clarifai 10.5.1__py3-none-any.whl → 10.5.3__py3-none-any.whl

clarifai/client/auth/helper.py

@@ -5,6 +5,7 @@ from urllib.parse import urlparse
 
 from clarifai_grpc.channel.clarifai_channel import ClarifaiChannel
 from clarifai_grpc.grpc.api import resources_pb2, service_pb2_grpc
+from clarifai.utils.constants import CLARIFAI_PAT_ENV_VAR, CLARIFAI_SESSION_TOKEN_ENV_VAR
 
 DEFAULT_BASE = "https://api.clarifai.com"
 DEFAULT_UI = "https://clarifai.com"
@@ -237,8 +238,8 @@ Additionally, these optional params are supported:
     """
     user_id = os.environ.get("CLARIFAI_USER_ID", "")
     app_id = os.environ.get("CLARIFAI_APP_ID", "")
-    token = os.environ.get("CLARIFAI_SESSION_TOKEN", "")
-    pat = os.environ.get("CLARIFAI_PAT", "")
+    token = os.environ.get(CLARIFAI_SESSION_TOKEN_ENV_VAR, "")
+    pat = os.environ.get(CLARIFAI_PAT_ENV_VAR, "")
     base = os.environ.get("CLARIFAI_API_BASE", DEFAULT_BASE)
     ui = os.environ.get("CLARIFAI_UI", DEFAULT_UI)
     root_certificates_path = os.environ.get("CLARIFAI_ROOT_CERTIFICATES_PATH", None)

clarifai/datasets/upload/text.py

@@ -1,3 +1,4 @@
+import uuid
 from concurrent.futures import ThreadPoolExecutor
 from typing import List, Tuple, Type
 
@@ -33,7 +34,7 @@ class TextClassificationDataset(ClarifaiDataset):
       labels = data_item.labels if isinstance(data_item.labels,
                                               list) else [data_item.labels]  # clarifai concept
       label_ids = data_item.label_ids
-      input_id = f"{self.dataset_id}-{id}" if data_item.id is None else f"{self.dataset_id}-{str(data_item.id)}"
+      input_id = f"{self.dataset_id}-{uuid.uuid4().hex[:8]}" if data_item.id is None else f"{self.dataset_id}-{str(data_item.id)}"
       if data_item.metadata is not None:
         metadata.update(data_item.metadata)
 

clarifai/models/model_serving/cli/login.py

@@ -1,6 +1,6 @@
 import argparse
 
-from clarifai.utils.constants import CLARIFAI_PAT_PATH
+from clarifai.models.model_serving.constants import CLARIFAI_PAT_PATH
 from ..utils import _persist_pat
 from .base import BaseClarifaiCli
 

clarifai/models/model_serving/constants.py

@@ -1,13 +1,20 @@
 import os
 
-from clarifai.utils.constants import CLARIFAI_HOME
-
 MAX_HW_DIM = 1024
 IMAGE_TENSOR_NAME = "image"
 TEXT_TENSOR_NAME = "text"
 
 BUILT_MODEL_EXT = ".clarifai"
 
+USER_CACHE_DIR = os.path.join(os.path.expanduser("~"), ".cache")
+CLARIFAI_HOME = os.path.expanduser(
+    os.getenv(
+        "CLARIFAI_HOME",
+        os.path.join(os.getenv("XDG_CACHE_HOME", USER_CACHE_DIR), "clarifai"),
+    ))
+os.makedirs(CLARIFAI_HOME, exist_ok=True)
+CLARIFAI_PAT_PATH = os.path.join(CLARIFAI_HOME, "pat")
+
 CLARIFAI_EXAMPLES_REPO = "https://github.com/Clarifai/examples.git"
 repo_name = CLARIFAI_EXAMPLES_REPO.split("/")[-1].replace(".git", "")
 CLARIFAI_EXAMPLES_REPO_PATH = os.path.join(CLARIFAI_HOME, repo_name)

clarifai/models/model_serving/utils.py

@@ -1,6 +1,7 @@
 import os
 
-from clarifai.utils.constants import CLARIFAI_PAT_ENV_VAR, CLARIFAI_PAT_PATH
+from clarifai.models.model_serving.constants import CLARIFAI_PAT_PATH
+from clarifai.utils.constants import CLARIFAI_PAT_ENV_VAR
 
 
 def _persist_pat(pat: str):

clarifai/runners/deepgram_live_transcribe.py

@@ -0,0 +1,98 @@
+import os
+import httpx
+from dotenv import load_dotenv
+import threading
+
+from deepgram import (
+    DeepgramClient,
+    LiveTranscriptionEvents,
+    LiveOptions,
+)
+
+load_dotenv()
+
+# URL for the realtime streaming audio you would like to transcribe
+URL = "http://stream.live.vc.bbcmedia.co.uk/bbc_world_service"
+
+os.environ["DG_API_KEY"] = "1d5666523f0f2fbaf3e2db6ae7717f6f87280b5e"
+API_KEY = os.getenv("DG_API_KEY")
+
+
+def main():
+  try:
+    # STEP 1: Create a Deepgram client using the API key
+    deepgram = DeepgramClient(API_KEY)
+
+    # STEP 2: Create a websocket connection to Deepgram
+    dg_connection = deepgram.listen.live.v("1")
+
+    # STEP 3: Define the event handlers for the connection
+    def on_message(self, result, **kwargs):
+      sentence = result.channel.alternatives[0].transcript
+      if len(sentence) == 0:
+        return
+      print(f"speaker: {sentence}")
+
+    def on_metadata(self, metadata, **kwargs):
+      print(f"\n\n{metadata}\n\n")
+
+    def on_error(self, error, **kwargs):
+      print(f"\n\n{error}\n\n")
+
+    # STEP 4: Register the event handlers
+    dg_connection.on(LiveTranscriptionEvents.Transcript, on_message)
+    dg_connection.on(LiveTranscriptionEvents.Metadata, on_metadata)
+    dg_connection.on(LiveTranscriptionEvents.Error, on_error)
+
+    # STEP 5: Configure Deepgram options for live transcription
+    options = LiveOptions(
+        model="nova-2",
+        language="en-US",
+        smart_format=True,
+    )
+
+    # STEP 6: Start the connection
+    dg_connection.start(options)
+
+    # STEP 7: Create a lock and a flag for thread synchronization
+    lock_exit = threading.Lock()
+    exit = False
+
+    # STEP 8: Define a thread that streams the audio and sends it to Deepgram
+    def myThread():
+      with httpx.stream("GET", URL) as r:
+        for data in r.iter_bytes():
+          lock_exit.acquire()
+          if exit:
+            break
+          lock_exit.release()
+
+          dg_connection.send(data)
+
+    # STEP 9: Start the thread
+    myHttp = threading.Thread(target=myThread)
+    myHttp.start()
+
+    # STEP 10: Wait for user input to stop recording
+    input("Press Enter to stop recording...\n\n")
+
+    # STEP 11: Set the exit flag to True to stop the thread
+    lock_exit.acquire()
+    exit = True
+    lock_exit.release()
+
+    # STEP 12: Wait for the thread to finish
+    myHttp.join()
+
+    # STEP 13: Close the connection to Deepgram
+    dg_connection.finish()
+
+    print("Finished")
+
+  except Exception as e:
+    print(f"Could not open socket: {e}")
+    return
+
+
+if __name__ == "__main__":
+  main()

clarifai/runners/deepgram_live_transcribe.py~

@@ -0,0 +1,98 @@
+import os
+import httpx
+from dotenv import load_dotenv
+import threading
+
+from deepgram import (
+    DeepgramClient,
+    LiveTranscriptionEvents,
+    LiveOptions,
+)
+
+load_dotenv()
+
+# URL for the realtime streaming audio you would like to transcribe
+URL = "http://stream.live.vc.bbcmedia.co.uk/bbc_world_service"
+
+os.environ.set("DG_API_KEY", "1d5666523f0f2fbaf3e2db6ae7717f6f87280b5e")
+API_KEY = os.getenv("DG_API_KEY")
+
+
+def main():
+  try:
+    # STEP 1: Create a Deepgram client using the API key
+    deepgram = DeepgramClient(API_KEY)
+
+    # STEP 2: Create a websocket connection to Deepgram
+    dg_connection = deepgram.listen.live.v("1")
+
+    # STEP 3: Define the event handlers for the connection
+    def on_message(self, result, **kwargs):
+      sentence = result.channel.alternatives[0].transcript
+      if len(sentence) == 0:
+        return
+      print(f"speaker: {sentence}")
+
+    def on_metadata(self, metadata, **kwargs):
+      print(f"\n\n{metadata}\n\n")
+
+    def on_error(self, error, **kwargs):
+      print(f"\n\n{error}\n\n")
+
+    # STEP 4: Register the event handlers
+    dg_connection.on(LiveTranscriptionEvents.Transcript, on_message)
+    dg_connection.on(LiveTranscriptionEvents.Metadata, on_metadata)
+    dg_connection.on(LiveTranscriptionEvents.Error, on_error)
+
+    # STEP 5: Configure Deepgram options for live transcription
+    options = LiveOptions(
+        model="nova-2",
+        language="en-US",
+        smart_format=True,
+    )
+
+    # STEP 6: Start the connection
+    dg_connection.start(options)
+
+    # STEP 7: Create a lock and a flag for thread synchronization
+    lock_exit = threading.Lock()
+    exit = False
+
+    # STEP 8: Define a thread that streams the audio and sends it to Deepgram
+    def myThread():
+      with httpx.stream("GET", URL) as r:
+        for data in r.iter_bytes():
+          lock_exit.acquire()
+          if exit:
+            break
+          lock_exit.release()
+
+          dg_connection.send(data)
+
+    # STEP 9: Start the thread
+    myHttp = threading.Thread(target=myThread)
+    myHttp.start()
+
+    # STEP 10: Wait for user input to stop recording
+    input("Press Enter to stop recording...\n\n")
+
+    # STEP 11: Set the exit flag to True to stop the thread
+    lock_exit.acquire()
+    exit = True
+    lock_exit.release()
+
+    # STEP 12: Wait for the thread to finish
+    myHttp.join()
+
+    # STEP 13: Close the connection to Deepgram
+    dg_connection.finish()
+
+    print("Finished")
+
+  except Exception as e:
+    print(f"Could not open socket: {e}")
+    return
+
+
+if __name__ == "__main__":
+  main()

clarifai/runners/deepgram_runner.py

@@ -0,0 +1,131 @@
+import os
+import time
+import httpx
+from dotenv import load_dotenv
+import threading
+import queue
+import hashlib
+
+from deepgram import (
+    DeepgramClient,
+    LiveTranscriptionEvents,
+    LiveOptions,
+)
+
+load_dotenv()
+
+os.environ["DG_API_KEY"] = "1d5666523f0f2fbaf3e2db6ae7717f6f87280b5e"
+API_KEY = os.getenv("DG_API_KEY")
+
+from clarifai_grpc.grpc.api import resources_pb2, service_pb2
+from collections.abc import Iterator
+from google.protobuf import json_format
+
+from clarifai.client.runner import Runner
+
+
+class MyRunner(Runner):
+  """A custom runner that adds "Hello World" to the end of the text and replaces the domain of the
+  image URL as an example.
+  """
+
+  def setup_connection(self):
+    print("ZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZz")
+    # STEP 2: Create a websocket connection to Deepgram
+    self.dg_connection = self.deepgram.listen.live.v("1")
+
+    output_q = self.output_q
+
+    # STEP 3: Define the event handlers for the connection
+    def on_message(self, result, **kwargs):
+      if result.is_final:
+        sentence = result.channel.alternatives[0].transcript
+        if len(sentence) == 0:
+          return
+        print("SSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSS")
+        print(f"speaker: {sentence}")
+        # put it on a queue as we get responses from deepgram.
+        output_q.put(sentence)
+
+    def on_metadata(self, metadata, **kwargs):
+      print(f"\n\n{metadata}\n\n")
+
+    def on_error(self, error, **kwargs):
+      print(f"\n\n{error}\n\n")
+
+    # STEP 4: Register the event handlers
+    self.dg_connection.on(LiveTranscriptionEvents.Transcript, on_message)
+    self.dg_connection.on(LiveTranscriptionEvents.Metadata, on_metadata)
+    self.dg_connection.on(LiveTranscriptionEvents.Error, on_error)
+
+    # STEP 5: Configure Deepgram options for live transcription
+    self.options = LiveOptions(
+        model="nova-2",
+        language="en-US",
+        smart_format=True,
+    )
+
+    # STEP 6: Start the connection
+    self.dg_connection.start(self.options)
+
+    print("DDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDD")
+    print(self.dg_connection._socket)
+
+  def __init__(self, *args, **kwargs):
+    print("MyRunner init")
+    # STEP 1: Create a Deepgram client using the API key
+    self.deepgram = DeepgramClient(API_KEY)
+    self.output_q = queue.Queue()
+
+    self.setup_connection()
+
+    super().__init__(*args, **kwargs)
+
+  def stream(self, request: service_pb2.PostModelOutputsRequest
+            ) -> Iterator[service_pb2.MultiOutputResponse]:
+    """Example yielding a whole batch of streamed stuff back.
+    """
+
+    assert len(request.inputs) == 1, "This runner only supports one input at a time."
+
+    # Get the next chunk of data from the incoming stream.
+
+    print("Got some audio data")
+
+    data = request.inputs[0].data.audio.base64
+    print(hashlib.md5(data).hexdigest())
+
+    # FIXME(zeiler): this doesnt' work but isn't iportant to our system.
+    if not self.dg_connection._socket:
+      #self.dg_connection.finish()
+      #self.dg_connection.start(self.options)
+      self.setup_connection()
+    self.dg_connection.send(data)
+    print("Sent it to deepgram")
+
+    while True:
+      try:
+        item = self.output_q.get(timeout=0.1)
+        output = resources_pb2.Output()
+        output.data.text.raw = item
+        output.status.code = 10000
+        print("YYYYYYYYYYYYYYYYYYYYYYYYYYYYYY")
+        print("Yielding: ", output.data.text.raw)
+        yield service_pb2.MultiOutputResponse(outputs=[
+            output,
+        ])
+      except queue.Empty:
+        print("Queue is empty, sleeping then breaking")
+        break
+
+  # # STEP 13: Close the connection to Deepgram
+  # dg_connection.finish()
+
+
+if __name__ == '__main__':
+  # Make sure you set these env vars before running the example.
+  # CLARIFAI_PAT
+  # CLARIFAI_USER_ID
+
+  # You need to first create a runner in the Clarifai API and then use the ID here.
+  MyRunner(runner_id="matt-test-runner", base_url="http://q6:32013", num_parallel_polls=1).start()