agno 2.0.0rc2__py3-none-any.whl → 2.0.2__py3-none-any.whl

agno/vectordb/lancedb/lance_db.py

@@ -140,6 +140,29 @@ class LanceDb(VectorDb):
 
         log_debug(f"Initialized LanceDb with table: '{self.table_name}'")
 
+    def _prepare_vector(self, embedding) -> List[float]:
+        """Prepare vector embedding for insertion, ensuring correct dimensions and type."""
+        if embedding is not None:
+            # Convert to list of floats
+            vector = [float(x) for x in embedding]
+
+            # Ensure vector has correct dimensions if specified
+            if self.dimensions:
+                if len(vector) != self.dimensions:
+                    if len(vector) > self.dimensions:
+                        # Truncate if too long
+                        vector = vector[: self.dimensions]
+                        log_debug(f"Truncated vector from {len(embedding)} to {self.dimensions} dimensions")
+                    else:
+                        # Pad with zeros if too short
+                        vector.extend([0.0] * (self.dimensions - len(vector)))
+                        log_debug(f"Padded vector from {len(embedding)} to {self.dimensions} dimensions")
+
+            return vector
+        else:
+            # Fallback if embedding is None
+            return [0.0] * (self.dimensions or 1536)
+
     async def _get_async_connection(self) -> lancedb.AsyncConnection:
         """Get or create an async connection to LanceDB."""
         if self.async_connection is None:
@@ -174,22 +197,37 @@ class LanceDb(VectorDb):
     async def async_create(self) -> None:
         """Create the table asynchronously if it does not exist."""
         if not await self.async_exists():
-            conn = await self._get_async_connection()
-            schema = self._base_schema()
+            try:
+                conn = await self._get_async_connection()
+                schema = self._base_schema()
 
-            log_debug(f"Creating table asynchronously: {self.table_name}")
-            self.async_table = await conn.create_table(self.table_name, schema=schema, mode="overwrite", exist_ok=True)
+                log_debug(f"Creating table asynchronously: {self.table_name}")
+                self.async_table = await conn.create_table(
+                    self.table_name, schema=schema, mode="overwrite", exist_ok=True
+                )
+                log_debug(f"Successfully created async table: {self.table_name}")
+            except Exception as e:
+                logger.error(f"Error creating async table: {e}")
+                # Try to fall back to sync table creation
+                try:
+                    log_debug("Falling back to sync table creation")
+                    self.table = self._init_table()
+                    log_debug("Sync table created successfully")
+                except Exception as sync_e:
+                    logger.error(f"Sync table creation also failed: {sync_e}")
+                    raise
 
     def _base_schema(self) -> pa.Schema:
+        # Use fixed-size list for vector field as required by LanceDB
+        if self.dimensions:
+            vector_field = pa.field(self._vector_col, pa.list_(pa.float32(), self.dimensions))
+        else:
+            # Fallback to dynamic list if dimensions not known (should be rare)
+            vector_field = pa.field(self._vector_col, pa.list_(pa.float32()))
+
         return pa.schema(
             [
-                pa.field(
-                    self._vector_col,
-                    pa.list_(
-                        pa.float32(),
-                        len(self.embedder.get_embedding("test")),  # type: ignore
-                    ),
-                ),
+                vector_field,
                 pa.field(self._id, pa.string()),
                 pa.field("payload", pa.string()),
             ]
@@ -278,7 +316,7 @@ class LanceDb(VectorDb):
             data.append(
                 {
                     "id": doc_id,
-                    "vector": document.embedding,
+                    "vector": self._prepare_vector(document.embedding),
                     "payload": json.dumps(payload),
                 }
             )
@@ -343,7 +381,7 @@ class LanceDb(VectorDb):
             data.append(
                 {
                     "id": doc_id,
-                    "vector": document.embedding,
+                    "vector": self._prepare_vector(document.embedding),
                     "payload": json.dumps(payload),
                 }
             )
@@ -356,6 +394,19 @@ class LanceDb(VectorDb):
         try:
             await self._get_async_connection()
 
+            # Ensure the async table is created before inserting
+            if self.async_table is None:
+                try:
+                    await self.async_create()
+                except Exception as create_e:
+                    logger.error(f"Failed to create async table: {create_e}")
+                    # Continue to fallback logic below
+
+            if self.async_table is None:
+                # Fall back to sync insertion if async table creation failed
+                logger.warning("Async table not available, falling back to sync insertion")
+                return self.insert(content_hash, documents, filters)
+
             if self.on_bad_vectors is not None:
                 await self.async_table.add(data, on_bad_vectors=self.on_bad_vectors, fill_value=self.fill_value)  # type: ignore
             else:
@@ -367,7 +418,14 @@ class LanceDb(VectorDb):
             self._refresh_sync_connection()
         except Exception as e:
             logger.error(f"Error during async document insertion: {e}")
-            raise
+            # Try falling back to sync insertion as a last resort
+            try:
+                logger.warning("Async insertion failed, attempting sync fallback")
+                self.insert(content_hash, documents, filters)
+                logger.info("Sync fallback successful")
+            except Exception as sync_e:
+                logger.error(f"Sync fallback also failed: {sync_e}")
+                raise e from sync_e
 
     def upsert_available(self) -> bool:
         """Check if upsert is available in LanceDB."""
@@ -638,26 +696,25 @@ class LanceDb(VectorDb):
             return await self.async_table.count_rows()
         return 0
 
-    def _async_get_count_sync(self) -> int:
-        """Helper method to run async_get_count in a new thread with its own event loop"""
-        import asyncio
-
-        return asyncio.run(self.async_get_count())
-
     def get_count(self) -> int:
         # If we have data in the async table but sync table isn't available, try to get count from async table
         if self.async_table is not None:
             try:
                 import asyncio
 
-                # Check if we're already in an async context
+                # Check if we're already in an event loop
                 try:
-                    return self._async_get_count_sync()
+                    asyncio.get_running_loop()
+                    # We're in an async context, can't use asyncio.run
+                    log_debug("Already in async context, falling back to sync table for count")
                 except RuntimeError:
                     # No event loop running, safe to use asyncio.run
-                    return asyncio.run(self.async_get_count())
-            except Exception:
-                pass
+                    try:
+                        return asyncio.run(self.async_get_count())
+                    except Exception as e:
+                        log_debug(f"Failed to get async count: {e}")
+            except Exception as e:
+                log_debug(f"Error in async count logic: {e}")
 
         if self.exists() and self.table:
             return self.table.count_rows()

agno/workflow/step.py

@@ -7,7 +7,7 @@ from uuid import uuid4
 from pydantic import BaseModel
 
 from agno.agent import Agent
-from agno.media import Audio, AudioArtifact, Image, ImageArtifact, Video, VideoArtifact
+from agno.media import Audio, Image, Video
 from agno.models.metrics import Metrics
 from agno.run.agent import RunOutput
 from agno.run.team import TeamRunOutput
@@ -931,20 +931,20 @@ class Step:
             # Convert any other type to string
             return RunOutput(content=str(result))
 
-    def _convert_audio_artifacts_to_audio(self, audio_artifacts: List[AudioArtifact]) -> List[Audio]:
+    def _convert_audio_artifacts_to_audio(self, audio_artifacts: List[Audio]) -> List[Audio]:
         """Convert AudioArtifact objects to Audio objects"""
         audios = []
         for audio_artifact in audio_artifacts:
             if audio_artifact.url:
                 audios.append(Audio(url=audio_artifact.url))
-            elif audio_artifact.base64_audio:  # use base64_audio instead of content
-                audios.append(Audio(content=audio_artifact.base64_audio))
+            elif audio_artifact.content:
+                audios.append(Audio(content=audio_artifact.content))
             else:
-                logger.warning(f"Skipping AudioArtifact with no URL or base64_audio: {audio_artifact}")
+                logger.warning(f"Skipping AudioArtifact with no URL or content: {audio_artifact}")
                 continue
         return audios
 
-    def _convert_image_artifacts_to_images(self, image_artifacts: List[ImageArtifact]) -> List[Image]:
+    def _convert_image_artifacts_to_images(self, image_artifacts: List[Image]) -> List[Image]:
         """
         Convert ImageArtifact objects to Image objects with proper content handling.
 
@@ -996,7 +996,7 @@ class Step:
 
         return images
 
-    def _convert_video_artifacts_to_videos(self, video_artifacts: List[VideoArtifact]) -> List[Video]:
+    def _convert_video_artifacts_to_videos(self, video_artifacts: List[Video]) -> List[Video]:
         """
         Convert VideoArtifact objects to Video objects with proper content handling.
 

agno/workflow/types.py

@@ -5,7 +5,7 @@ from typing import Any, Dict, List, Optional, Union
 from fastapi import WebSocket
 from pydantic import BaseModel
 
-from agno.media import AudioArtifact, File, ImageArtifact, VideoArtifact
+from agno.media import Audio, File, Image, Video
 from agno.models.metrics import Metrics
 from agno.utils.log import log_warning
 
@@ -19,9 +19,9 @@ class WorkflowExecutionInput:
     additional_data: Optional[Dict[str, Any]] = None
 
     # Media inputs
-    images: Optional[List[ImageArtifact]] = None
-    videos: Optional[List[VideoArtifact]] = None
-    audio: Optional[List[AudioArtifact]] = None
+    images: Optional[List[Image]] = None
+    videos: Optional[List[Video]] = None
+    audio: Optional[List[Audio]] = None
     files: Optional[List[File]] = None
 
     def get_input_as_string(self) -> Optional[str]:
@@ -72,9 +72,9 @@ class StepInput:
     additional_data: Optional[Dict[str, Any]] = None
 
     # Media inputs
-    images: Optional[List[ImageArtifact]] = None
-    videos: Optional[List[VideoArtifact]] = None
-    audio: Optional[List[AudioArtifact]] = None
+    images: Optional[List[Image]] = None
+    videos: Optional[List[Video]] = None
+    audio: Optional[List[Audio]] = None
     files: Optional[List[File]] = None
 
     def get_input_as_string(self) -> Optional[str]:
@@ -225,9 +225,9 @@ class StepOutput:
     step_run_id: Optional[str] = None
 
     # Media outputs
-    images: Optional[List[ImageArtifact]] = None
-    videos: Optional[List[VideoArtifact]] = None
-    audio: Optional[List[AudioArtifact]] = None
+    images: Optional[List[Image]] = None
+    videos: Optional[List[Video]] = None
+    audio: Optional[List[Audio]] = None
     files: Optional[List[File]] = None
 
     # Metrics for this step execution
@@ -282,15 +282,15 @@ class StepOutput:
         # Reconstruct media artifacts
         images = data.get("images")
         if images:
-            images = [ImageArtifact.model_validate(img) for img in images]
+            images = [Image.model_validate(img) for img in images]
 
         videos = data.get("videos")
         if videos:
-            videos = [VideoArtifact.model_validate(vid) for vid in videos]
+            videos = [Video.model_validate(vid) for vid in videos]
 
         audio = data.get("audio")
         if audio:
-            audio = [AudioArtifact.model_validate(aud) for aud in audio]
+            audio = [Audio.model_validate(aud) for aud in audio]
 
         files = data.get("files")
         if files:

agno/workflow/workflow.py

@@ -26,7 +26,7 @@ from pydantic import BaseModel
 from agno.agent.agent import Agent
 from agno.db.base import BaseDb, SessionType
 from agno.exceptions import RunCancelledException
-from agno.media import Audio, AudioArtifact, File, Image, ImageArtifact, Video, VideoArtifact
+from agno.media import Audio, File, Image, Video
 from agno.models.message import Message
 from agno.models.metrics import Metrics
 from agno.run.agent import RunEvent
@@ -745,9 +745,9 @@ class Workflow:
         self,
         execution_input: WorkflowExecutionInput,
         previous_step_outputs: Optional[Dict[str, StepOutput]] = None,
-        shared_images: Optional[List[ImageArtifact]] = None,
-        shared_videos: Optional[List[VideoArtifact]] = None,
-        shared_audio: Optional[List[AudioArtifact]] = None,
+        shared_images: Optional[List[Image]] = None,
+        shared_videos: Optional[List[Video]] = None,
+        shared_audio: Optional[List[Audio]] = None,
         shared_files: Optional[List[File]] = None,
     ) -> StepInput:
         """Helper method to create StepInput with enhanced data flow support"""
@@ -890,12 +890,12 @@ class Workflow:
                 collected_step_outputs: List[Union[StepOutput, List[StepOutput]]] = []
                 previous_step_outputs: Dict[str, StepOutput] = {}
 
-                shared_images: List[ImageArtifact] = execution_input.images or []
-                output_images: List[ImageArtifact] = (execution_input.images or []).copy()  # Start with input images
-                shared_videos: List[VideoArtifact] = execution_input.videos or []
-                output_videos: List[VideoArtifact] = (execution_input.videos or []).copy()  # Start with input videos
-                shared_audio: List[AudioArtifact] = execution_input.audio or []
-                output_audio: List[AudioArtifact] = (execution_input.audio or []).copy()  # Start with input audio
+                shared_images: List[Image] = execution_input.images or []
+                output_images: List[Image] = (execution_input.images or []).copy()  # Start with input images
+                shared_videos: List[Video] = execution_input.videos or []
+                output_videos: List[Video] = (execution_input.videos or []).copy()  # Start with input videos
+                shared_audio: List[Audio] = execution_input.audio or []
+                output_audio: List[Audio] = (execution_input.audio or []).copy()  # Start with input audio
                 shared_files: List[File] = execution_input.files or []
                 output_files: List[File] = (execution_input.files or []).copy()  # Start with input files
 
@@ -1050,12 +1050,12 @@ class Workflow:
                 collected_step_outputs: List[Union[StepOutput, List[StepOutput]]] = []
                 previous_step_outputs: Dict[str, StepOutput] = {}
 
-                shared_images: List[ImageArtifact] = execution_input.images or []
-                output_images: List[ImageArtifact] = (execution_input.images or []).copy()  # Start with input images
-                shared_videos: List[VideoArtifact] = execution_input.videos or []
-                output_videos: List[VideoArtifact] = (execution_input.videos or []).copy()  # Start with input videos
-                shared_audio: List[AudioArtifact] = execution_input.audio or []
-                output_audio: List[AudioArtifact] = (execution_input.audio or []).copy()  # Start with input audio
+                shared_images: List[Image] = execution_input.images or []
+                output_images: List[Image] = (execution_input.images or []).copy()  # Start with input images
+                shared_videos: List[Video] = execution_input.videos or []
+                output_videos: List[Video] = (execution_input.videos or []).copy()  # Start with input videos
+                shared_audio: List[Audio] = execution_input.audio or []
+                output_audio: List[Audio] = (execution_input.audio or []).copy()  # Start with input audio
                 shared_files: List[File] = execution_input.files or []
                 output_files: List[File] = (execution_input.files or []).copy()  # Start with input files
 
@@ -1326,12 +1326,12 @@ class Workflow:
                 collected_step_outputs: List[Union[StepOutput, List[StepOutput]]] = []
                 previous_step_outputs: Dict[str, StepOutput] = {}
 
-                shared_images: List[ImageArtifact] = execution_input.images or []
-                output_images: List[ImageArtifact] = (execution_input.images or []).copy()  # Start with input images
-                shared_videos: List[VideoArtifact] = execution_input.videos or []
-                output_videos: List[VideoArtifact] = (execution_input.videos or []).copy()  # Start with input videos
-                shared_audio: List[AudioArtifact] = execution_input.audio or []
-                output_audio: List[AudioArtifact] = (execution_input.audio or []).copy()  # Start with input audio
+                shared_images: List[Image] = execution_input.images or []
+                output_images: List[Image] = (execution_input.images or []).copy()  # Start with input images
+                shared_videos: List[Video] = execution_input.videos or []
+                output_videos: List[Video] = (execution_input.videos or []).copy()  # Start with input videos
+                shared_audio: List[Audio] = execution_input.audio or []
+                output_audio: List[Audio] = (execution_input.audio or []).copy()  # Start with input audio
                 shared_files: List[File] = execution_input.files or []
                 output_files: List[File] = (execution_input.files or []).copy()  # Start with input files
 
@@ -1484,12 +1484,12 @@ class Workflow:
                 collected_step_outputs: List[Union[StepOutput, List[StepOutput]]] = []
                 previous_step_outputs: Dict[str, StepOutput] = {}
 
-                shared_images: List[ImageArtifact] = execution_input.images or []
-                output_images: List[ImageArtifact] = (execution_input.images or []).copy()  # Start with input images
-                shared_videos: List[VideoArtifact] = execution_input.videos or []
-                output_videos: List[VideoArtifact] = (execution_input.videos or []).copy()  # Start with input videos
-                shared_audio: List[AudioArtifact] = execution_input.audio or []
-                output_audio: List[AudioArtifact] = (execution_input.audio or []).copy()  # Start with input audio
+                shared_images: List[Image] = execution_input.images or []
+                output_images: List[Image] = (execution_input.images or []).copy()  # Start with input images
+                shared_videos: List[Video] = execution_input.videos or []
+                output_videos: List[Video] = (execution_input.videos or []).copy()  # Start with input videos
+                shared_audio: List[Audio] = execution_input.audio or []
+                output_audio: List[Audio] = (execution_input.audio or []).copy()  # Start with input audio
                 shared_files: List[File] = execution_input.files or []
                 output_files: List[File] = (execution_input.files or []).copy()  # Start with input files
 

{agno-2.0.0rc2.dist-info → agno-2.0.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agno
-Version: 2.0.0rc2
+Version: 2.0.2
 Summary: Agno: a lightweight library for building Multi-Agent Systems
 Author-email: Ashpreet Bedi <ashpreet@agno.com>
 Project-URL: homepage, https://agno.com
@@ -353,3 +353,142 @@ Requires-Dist: agno[agui]; extra == "tests"
 Requires-Dist: twine; extra == "tests"
 Requires-Dist: build; extra == "tests"
 Dynamic: license-file
+
+<div align="center" id="top">
+  <a href="https://docs.agno.com">
+    <picture>
+      <source media="(prefers-color-scheme: dark)" srcset="https://agno-public.s3.us-east-1.amazonaws.com/assets/logo-dark.svg">
+      <source media="(prefers-color-scheme: light)" srcset="https://agno-public.s3.us-east-1.amazonaws.com/assets/logo-light.svg">
+      <img src="https://agno-public.s3.us-east-1.amazonaws.com/assets/logo-light.svg" alt="Agno">
+    </picture>
+  </a>
+</div>
+<div align="center">
+  <a href="https://docs.agno.com">📚 Documentation</a> &nbsp;|&nbsp;
+  <a href="https://docs.agno.com/examples/introduction">💡 Examples</a> &nbsp;|&nbsp;
+  <a href="https://github.com/agno-agi/agno/stargazers">🌟 Star Us</a>
+</div>
+
+## What is Agno?
+
+[Agno](https://docs.agno.com) is a high-performance runtime for multi-agent systems. Use it to build, run and manage secure multi-agent systems in your cloud.
+
+Agno gives you the fastest framework for building agents with session management, memory, knowledge, human in the loop and MCP support. You can put agents together as an autonomous multi-agent team, or build step-based agentic workflows for full control over complex multi-step processes.
+
+In 10 lines of code, we can build an Agent that will fetch the top stories from HackerNews and summarize them.
+
+```python hackernews_agent.py
+from agno.agent import Agent
+from agno.models.anthropic import Claude
+from agno.tools.hackernews import HackerNewsTools
+
+agent = Agent(
+    model=Claude(id="claude-sonnet-4-0"),
+    tools=[HackerNewsTools()],
+    markdown=True,
+)
+agent.print_response("Summarize the top 5 stories on hackernews", stream=True)
+```
+
+But the real advantage of Agno is its [AgentOS](https://docs.agno.com/agent-os/introduction) runtime:
+
+1. You get a pre-built FastAPI app for running your agentic system, meaning you start building your product on day one. This is a remarkable advantage over other solutions or rolling your own.
+2. You also get a control plane which connects directly to your AgentOS for testing, monitoring and managing your system. This gives you unmatched visibility and control over your system.
+3. Your AgentOS runs in your cloud and you get complete data privacy because no data ever leaves your system. This is incredible for security conscious enterprises that can't send traces to external services.
+
+For organizations building agents, Agno provides the complete solution. You get the fastest framework for building agents (speed of development and execution), a pre-built FastAPI app that lets you build your product on day one, and a control plane for managing your system.
+
+We bring a novel architecture that no other framework provides, your AgentOS runs securely in your cloud, and the control plane connects directly to it from your browser. You don't need to send data to external services or pay retention costs, you get complete privacy and control.
+
+## Getting started
+
+If you're new to Agno, follow our [quickstart](https://docs.agno.com/introduction/quickstart) to build your first Agent and run it using the AgentOS.
+
+After that, checkout the [examples gallery](https://docs.agno.com/examples/introduction) and build real-world applications with Agno.
+
+## Documentation, Community & More examples
+
+- Docs: <a href="https://docs.agno.com" target="_blank" rel="noopener noreferrer">docs.agno.com</a>
+- Cookbook: <a href="https://github.com/agno-agi/agno/tree/main/cookbook" target="_blank" rel="noopener noreferrer">Cookbook</a>
+- Community forum: <a href="https://community.agno.com/" target="_blank" rel="noopener noreferrer">community.agno.com</a>
+- Discord: <a href="https://discord.gg/4MtYHHrgA8" target="_blank" rel="noopener noreferrer">discord</a>
+
+## Setup your coding agent to use Agno
+
+For LLMs and AI assistants to understand and navigate Agno's documentation, we provide an [llms.txt](https://docs.agno.com/llms.txt) or [llms-full.txt](https://docs.agno.com/llms-full.txt) file.
+
+This file is built for AI systems to efficiently parse and reference our documentation.
+
+### IDE Integration
+
+When building Agno agents, using Agno documentation as a source in your IDE is a great way to speed up your development. Here's how to integrate with Cursor:
+
+1. In Cursor, go to the "Cursor Settings" menu.
+2. Find the "Indexing & Docs" section.
+3. Add `https://docs.agno.com/llms-full.txt` to the list of documentation URLs.
+4. Save the changes.
+
+Now, Cursor will have access to the Agno documentation. You can do the same with other IDEs like VSCode, Windsurf etc.
+
+## Performance
+
+At Agno, we're obsessed with performance. Why? because even simple AI workflows can spawn thousands of Agents. Scale that to a modest number of users and performance becomes a bottleneck. Agno is designed for building highly performant agentic systems:
+
+- Agent instantiation: ~3μs on average
+- Memory footprint: ~6.5Kib on average
+
+> Tested on an Apple M4 Mackbook Pro.
+
+While an Agent's run-time is bottlenecked by inference, we must do everything possible to minimize execution time, reduce memory usage, and parallelize tool calls. These numbers may seem trivial at first, but our experience shows that they add up even at a reasonably small scale.
+
+### Instantiation time
+
+Let's measure the time it takes for an Agent with 1 tool to start up. We'll run the evaluation 1000 times to get a baseline measurement.
+
+You should run the evaluation yourself on your own machine, please, do not take these results at face value.
+
+```shell
+# Setup virtual environment
+./scripts/perf_setup.sh
+source .venvs/perfenv/bin/activate
+# OR Install dependencies manually
+# pip install openai agno langgraph langchain_openai
+
+# Agno
+python evals/performance/instantiation_with_tool.py
+
+# LangGraph
+python evals/performance/other/langgraph_instantiation.py
+```
+
+> The following evaluation is run on an Apple M4 Mackbook Pro. It also runs as a Github action on this repo.
+
+LangGraph is on the right, **let's start it first and give it a head start**.
+
+Agno is on the left, notice how it finishes before LangGraph gets 1/2 way through the runtime measurement, and hasn't even started the memory measurement. That's how fast Agno is.
+
+https://github.com/user-attachments/assets/ba466d45-75dd-45ac-917b-0a56c5742e23
+
+### Memory usage
+
+To measure memory usage, we use the `tracemalloc` library. We first calculate a baseline memory usage by running an empty function, then run the Agent 1000x times and calculate the difference. This gives a (reasonably) isolated measurement of the memory usage of the Agent.
+
+We recommend running the evaluation yourself on your own machine, and digging into the code to see how it works. If we've made a mistake, please let us know.
+
+### Conclusion
+
+Agno agents are designed for performance and while we do share some benchmarks against other frameworks, we should be mindful that accuracy and reliability are more important than speed.
+
+Given that each framework is different and we won't be able to tune their performance like we do with Agno, for future benchmarks we'll only be comparing against ourselves.
+
+## Contributions
+
+We welcome contributions, read our [contributing guide](https://github.com/agno-agi/agno/blob/v2.0/CONTRIBUTING.md) to get started.
+
+## Telemetry
+
+Agno logs which model an agent used so we can prioritize updates to the most popular providers. You can disable this by setting `AGNO_TELEMETRY=false` in your environment.
+
+<p align="left">
+  <a href="#top">⬆️ Back to Top</a>
+</p>