pensiev 0.25.5__py3-none-any.whl

memos/utils.py

@@ -0,0 +1,49 @@
+from PIL import Image
+import piexif
+from PIL.PngImagePlugin import PngInfo
+import json
+
+
+def write_image_metadata(image_path, metadata):
+    img = Image.open(image_path)
+    image_path_str = str(image_path)
+
+    if image_path_str.lower().endswith((".jpg", ".jpeg", ".tiff", ".webp")):
+        exif_dict = {"0th": {}, "Exif": {}, "GPS": {}, "1st": {}, "thumbnail": None}
+        exif_dict["0th"][piexif.ImageIFD.ImageDescription] = json.dumps(
+            metadata
+        ).encode("utf-8")
+        exif_bytes = piexif.dump(exif_dict)
+        img.save(image_path, exif=exif_bytes)
+    elif image_path_str.lower().endswith(".png"):
+        metadata_info = PngInfo()
+        metadata_info.add_text("Description", json.dumps(metadata))
+        img.save(image_path, "PNG", pnginfo=metadata_info)
+    else:
+        print(f"Skipping unsupported file format: {image_path_str}")
+
+
+def get_image_metadata(image_path):
+    img = Image.open(image_path)
+    image_path_str = str(image_path)
+
+    if image_path_str.lower().endswith((".jpg", ".jpeg", ".tiff", ".webp")):
+        try:
+            exif_dict = piexif.load(image_path_str)
+            existing_description = exif_dict["0th"].get(
+                piexif.ImageIFD.ImageDescription, b"{}"
+            )
+            return json.loads(existing_description.decode("utf-8"))
+        except Exception as e:
+            print(f"Error decoding EXIF metadata for {image_path_str}: {e}")
+            return None
+    elif image_path_str.lower().endswith(".png"):
+        existing_description = img.info.get("Description", "{}")
+        try:
+            return json.loads(existing_description)
+        except json.JSONDecodeError as e:
+            print(f"Error decoding PNG metadata for {image_path_str}: {e}")
+            return None
+    else:
+        print(f"Unsupported file format: {image_path_str}")
+        return None

memos_ml_backends/florence2_server.py

@@ -0,0 +1,176 @@
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+from typing import List, Dict, Any, Optional
+import httpx
+import torch
+from PIL import Image
+import base64
+import io
+from transformers import AutoProcessor, AutoModelForCausalLM
+import time
+from memos_ml_backends.schemas import (
+    ChatCompletionRequest,
+    ChatCompletionResponse,
+    ModelData,
+    ModelsResponse,
+    get_image_from_url,
+)
+
+MODEL_INFO = {"name": "florence2-base-ft", "max_model_len": 2048}
+
+# 检测可用的设备
+if torch.cuda.is_available():
+    device = torch.device("cuda")
+elif torch.backends.mps.is_available():
+    device = torch.device("mps")
+else:
+    device = torch.device("cpu")
+
+torch_dtype = (
+    torch.float32
+    if (torch.cuda.is_available() and torch.cuda.get_device_capability()[0] <= 6)
+    or (not torch.cuda.is_available() and not torch.backends.mps.is_available())
+    else torch.float16
+)
+print(f"Using device: {device}")
+
+# Load Florence-2 model
+florence_model = AutoModelForCausalLM.from_pretrained(
+    "microsoft/Florence-2-base-ft",
+    torch_dtype=torch_dtype,
+    attn_implementation="sdpa",
+    trust_remote_code=True,
+).to(device, torch_dtype)
+florence_processor = AutoProcessor.from_pretrained(
+    "microsoft/Florence-2-base-ft", trust_remote_code=True
+)
+
+app = FastAPI()
+
+
+async def generate_florence_result(text_input, image_input, max_tokens):
+    task_prompt = "<MORE_DETAILED_CAPTION>"
+    prompt = task_prompt + ""
+
+    inputs = florence_processor(
+        text=prompt, images=image_input, return_tensors="pt"
+    ).to(device, torch_dtype)
+
+    generated_ids = florence_model.generate(
+        input_ids=inputs["input_ids"],
+        pixel_values=inputs["pixel_values"],
+        max_new_tokens=max_tokens or 1024,
+        do_sample=False,
+        num_beams=3,
+    )
+
+    generated_texts = florence_processor.batch_decode(
+        generated_ids, skip_special_tokens=False
+    )
+
+    parsed_answer = florence_processor.post_process_generation(
+        generated_texts[0],
+        task=task_prompt,
+        image_size=(image_input.width, image_input.height),
+    )
+
+    return parsed_answer.get(task_prompt, "")
+
+
+@app.post("/v1/chat/completions", response_model=ChatCompletionResponse)
+async def chat_completions(request: ChatCompletionRequest):
+    try:
+        last_message = request.messages[-1]
+        text_input = last_message.get("content", "")
+        image_input = None
+
+        if isinstance(text_input, list):
+            for content in text_input:
+                if content.get("type") == "image_url":
+                    image_url = content["image_url"].get("url")
+                    image_input = await get_image_from_url(image_url)
+                    break
+            text_input = " ".join(
+                [
+                    content["text"]
+                    for content in text_input
+                    if content.get("type") == "text"
+                ]
+            )
+
+        if image_input is None:
+            raise ValueError("Image input is required")
+
+        parsed_answer = await generate_florence_result(
+            text_input, image_input, request.max_tokens
+        )
+
+        result = ChatCompletionResponse(
+            id=str(int(time.time())),
+            object="chat.completion",
+            created=int(time.time()),
+            model=request.model,
+            choices=[
+                {
+                    "index": 0,
+                    "message": {
+                        "role": "assistant",
+                        "content": parsed_answer,
+                    },
+                    "finish_reason": "stop",
+                }
+            ],
+            usage={
+                "prompt_tokens": 0,
+                "total_tokens": 0,
+                "completion_tokens": 0,
+            },
+        )
+
+        return result
+    except Exception as e:
+        print(f"Error generating chat completion: {str(e)}")
+        raise HTTPException(
+            status_code=500, detail=f"Error generating chat completion: {str(e)}"
+        )
+
+
+@app.get("/v1/models", response_model=ModelsResponse)
+async def get_models():
+    model_data = ModelData(
+        id=MODEL_INFO["name"],
+        created=int(time.time()),
+        max_model_len=MODEL_INFO["max_model_len"],
+        permission=[
+            {
+                "id": f"modelperm-{MODEL_INFO['name']}",
+                "object": "model_permission",
+                "created": int(time.time()),
+                "allow_create_engine": False,
+                "allow_sampling": False,
+                "allow_logprobs": False,
+                "allow_search_indices": False,
+                "allow_view": False,
+                "allow_fine_tuning": False,
+                "organization": "*",
+                "group": None,
+                "is_blocking": False,
+            }
+        ],
+    )
+
+    return ModelsResponse(data=[model_data])
+
+
+if __name__ == "__main__":
+    import argparse
+    import uvicorn
+
+    parser = argparse.ArgumentParser(description="Run the Florence-2 server")
+    parser.add_argument(
+        "--port", type=int, default=8000, help="Port to run the server on"
+    )
+    args = parser.parse_args()
+
+    print("Using Florence-2 model")
+    uvicorn.run(app, host="0.0.0.0", port=args.port)

memos_ml_backends/qwen2vl_server.py

@@ -0,0 +1,182 @@
+from fastapi import FastAPI, HTTPException
+import torch
+from transformers import AutoProcessor, Qwen2VLForConditionalGeneration
+from qwen_vl_utils import process_vision_info
+import time
+from memos_ml_backends.schemas import (
+    ChatCompletionRequest,
+    ChatCompletionResponse,
+    ModelData,
+    ModelsResponse,
+    get_image_from_url,
+)
+
+MODEL_INFO = {"name": "Qwen2-VL-2B-Instruct", "max_model_len": 32768}
+
+# 检测可用的设备
+if torch.cuda.is_available():
+    device = torch.device("cuda")
+elif torch.backends.mps.is_available():
+    device = torch.device("mps")
+else:
+    device = torch.device("cpu")
+
+torch_dtype = (
+    torch.float32
+    if (torch.cuda.is_available() and torch.cuda.get_device_capability()[0] <= 6)
+    or (not torch.cuda.is_available() and not torch.backends.mps.is_available())
+    else torch.float16
+)
+print(f"Using device: {device}")
+
+# Load Qwen2VL model
+qwen2vl_model = Qwen2VLForConditionalGeneration.from_pretrained(
+    "Qwen/Qwen2-VL-2B-Instruct",
+    torch_dtype=torch_dtype,
+    device_map="auto",
+).to(device, torch_dtype)
+qwen2vl_processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-2B-Instruct-GPTQ-Int4")
+
+app = FastAPI()
+
+
+async def generate_qwen2vl_result(text_input, image_input, max_tokens):
+    messages = [
+        {
+            "role": "user",
+            "content": [
+                {"type": "image", "image": image_input},
+                {"type": "text", "text": text_input},
+            ],
+        }
+    ]
+
+    text = qwen2vl_processor.apply_chat_template(
+        messages, tokenize=False, add_generation_prompt=True
+    )
+
+    image_inputs, video_inputs = process_vision_info(messages)
+
+    inputs = qwen2vl_processor(
+        text=[text],
+        images=image_inputs,
+        videos=video_inputs,
+        padding=True,
+        return_tensors="pt",
+    )
+    inputs = inputs.to(device)
+
+    generated_ids = qwen2vl_model.generate(**inputs, max_new_tokens=(max_tokens or 512))
+
+    generated_ids_trimmed = [
+        out_ids[len(in_ids) :]
+        for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
+    ]
+
+    output_text = qwen2vl_processor.batch_decode(
+        generated_ids_trimmed,
+        skip_special_tokens=True,
+        clean_up_tokenization_spaces=False,
+    )
+
+    return output_text[0] if output_text else ""
+
+
+@app.post("/v1/chat/completions", response_model=ChatCompletionResponse)
+async def chat_completions(request: ChatCompletionRequest):
+    try:
+        last_message = request.messages[-1]
+        text_input = last_message.get("content", "")
+        image_input = None
+
+        if isinstance(text_input, list):
+            for content in text_input:
+                if content.get("type") == "image_url":
+                    image_url = content["image_url"].get("url")
+                    image_input = await get_image_from_url(image_url)
+                    break
+            text_input = " ".join(
+                [
+                    content["text"]
+                    for content in text_input
+                    if content.get("type") == "text"
+                ]
+            )
+
+        if image_input is None:
+            raise ValueError("Image input is required")
+
+        parsed_answer = await generate_qwen2vl_result(
+            text_input, image_input, request.max_tokens
+        )
+
+        result = ChatCompletionResponse(
+            id=str(int(time.time())),
+            object="chat.completion",
+            created=int(time.time()),
+            model=request.model,
+            choices=[
+                {
+                    "index": 0,
+                    "message": {
+                        "role": "assistant",
+                        "content": parsed_answer,
+                    },
+                    "finish_reason": "stop",
+                }
+            ],
+            usage={
+                "prompt_tokens": 0,
+                "total_tokens": 0,
+                "completion_tokens": 0,
+            },
+        )
+
+        return result
+    except Exception as e:
+        print(f"Error generating chat completion: {str(e)}")
+        raise HTTPException(
+            status_code=500, detail=f"Error generating chat completion: {str(e)}"
+        )
+
+
+# 添加新的 GET /v1/models 端点
+@app.get("/v1/models", response_model=ModelsResponse)
+async def get_models():
+    model_data = ModelData(
+        id=MODEL_INFO["name"],
+        created=int(time.time()),
+        max_model_len=MODEL_INFO["max_model_len"],
+        permission=[
+            {
+                "id": f"modelperm-{MODEL_INFO['name']}",
+                "object": "model_permission",
+                "created": int(time.time()),
+                "allow_create_engine": False,
+                "allow_sampling": False,
+                "allow_logprobs": False,
+                "allow_search_indices": False,
+                "allow_view": False,
+                "allow_fine_tuning": False,
+                "organization": "*",
+                "group": None,
+                "is_blocking": False,
+            }
+        ],
+    )
+
+    return ModelsResponse(data=[model_data])
+
+
+if __name__ == "__main__":
+    import argparse
+    import uvicorn
+
+    parser = argparse.ArgumentParser(description="Run the Qwen2VL server")
+    parser.add_argument(
+        "--port", type=int, default=8000, help="Port to run the server on"
+    )
+    args = parser.parse_args()
+
+    print("Using Qwen2VL model")
+    uvicorn.run(app, host="0.0.0.0", port=args.port)

memos_ml_backends/schemas.py

@@ -0,0 +1,48 @@
+from pydantic import BaseModel
+from typing import List, Dict, Any, Optional
+import httpx
+from PIL import Image
+import base64
+import io
+
+class ChatCompletionRequest(BaseModel):
+    model: str
+    messages: List[Dict[str, Any]]
+    max_tokens: Optional[int] = None
+
+class ChatCompletionResponse(BaseModel):
+    id: str
+    object: str
+    created: int
+    model: str
+    choices: List[Dict[str, Any]]
+    usage: Dict[str, int]
+
+class ModelData(BaseModel):
+    id: str
+    object: str = "model"
+    created: int
+    owned_by: str = "transformers"
+    root: str = "models"
+    parent: Optional[str] = None
+    max_model_len: int
+    permission: List[Dict[str, Any]]
+
+class ModelsResponse(BaseModel):
+    object: str = "list"
+    data: List[ModelData]
+
+async def get_image_from_url(image_url):
+    if image_url.startswith("data:image/"):
+        image_data = base64.b64decode(image_url.split(",")[1])
+        return Image.open(io.BytesIO(image_data))
+    elif image_url.startswith("file://"):
+        file_path = image_url[len("file://") :]
+        return Image.open(file_path)
+    else:
+        async with httpx.AsyncClient() as client:
+            response = await client.get(image_url)
+            response.raise_for_status()
+            image_data = response.content
+            return Image.open(io.BytesIO(image_data))
+

pensiev-0.25.5.dist-info/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2024 Arkohut
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.