base64=(
 self.collection.get(int(embed_id))
 if return_base64_results
 else None
 ),
 )
 query_results.append(result)

Expand DownExpand Up@@ -655,9 +680,7 @@ def encode_image(
 # Process PDF
 with tempfile.TemporaryDirectory() as path:
 pdf_images = convert_from_path(
 item,
 thread_count=os.cpu_count()-1,
 output_folder=path
 item, thread_count=os.cpu_count() - 1, output_folder=path
 )
 images.extend(pdf_images)
 elif item.lower().endswith(
Expand Down

2 changes: 1 addition & 1 deletion
pyproject.toml

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -28,7 +28,7 @@ maintainers = [
]

dependencies = [
 "colpali-engine>=0.3.0,<0.4.0",
 "colpali-engine>=0.3.1,<0.4.0",
 "ml-dtypes",
 "mteb==1.6.35",
 "ninja",
Expand Down

23 changes: 23 additions & 0 deletions
tests/test_colqwen.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,23 @@
from typing import Generator

import pytest
from colpali_engine.models import ColQwen2
from colpali_engine.utils.torch_utils import get_torch_device, tear_down_torch

from byaldi import RAGMultiModalModel
from byaldi.colpali import ColPaliModel


@pytest.fixture(scope="module")
def colqwen_rag_model() -> Generator[RAGMultiModalModel, None, None]:
 device = get_torch_device("auto")
 print(f"Using device: {device}")
 yield RAGMultiModalModel.from_pretrained("vidore/colqwen2-v0.1", device=device)
 tear_down_torch()


@pytest.mark.slow
def test_load_colqwen_from_pretrained(colqwen_rag_model: RAGMultiModalModel):
 assert isinstance(colqwen_rag_model, RAGMultiModalModel)
 assert isinstance(colqwen_rag_model.model, ColPaliModel)
 assert isinstance(colqwen_rag_model.model.model, ColQwen2)