auto saved + fixed run method of flow

demos/positive_med.py

@@ -23,7 +23,7 @@ Distribution Agent:
 
 """
 
-from swarms import OpenAIChat
+from swarms.models import OpenAIChat
 from termcolor import colored
 
 TOPIC_GENERATOR = f"""
@@ -264,7 +264,7 @@ Denote the social media's by using the social media name in HTML like tags
 {{ARTICLE}}
 """
 
-llm = OpenAIChat(openai_api_key="")
+llm = OpenAIChat(openai_api_key="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")
 
 
 def get_review_prompt(article):

example.py

@@ -1,7 +1,7 @@
 from swarms.models import OpenAIChat
 from swarms.structs import Flow
 
-api_key = ""
+api_key = "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"
 
 # Initialize the language model, this model can be swapped out with Anthropic, ETC, Huggingface Models like Mistral, ETC
 llm = OpenAIChat(
@@ -14,7 +14,7 @@ llm = OpenAIChat(
 ## Initialize the workflow
 flow = Flow(
     llm=llm,
-    max_loops=1,
+    max_loops=2,
     dashboard=True,
     # stopping_condition=None,  # You can define a stopping condition as needed.
     # loop_interval=1,
@@ -31,5 +31,5 @@ out = flow.run("Generate a 10,000 word blog on health and wellness.")
 # out = flow.validate_response(out)
 # out = flow.analyze_feedback(out)
 # out = flow.print_history_and_memory()
-# out = flow.save_state("flow_state.json")
-print(out)
+# # out = flow.save_state("flow_state.json")
+# print(out)

flow_state.json

@@ -1,14 +0,0 @@
-{
-    "memory": [
-        [
-            "Human: Generate a 10,000 word blog on health and wellness."
-        ]
-    ],
-    "llm_params": {},
-    "loop_interval": 1,
-    "retry_attempts": 3,
-    "retry_interval": 1,
-    "interactive": false,
-    "dashboard": true,
-    "dynamic_temperature": false
-}

swarms/models/fuyu.py

@@ -60,7 +60,5 @@ class Fuyu:
         for k, v in model_inputs.items():
             model_inputs[k] = v.to(self.device_map)
 
-        output = self.model.generate(
-            **model_inputs, max_new_tokens=self.max_new_tokens
-        )
+        output = self.model.generate(**model_inputs, max_new_tokens=self.max_new_tokens)
         text = self.processor.batch_decode(output[:, -7:], skip_special_tokens=True)

swarms/structs/flow.py

@@ -105,6 +105,8 @@ class Flow:
         system_message: str = FLOW_SYSTEM_PROMPT,
         # tools: List[BaseTool] = None,
         dynamic_temperature: bool = False,
+        saved_state: Optional[str] = None,
+        autosave: bool = False,
         **kwargs: Any,
     ):
         self.llm = llm
@@ -124,6 +126,9 @@ class Flow:
         # self.tools = tools
         self.system_message = system_message
         self.name = name
+        self.saved_state = saved_state
+        self.autosave = autosave
+        self.response_filters = []
 
     def provide_feedback(self, feedback: str) -> None:
         """Allow users to provide feedback on the responses."""
@@ -206,7 +211,7 @@ class Flow:
 
         print(dashboard)
 
-    def run(self, task: str, save: bool = True, **kwargs):
+    def run(self, task: str, **kwargs):
         """
         Run the autonomous agent loop
 
@@ -220,15 +225,15 @@ class Flow:
         4. If stopping condition is not met, generate a response
         5. Repeat until stopping condition is met or max_loops is reached
 
-        Example:
-        >>> out = flow.run("Generate a 10,000 word blog on health and wellness.")
-
         """
-        # Start with a new history or continue from the last saved state
-        if not self.memory or not self.memory[-1]:
-            history = [f"Human: {task}"]
-        else:
-            history = self.memory[-1]
+        # Restore from saved state if provided, ortherwise start with a new history
+        # if self.saved_state:
+        #     self.load_state(self.saved_state)
+        #     history = self.memory[-1]
+        #     print(f"Loaded state from {self.saved_state}")
+        # else:
+        #     history = [f"Human: {task}"]
+        #     self.memory.append(history)
 
         response = task
         history = [f"Human: {task}"]
@@ -237,12 +242,9 @@ class Flow:
         if self.dashboard:
             self.print_dashboard(task)
 
-        # Start or continue the loop process
-        for i in range(len(history), self.max_loops):
+        for i in range(self.max_loops):
             print(colored(f"\nLoop {i+1} of {self.max_loops}", "blue"))
             print("\n")
-            response = history[-1].split(": ", 1)[-1]  # Get the last response
-
             if self._check_stopping_condition(response) or parse_done_token(response):
                 break
 
@@ -254,8 +256,8 @@ class Flow:
             while attempt < self.retry_attempts:
                 try:
                     response = self.llm(
-                        self.agent_history_prompt(FLOW_SYSTEM_PROMPT, response)
-                        ** kwargs,
+                        self.agent_history_prompt(FLOW_SYSTEM_PROMPT, response),
+                        **kwargs,
                     )
                     # print(f"Next query: {response}")
                     # break
@@ -277,8 +279,8 @@ class Flow:
             time.sleep(self.loop_interval)
         self.memory.append(history)
 
-        if save:
-            self.save("flow_history.json")
+        # if self.autosave:
+        #     self.save_state("flow_state.json")
 
         return response  # , history
 
@@ -353,8 +355,8 @@ class Flow:
             time.sleep(self.loop_interval)
         self.memory.append(history)
 
-        if save:
-            self.save_state("flow_history.json")
+        # if save:
+        #     self.save_state("flow_history.json")
 
         return response  # , history
 
@@ -409,7 +411,13 @@ class Flow:
             json.dump(self.memory, f)
         print(f"Saved flow history to {file_path}")
 
-    def load(self, file_path) -> None:
+    def load(self, file_path: str):
+        """
+        Load the flow history from a file.
+
+        Args:
+            file_path (str): The path to the file containing the saved flow history.
+        """
         with open(file_path, "r") as f:
             self.memory = json.load(f)
         print(f"Loaded flow history from {file_path}")
@@ -660,10 +668,6 @@ class Flow:
         with open(file_path, "r") as f:
             state = json.load(f)
 
-        # Assuming 'llm_class' is a class reference to the language
-        # llm_params = state.get("llm_params", {})
-        # self.llm = self.llm(**llm_params)
-
         # Restore other saved attributes
         self.memory = state.get("memory", [])
         self.max_loops = state.get("max_loops", 5)

tests/models/anthropic.py

@@ -3,6 +3,7 @@ import pytest
 from unittest.mock import Mock, patch
 from swarms.models.anthropic import Anthropic
 
+
 @pytest.fixture
 def mock_anthropic_env():
     os.environ["ANTHROPIC_API_URL"] = "https://test.anthropic.com"
@@ -11,15 +12,18 @@ def mock_anthropic_env():
     del os.environ["ANTHROPIC_API_URL"]
     del os.environ["ANTHROPIC_API_KEY"]
 
+
 @pytest.fixture
 def mock_requests_post():
     with patch("requests.post") as mock_post:
         yield mock_post
 
+
 @pytest.fixture
 def anthropic_instance():
     return Anthropic(model="test-model")
 
+
 def test_anthropic_init_default_values(anthropic_instance):
     assert anthropic_instance.model == "test-model"
     assert anthropic_instance.max_tokens_to_sample == 256
@@ -31,6 +35,7 @@ def test_anthropic_init_default_values(anthropic_instance):
     assert anthropic_instance.anthropic_api_url == "https://test.anthropic.com"
     assert anthropic_instance.anthropic_api_key == "test_api_key"
 
+
 def test_anthropic_init_custom_values():
     anthropic_instance = Anthropic(
         model="custom-model",
@@ -49,6 +54,7 @@ def test_anthropic_init_custom_values():
     assert anthropic_instance.streaming is True
     assert anthropic_instance.default_request_timeout == 300
 
+
 def test_anthropic_default_params(anthropic_instance):
     default_params = anthropic_instance._default_params()
     assert default_params == {
@@ -56,6 +62,7 @@ def test_anthropic_default_params(anthropic_instance):
         "model": "test-model",
     }
 
+
 def test_anthropic_run(mock_anthropic_env, mock_requests_post, anthropic_instance):
     mock_response = Mock()
     mock_response.json.return_value = {"completion": "Generated text"}
@@ -79,6 +86,7 @@ def test_anthropic_run(mock_anthropic_env, mock_requests_post, anthropic_instanc
         timeout=600,
     )
 
+
 def test_anthropic_call(mock_anthropic_env, mock_requests_post, anthropic_instance):
     mock_response = Mock()
     mock_response.json.return_value = {"completion": "Generated text"}
@@ -102,7 +110,10 @@ def test_anthropic_call(mock_anthropic_env, mock_requests_post, anthropic_instan
         timeout=600,
     )
 
-def test_anthropic_exception_handling(mock_anthropic_env, mock_requests_post, anthropic_instance):
+
+def test_anthropic_exception_handling(
+    mock_anthropic_env, mock_requests_post, anthropic_instance
+):
     mock_response = Mock()
     mock_response.json.return_value = {"error": "An error occurred"}
     mock_requests_post.return_value = mock_response

tests/models/distilled_whisperx.py

@@ -117,4 +117,3 @@ async def test_async_transcribe_with_mocked_model(mocked_model, audio_file_path)
     model_wrapper = DistilWhisperModel()
     transcription = await model_wrapper.async_transcribe(audio_file_path)
     assert transcription == "mocked transcription"
-