polymage 0.0.1__tar.gz

polymage-0.0.1/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 [yyyy] [name of copyright owner]
+
+   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.

polymage-0.0.1/PKG-INFO

@@ -0,0 +1,63 @@
+Metadata-Version: 2.4
+Name: polymage
+Version: 0.0.1
+Summary: polymage : a multimodal agent python library
+Author-email: Fabrice Gaillard <fgaillard@w3architect.com>
+License: Apache 2.0
+Requires-Python: >=3.13
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: groq>=0.37.1
+Requires-Dist: instructor>=1.13.0
+Requires-Dist: ollama>=0.6.1
+Requires-Dist: openai>=2.9.0
+Requires-Dist: pillow>=12.0.0
+Requires-Dist: requests>=2.32.5
+Dynamic: license-file
+
+# Multimodal Agents Framework
+
+A modular, platform-agnostic Python library to orchestrate multimodal AI agents across platforms 
+and models (Gemma, moondream, Flux, HiDream, etc.)
+
+Can run both on Local platforms
+- Ollama (https://ollama.com), available for macOS, Windows, and Linux
+- LmStudio (https://lmstudio.ai), available for macOS, Windows, and Linux
+- DrawThings (https://drawthings.ai), available only on macOS
+
+And on Cloud platforms
+- Groq (https://groq.com/)
+- Cloudflare (https://developers.cloudflare.com/workers-ai/)
+
+
+## ✨ Features
+
+- Define agents with prompts + multimodal inputs (image, audio, video, text)
+- Run same agent on multiple platforms/models for comparison
+- Workflow orchestration : just python scripts or tools like Apache Airflow
+
+## 🚀 Quick Start
+
+### Clone the repo
+
+```bash
+# clone the repo
+ git clone 
+```
+
+### Use uv to create a virtual environment (https://docs.astral.sh/uv/)
+
+uv is the best tool to manage multiple python version and multiple virtual python environment on your machine
+
+Installation guide at https://docs.astral.sh/uv/getting-started/installation/
+
+```bash
+uv venv
+```
+
+
+
+
+---
+
+Apache 2.0 License — Happy building! 🚀

polymage-0.0.1/README.md

@@ -0,0 +1,46 @@
+# Multimodal Agents Framework
+
+A modular, platform-agnostic Python library to orchestrate multimodal AI agents across platforms 
+and models (Gemma, moondream, Flux, HiDream, etc.)
+
+Can run both on Local platforms
+- Ollama (https://ollama.com), available for macOS, Windows, and Linux
+- LmStudio (https://lmstudio.ai), available for macOS, Windows, and Linux
+- DrawThings (https://drawthings.ai), available only on macOS
+
+And on Cloud platforms
+- Groq (https://groq.com/)
+- Cloudflare (https://developers.cloudflare.com/workers-ai/)
+
+
+## ✨ Features
+
+- Define agents with prompts + multimodal inputs (image, audio, video, text)
+- Run same agent on multiple platforms/models for comparison
+- Workflow orchestration : just python scripts or tools like Apache Airflow
+
+## 🚀 Quick Start
+
+### Clone the repo
+
+```bash
+# clone the repo
+ git clone 
+```
+
+### Use uv to create a virtual environment (https://docs.astral.sh/uv/)
+
+uv is the best tool to manage multiple python version and multiple virtual python environment on your machine
+
+Installation guide at https://docs.astral.sh/uv/getting-started/installation/
+
+```bash
+uv venv
+```
+
+
+
+
+---
+
+Apache 2.0 License — Happy building! 🚀

polymage-0.0.1/pyproject.toml

@@ -0,0 +1,22 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "polymage"
+version = "0.0.1"
+authors = [
+  { name="Fabrice Gaillard", email="fgaillard@w3architect.com" },
+]
+description = "polymage : a multimodal agent python library"
+readme = "README.md"
+license = {text = "Apache 2.0"}
+requires-python = ">=3.13"
+dependencies = [
+    "groq>=0.37.1",
+    "instructor>=1.13.0",
+    "ollama>=0.6.1",
+    "openai>=2.9.0",
+    "pillow>=12.0.0",
+    "requests>=2.32.5",
+]

polymage-0.0.1/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

polymage-0.0.1/src/polymage/__init__.py

@@ -0,0 +1 @@
+

polymage-0.0.1/src/polymage/agent/InstructAgent.py

@@ -0,0 +1,16 @@
+from typing import Any
+
+from omniagent.agent.agent import Agent
+
+
+class InstructAgent(Agent):
+	def __init__(self, **kwargs):
+		super().__init__(**kwargs)
+
+
+	def run(self, prompt: str, **kwargs) -> Any:
+		platform=self.platform
+		model=self.model
+		system_prompt=self.system_prompt
+
+		return platform.generate(model=model, prompt=prompt, system_prompt=system_prompt, **kwargs)

polymage-0.0.1/src/polymage/agent/__init__.py

@@ -0,0 +1 @@
+

polymage-0.0.1/src/polymage/agent/agent.py

@@ -0,0 +1,24 @@
+from abc import ABC
+from typing import Any, Optional
+
+from omniagent.platform.platfom import Platform
+
+
+class Agent(ABC):
+	def __init__(
+			self,
+			platform: Platform,
+			model: str,
+			system_prompt: Optional[str] = None,
+	):
+		self.platform=platform
+		self.model=model
+		self.system_prompt=system_prompt or ""
+
+	def run(self, prompt: str, **kwargs) -> Any:
+		platform=self.platform
+		model=self.model
+		system_prompt=self.system_prompt
+
+		return platform.generate(model=model, prompt=prompt, system_prompt=system_prompt, **kwargs)
+

polymage-0.0.1/src/polymage/imageutils.py

@@ -0,0 +1,75 @@
+import base64
+from io import BytesIO
+from PIL import Image
+
+
+def base64_to_image(base64_string) -> Image.Image:
+    """
+    Convert a base64 string to a PIL Image object.
+    
+    Args:
+        base64_string (str): Base64 encoded image string
+        
+    Returns:
+        PIL.Image.Image: The decoded image as a PIL Image object
+        
+    Raises:
+        ValueError: If the base64 string is invalid or cannot be decoded
+        OSError: If the decoded data is not a valid image format
+    """
+    try:
+        # Remove data URL prefix if present (e.g., "data:image/png;base64,")
+        if base64_string.startswith('data:'):
+            # Find the comma and take everything after it
+            base64_string = base64_string.split(',', 1)[1]
+        
+        # Decode the base64 string to bytes
+        image_bytes = base64.b64decode(base64_string)
+        
+        # Create a BytesIO object from the decoded bytes
+        image_buffer = BytesIO(image_bytes)
+        
+        # Open the image using PIL
+        image = Image.open(image_buffer)
+        
+        # Load the image data to ensure it's valid
+        image.load()
+        
+        return image
+
+    except OSError as e:
+        raise OSError(f"Invalid image data or unsupported format: {e}")
+
+
+def image_to_base64(image, format='PNG') -> str:
+    """
+    Convert an image to a base64-encoded string.
+
+    Parameters:
+        image (str or PIL.Image.Image): 
+            - If str: path to the image file.
+            - If PIL.Image.Image: an in-memory image object.
+        format (str): 
+            The image format to use when encoding (e.g., 'PNG', 'JPEG'). 
+            Only used if input is a PIL Image object. Default is 'PNG'.
+
+    Returns:
+        str: Base64-encoded string of the image.
+
+    Raises:
+        FileNotFoundError: If image path does not exist.
+        ValueError: If input type is not supported.
+    """
+    if isinstance(image, str):
+        # Input is a file path
+        with open(image, "rb") as image_file:
+            encoded_str = base64.b64encode(image_file.read()).decode('utf-8')
+    elif isinstance(image, Image.Image):
+        # Input is a PIL Image object
+        buffered = BytesIO()
+        image.save(buffered, format=format)
+        encoded_str = base64.b64encode(buffered.getvalue()).decode('utf-8')
+    else:
+        raise ValueError("Input must be a file path (str) or a PIL Image object.")
+
+    return encoded_str

polymage-0.0.1/src/polymage/model/__init__.py

@@ -0,0 +1 @@
+

polymage-0.0.1/src/polymage/model/model.py

@@ -0,0 +1,17 @@
+from abc import ABC
+from typing import Dict, Optional, Any
+
+
+class Model(ABC):
+    name: str
+    type: str  # e.g., "text2text", "text2image", "image2image"
+    default_params: Dict[str, Any]
+
+    def __init__(self, name: str, type: str, **overrides):
+        self.name = name
+        self.type = type
+        self.params = {**self.default_params, **overrides}
+
+    def get_payload(self, input_data: Dict[str, Any]) -> Dict[str, Any]:
+        """Build platform-agnostic payload (agent may further modify)."""
+        raise NotImplementedError

polymage-0.0.1/src/polymage/platform/__init__.py

@@ -0,0 +1 @@
+

polymage-0.0.1/src/polymage/platform/cloudflare.py

@@ -0,0 +1,43 @@
+import os
+import random
+import requests
+
+from src.omniagent.platform.platfom import Platform
+
+
+"""
+Clouflare provide AI workers with some free tier
+
+Clouflare support LLm and some other multimedia models
+you can find the list of supported models here : https://developers.cloudflare.com/workers-ai/models/
+"""
+
+
+class CloudflarePlatform(Platform):
+    def __init__(self, **kwargs):
+        super().__init__("cloudflare", **kwargs)
+
+    def _text2image(self, agent: Agent, model: str, prompt: str) -> str:
+        CLOUDFLARE_ID = os.environ['CLOUDFLARE_ID']
+        CLOUDFLARE_TOKEN = os.environ['CLOUDFLARE_TOKEN']
+        random_seed = random.randint(0, 2 ** 32 - 1)
+        url = "https://api.cloudflare.com/client/v4/accounts/" + CLOUDFLARE_ID + "/ai/run/@cf/black-forest-labs/flux-1-schnell"
+        headers = {
+            'Content-Type': 'application/json',
+            'Authorization': 'Bearer ' + CLOUDFLARE_TOKEN
+        }
+        data = {
+            'steps': 5,
+            'seed': random_seed,
+            'prompt': prompt
+        }
+        try:
+            response = requests.post(url, headers=headers, json=data)
+            response.raise_for_status()  # Raise an exception for HTTP errors
+            result = response.json()
+            #print(f"RESULT = {result}")
+            return result['result']['image']
+
+        except Exception as e:
+            print(f"Error generating image: {e}")
+            raise

polymage-0.0.1/src/polymage/platform/drawthings.py

@@ -0,0 +1,119 @@
+import base64
+from io import BytesIO
+
+import requests
+from typing import Any
+from PIL import Image
+
+import omniagent.imageutils
+from omniagent.platform.platfom import Platform
+
+#
+# installed models default params
+#
+highdream_fast_settings = {
+    "model": "hidream_i1_fast_q8p.ckpt",
+    "negative_prompt": "",
+    "steps": 14,
+    "batch_count": 1,
+    "sampler": "DPM++ 2M Trailing",
+    "seed": -1,
+    "hires_fix": False,
+    "tiled_decoding": False,
+    "clip_skip": 1,
+    "shift": 1.0,
+    "guidance_scale": 1.0,
+    "resolution_dependent_shift": False
+}
+
+flux_kontext_settings = {
+    "model": "flux_1_kontext_dev_q8p.ckpt",
+    "negative_prompt": "",
+    "steps": 8,
+    "batch_count": 1,
+    "sampler": "DPM++ 2M Trailing",
+    "seed": -1,
+    "hires_fix": False,
+    "tiled_decoding": False,
+    "clip_skip": 1,
+    "shift": 1.0,
+    "guidance_scale": 2.0,
+    "resolution_dependent_shift": True,
+    "loras": [{"file": "flux.1_turbo_alpha_lora_f16.ckpt", "weight": 1, "mode": "all"}],
+}
+
+qwen_image_edit_settings_4_steps = {
+    "model": "qwen_image_edit_2509_q8p.ckpt",
+    "negative_prompt": "",
+    "steps": 5,
+    "batch_count": 1,
+    "sampler": "DPM++ 2M Trailing",
+    "seed": -1,
+    "hires_fix": False,
+    "tiled_decoding": False,
+    "clip_skip": 1,
+    "shift": 1.0,
+    "guidance_scale": 2.0,
+    "resolution_dependent_shift": True,
+    "loras": [{"file": "qwen_image_edit_2509_lightning_4_step_v1.0_lora_f16.ckpt", "weight": 1, "mode": "all"}],
+}
+
+qwen_image_edit_settings_8_steps = {
+    "model": "qwen_image_edit_2509_q8p.ckpt",
+    "negative_prompt": "",
+    "steps": 8,
+    "batch_count": 1,
+    "sampler": "DPM++ 2M Trailing",
+    "seed": -1,
+    "hires_fix": False,
+    "tiled_decoding": False,
+    "clip_skip": 1,
+    "shift": 1.0,
+    "guidance_scale": 2.0,
+    "resolution_dependent_shift": True,
+    "loras": [{"file": "qwen_image_edit_2509_lightning_8_step_v1.0_lora_f16.ckpt", "weight": 1, "mode": "all"}],
+}
+
+
+
+MODELS_SETTINGS = {
+    "highdream_fast": highdream_fast_settings,
+    "flux_kontext": flux_kontext_settings,
+    "qwen_image_edit_4_steps": qwen_image_edit_settings_4_steps,
+    "qwen_image_edit_8_steps": qwen_image_edit_settings_8_steps,
+}
+
+class DrawThingsPlatform(Platform):
+    def __init__(self, host: str = "127.0.0.1:7860", **kwargs):
+        self.host = host
+
+
+    def _text2image(self, model: str, prompt: str) -> Image:
+        payload = MODELS_SETTINGS[model]
+        payload["prompt"] = prompt
+
+        try:
+            response = requests.post(f"http://{self.host}/sdapi/v1/txt2img", json=payload)
+            response.raise_for_status()
+            json_data = response.json()
+            base64_string = json_data["images"][0]
+            image = omniagent.base64_to_image(base64_string)
+            return image
+        except Exception as e:
+            raise RuntimeError(f"DrawThings API error: {e}")
+
+
+    def _image2image(self, model: str, prompt: str, image: Image) -> Image:
+        payload = MODELS_SETTINGS[model]
+        payload["prompt"] = prompt
+        base64_image = omniagent.image_to_base64(image)
+        payload["init_images"] = [base64_image]
+
+        try:
+            response = requests.post(f"http://{self.host}/sdapi/v1/img2img", json=payload)
+            response.raise_for_status()
+            json_data = response.json()
+            base64_string = json_data["images"][0]
+            return base64_string
+        except Exception as e:
+            raise RuntimeError(f"DrawThings API error: {e}")

polymage-0.0.1/src/polymage/platform/groq.py

@@ -0,0 +1,52 @@
+from groq import Groq
+
+from src.omniagent.platform.platfom import Platform
+
+
+"""
+groq platform
+
+groq support LLm and audio2text models
+you can find the list of supported models here : https://console.groq.com/docs/models
+"""
+
+
+class GroqPlatform(Platform):
+    def __init__(self, api_key: str, **kwargs):
+        super().__init__("groq", api_key=api_key, **kwargs)
+        self.client = Groq(api_key=api_key)
+
+    def _text2text(self, model: str, prompt: str) -> str:
+        messages = []
+        messages.append({"role": "user", "content": prompt})
+        #
+        # TODO manage system prompt
+        #
+        #if agent.system_prompt:
+        #    messages.append({"role": "system", "content": agent.system_prompt})
+
+        try:
+            response = self.client.chat.completions.create(
+                model=model,
+                messages=messages,
+                # Controls randomness: lowering results in less random completions.
+                # As the temperature approaches zero, the model will become deterministic
+                # and repetitive.
+                temperature=0.8,
+                # The maximum number of tokens to generate. Requests can use up to
+                # 32,768 tokens shared between prompt and completion.
+                max_tokens=4096,
+                # Controls diversity via nucleus sampling: 0.5 means half of all
+                # likelihood-weighted options are considered.
+                top_p=1,
+                # A stop sequence is a predefined or user-specified text string that
+                # signals an AI to stop generating content, ensuring its responses
+                # remain focused and concise. Examples include punctuation marks and
+                # markers like "[end]".
+                stop=None,
+                # If set, partial message deltas will be sent.
+                stream=False,
+            )
+            return response.choices[0].message.content or ""
+        except Exception as e:
+            raise RuntimeError(f"Groq API error: {e}")

polymage-0.0.1/src/polymage/platform/lmstudio.py

@@ -0,0 +1,114 @@
+import instructor
+from typing import Optional, Any
+from openai import OpenAI
+from pydantic import BaseModel
+from PIL import Image
+
+from omniagent.imageutils import image_to_base64
+from omniagent.platform.platfom import Platform
+
+#
+# example : https://github.com/YorkieDev/lmstudioservercodeexamples?tab=readme-ov-file#vision-analysis-python
+#
+
+class LMStudioPlatform(Platform):
+    def __init__(self, host: str = "127.0.0.1:1234", **kwargs):
+        self.host = host
+
+
+    def _text2text(self, model: str, prompt: str, **kwargs) -> str:
+        system_prompt: Optional[str] = kwargs.get("system_promt", "")
+
+        client = OpenAI(
+                base_url="http://localhost:1234/v1",  # LM Studio's default endpoint
+                api_key="lm-studio"  # Dummy key (LM Studio doesn't require real keys)
+        )
+        response = client.chat.completions.create(
+		    model=model,  # e.g., "gpt-4o" or local model like "llama-3"
+		    messages=[
+			    {"role": "system", "content": system_prompt},
+			    {"role": "user", "content": prompt}
+		    ],
+		    temperature=0.8
+	    )
+        return response.choices[0].message.content
+
+
+    def _text2data(self, model: str, response_model: BaseModel, prompt: str, **kwargs) -> Any:
+        # Patch the OpenAI client with Instructor
+        client = instructor.patch(
+            OpenAI(
+                base_url="http://localhost:1234/v1",  # LM Studio's default endpoint
+                api_key="lm-studio"  # Dummy key (LM Studio doesn't require real keys)
+            ),
+            mode=instructor.Mode.JSON  # CRITICAL FOR NON-OPENAI MODELS
+        )
+
+        # Get structured response
+        response_data = client.chat.completions.create(
+            model=model,  # Must match LM Studio's loaded model name
+            response_model=response_model,
+            messages=[
+                {"role": "user", "content": prompt}
+            ],
+            max_retries=3  # Auto-retry on validation failures
+        )
+
+        return response_data.model_dump_json(indent=2)
+
+
+
+    def _image2text(self, model: str, prompt: str, image: Image.Image) -> str:
+        client = OpenAI(
+                base_url="http://localhost:1234/v1",  # LM Studio's default endpoint
+                api_key="lm-studio"  # Dummy key (LM Studio doesn't require real keys)
+        )
+
+        base64_image = image_to_base64(image)
+
+        response = client.responses.create(
+            model=model,
+            input=[
+                {
+                    "role": "user",
+                    "content": [
+                        {"type": "input_text", "text": prompt},
+                        {"type": "input_image", "image_url": f"data:image/png;base64,{base64_image}"},
+                    ],
+                }
+            ],
+        )
+        return response.model_dump_json(indent=2)
+
+    def _image2data(self, model: str, response_model: BaseModel, prompt: str, image: Image.Image, **kwargs) -> str:
+        # Patch the OpenAI client with Instructor
+        client = instructor.patch(
+            OpenAI(
+                base_url="http://localhost:1234/v1",  # LM Studio's default endpoint
+                api_key="lm-studio"  # Dummy key (LM Studio doesn't require real keys)
+            ),
+            mode=instructor.Mode.JSON  # CRITICAL FOR NON-OPENAI MODELS
+        )
+
+        # Get structured response
+        response_data = client.chat.completions.create(
+            model="your-model-name-here",  # Must match LM Studio's loaded model name
+            response_model=response_model,
+            messages=[{
+                "role": "user",
+                "content": prompt
+            }],
+            max_retries=3  # Auto-retry on validation failures
+        )
+
+        return response_data.model_dump_json(indent=2)
+
+
+    def _text2image(self, model: str, prompt: str, **kwargs) -> Image.Image:
+        """Platform-specific execution interface"""
+        pass
+
+    def _image2image(self, model: str, prompt: str, image: Image.Image, **kwargs) -> Image.Image:
+        """Platform-specific execution interface"""
+        pass
+

polymage-0.0.1/src/polymage/platform/ollama.py

@@ -0,0 +1,33 @@
+from ollama import chat
+from PIL import Image
+
+from src.omniagent.platform.platfom import Platform
+
+class OllamaPlatform(Platform):
+    def __init__(self, host: str = "http://localhost:11434", **kwargs):
+        super().__init__("ollama", **kwargs)
+        self.host = host
+
+
+    def _text2text(self, model: str, prompt: str, **kwargs) -> str:
+        payload = {
+                'role': 'user',
+                'content': prompt,
+        }
+
+        try:
+            response = chat(model=model, messages=[payload])
+            return response['message']['content']
+        except Exception as e:
+            raise RuntimeError(f"Ollama API error: {e}")
+
+
+    def _image2text(self, model: str, prompt: str, image: Image.Image) -> str:
+        """
+        Not implemented yet
+        :param model:
+        :param prompt:
+        :param image:
+        :return:
+        """
+        pass

polymage-0.0.1/src/polymage/platform/platfom.py

@@ -0,0 +1,76 @@
+from abc import ABC, abstractmethod
+from typing import Any, Optional
+from pydantic import BaseModel
+from PIL import Image
+
+class Platform(ABC):
+    """Abstract base for AI platform connectors"""
+
+    def generate(self, model: str, prompt: str, **kwargs) -> Any:
+        """
+        Polymorphic entry point that dispatches to the appropriate internal method
+        based on the presence of an input image and/or expected output type.
+        """
+        print(f"Generate model={model}, prompt={prompt}, kwargs={kwargs}")
+        image: Optional[Image.Image] = kwargs.get("image", None)
+        output_type: str = kwargs.get("output_type", "text")  # 'text' or 'image'
+
+        if image is not None:
+            # Image input → multimodal
+            if output_type == "image":
+                return self._image2image(model, prompt, image, **kwargs)
+            else:
+                return self._image2text(model, prompt, image, **kwargs)
+        else:
+            # Text-only input
+            if output_type == "image":
+                return self._text2image(model, prompt, **kwargs)
+            else:
+                return self._text2text(model, prompt, **kwargs)
+
+
+    def generate_data(self, model: str, response_model: BaseModel, prompt: str, **kwargs) -> Any:
+        """
+            Polymorphic entry point that dispatches to the appropriate internal method
+            based on the presence of an input image.
+            use for text to text or image to text structured output
+        """
+        image: Optional[Image.Image] = kwargs.get("image", None)
+        if image is not None:
+            # Image input → multimodal
+            return self._image2data(model, response_model, prompt, image, **kwargs)
+        else:
+            return self._text2data(model, response_model, prompt, **kwargs)
+
+
+    @abstractmethod
+    def _text2text(self, model: str, prompt: str, **kwargs) -> Any:
+        """Platform-specific execution interface"""
+        pass
+
+    @abstractmethod
+    def _text2data(self, model: str, response_model: BaseModel, prompt: str, **kwargs) -> Any:
+        """Platform-specific execution interface"""
+        pass
+
+    @abstractmethod
+    def _text2image(self, model: str, prompt: str, **kwargs) -> Image.Image:
+        """Platform-specific execution interface"""
+        pass
+
+    @abstractmethod
+    def _image2text(self, model: str, prompt: str, image: Image.Image, **kwargs) -> str:
+        """Platform-specific execution interface"""
+        pass
+
+    @abstractmethod
+    def _image2data(self, model: str, response_model: BaseModel, prompt: str, image: Image.Image, **kwargs) -> Any:
+        """Platform-specific execution interface"""
+        pass
+
+    @abstractmethod
+    def _image2image(self, model: str, prompt: str, image: Image.Image, **kwargs) -> Image.Image:
+        """Platform-specific execution interface"""
+        pass
+
+

polymage-0.0.1/src/polymage.egg-info/PKG-INFO

@@ -0,0 +1,63 @@
+Metadata-Version: 2.4
+Name: polymage
+Version: 0.0.1
+Summary: polymage : a multimodal agent python library
+Author-email: Fabrice Gaillard <fgaillard@w3architect.com>
+License: Apache 2.0
+Requires-Python: >=3.13
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: groq>=0.37.1
+Requires-Dist: instructor>=1.13.0
+Requires-Dist: ollama>=0.6.1
+Requires-Dist: openai>=2.9.0
+Requires-Dist: pillow>=12.0.0
+Requires-Dist: requests>=2.32.5
+Dynamic: license-file
+
+# Multimodal Agents Framework
+
+A modular, platform-agnostic Python library to orchestrate multimodal AI agents across platforms 
+and models (Gemma, moondream, Flux, HiDream, etc.)
+
+Can run both on Local platforms
+- Ollama (https://ollama.com), available for macOS, Windows, and Linux
+- LmStudio (https://lmstudio.ai), available for macOS, Windows, and Linux
+- DrawThings (https://drawthings.ai), available only on macOS
+
+And on Cloud platforms
+- Groq (https://groq.com/)
+- Cloudflare (https://developers.cloudflare.com/workers-ai/)
+
+
+## ✨ Features
+
+- Define agents with prompts + multimodal inputs (image, audio, video, text)
+- Run same agent on multiple platforms/models for comparison
+- Workflow orchestration : just python scripts or tools like Apache Airflow
+
+## 🚀 Quick Start
+
+### Clone the repo
+
+```bash
+# clone the repo
+ git clone 
+```
+
+### Use uv to create a virtual environment (https://docs.astral.sh/uv/)
+
+uv is the best tool to manage multiple python version and multiple virtual python environment on your machine
+
+Installation guide at https://docs.astral.sh/uv/getting-started/installation/
+
+```bash
+uv venv
+```
+
+
+
+
+---
+
+Apache 2.0 License — Happy building! 🚀

polymage-0.0.1/src/polymage.egg-info/SOURCES.txt

@@ -0,0 +1,22 @@
+LICENSE
+README.md
+pyproject.toml
+src/polymage/__init__.py
+src/polymage/imageutils.py
+src/polymage.egg-info/PKG-INFO
+src/polymage.egg-info/SOURCES.txt
+src/polymage.egg-info/dependency_links.txt
+src/polymage.egg-info/requires.txt
+src/polymage.egg-info/top_level.txt
+src/polymage/agent/InstructAgent.py
+src/polymage/agent/__init__.py
+src/polymage/agent/agent.py
+src/polymage/model/__init__.py
+src/polymage/model/model.py
+src/polymage/platform/__init__.py
+src/polymage/platform/cloudflare.py
+src/polymage/platform/drawthings.py
+src/polymage/platform/groq.py
+src/polymage/platform/lmstudio.py
+src/polymage/platform/ollama.py
+src/polymage/platform/platfom.py

polymage-0.0.1/src/polymage.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

polymage-0.0.1/src/polymage.egg-info/requires.txt

@@ -0,0 +1,6 @@
+groq>=0.37.1
+instructor>=1.13.0
+ollama>=0.6.1
+openai>=2.9.0
+pillow>=12.0.0
+requests>=2.32.5

polymage-0.0.1/src/polymage.egg-info/top_level.txt

@@ -0,0 +1 @@
+polymage