dhisana 0.0.1.dev4__tar.gz → 0.0.1.dev5__tar.gz

{dhisana-0.0.1.dev4 → dhisana-0.0.1.dev5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: dhisana
-Version: 0.0.1.dev4
+Version: 0.0.1.dev5
 Summary: A Python SDK for Dhisana AI Platform
 Home-page: https://github.com/dhisana-ai/dhisana-python-sdk
 Author: Admin

{dhisana-0.0.1.dev4 → dhisana-0.0.1.dev5}/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
 
 setup(
     name='dhisana',  
-    version='0.0.1-dev4',
+    version='0.0.1-dev5',
     description='A Python SDK for Dhisana AI Platform',
     author='Admin',
     author_email='contact@dhisana.ai',

{dhisana-0.0.1.dev4 → dhisana-0.0.1.dev5}/src/dhisana/ui/components.py

@@ -110,7 +110,7 @@ class Chart(Component):
 
 
 class Form(Component):
-    def __init__(self, children: List[Component], on_submit: str):
+    def __init__(self, children: List[Component], on_submit: List[str]):
         self.children = children
         self.on_submit = on_submit
 

{dhisana-0.0.1.dev4 → dhisana-0.0.1.dev5}/src/dhisana/utils/openai_helpers.py

@@ -58,6 +58,8 @@ async def run_assistant(client, assistant, thread, prompt, response_type, allowe
     while run.status == 'requires_action':
         if iteration_count >= max_iterations:
             print("Exceeded maximum number of iterations for requires_action.")
+            # Cancel the run before returning
+            await client.beta.threads.runs.cancel(run_id=run.id)
             return "Error: Exceeded maximum number of iterations for requires_action."
 
         tool_outputs = await handle_required_action(run)
@@ -69,6 +71,7 @@ async def run_assistant(client, assistant, thread, prompt, response_type, allowe
     return await handle_run_completion(client, thread, run)
 
 
+
 async def send_initial_message(client, thread, prompt):
     client.beta.threads.messages.create(
         thread_id=thread.id,
@@ -103,6 +106,7 @@ async def handle_required_action(run):
     tool_outputs = []
     current_batch_size = 0
     max_batch_size = 256 * 1024  # 256 KB
+    print(f"Handling required action")
 
     if hasattr(run, 'required_action') and hasattr(run.required_action, 'submit_tool_outputs'):
         for tool in run.required_action.submit_tool_outputs.tool_calls:
@@ -243,24 +247,19 @@ async def process_agent_request(row_batch: List[Dict], workflow: Dict, custom_in
             model="gpt-4o-2024-08-06"
         )
         thread = client.beta.threads.create()
-
         parsed_outputs = []
-        for row in row_batch:
-            try:
-                task_outputs = {}  # Dictionary to store outputs of tasks
-                input_list = {}
-                input_list['initial_input_list'] = {
-                    "data": [row],
-                    "format": "list"
-                  }
-                task_outputs['initial_input'] = input_list
-                for task in workflow['tasks']:
-                    # Process each task
-                    task_outputs = await process_task(client, assistant, thread, row, task, task_outputs)
-                # Collect the final output
-                parsed_outputs.append(task_outputs)
-            except Exception as e:
-                print(f"Error processing row {row}: {e}")
+        task_outputs = {}  # Dictionary to store outputs of tasks
+        input_list = {}
+        input_list['initial_input_list'] = {
+            "data": row_batch,
+            "format": "list"
+            }
+        task_outputs['initial_input'] = input_list
+        for task in workflow['tasks']:
+            # Process each task
+            task_outputs = await process_task(client, assistant, thread, task, task_outputs)
+        # Collect the final output
+        parsed_outputs.append(task_outputs)
         return parsed_outputs
     except Exception as e:
         print(f"An error occurred: {e}")
@@ -272,24 +271,20 @@ async def process_agent_request(row_batch: List[Dict], workflow: Dict, custom_in
             print(f"Error deleting assistant: {e}")
 
 
-async def process_task(client, assistant, thread, row, task, task_outputs):
+async def process_task(client, assistant, thread, task, task_outputs):
     """
     Process a single task in the workflow.
     """
-    try:
-        # Prepare inputs
-        task_inputs = await prepare_task_inputs(row, task, task_outputs)
+    # Prepare inputs
+    task_inputs = await prepare_task_inputs(task, task_outputs)
 
-        # Run the operation
-        output = await run_task_operation(client, assistant, thread, task, task_inputs)
+    # Run the operation
+    output = await run_task_operation(client, assistant, thread, task, task_inputs)
 
-        # Store outputs
-        await store_task_outputs(task, output, task_outputs)
+    # Store outputs
+    await store_task_outputs(task, output, task_outputs)
 
-        return task_outputs
-    except Exception as e:
-        print(f"Error processing task {task['id']}: {e}")
-        return task_outputs
+    return task_outputs
 
 async def read_csv_rows(file_path):
     rows = []
@@ -299,7 +294,7 @@ async def read_csv_rows(file_path):
             rows.append(row)
     return rows
 
-async def prepare_task_inputs(row, task, task_outputs):
+async def prepare_task_inputs(task, task_outputs):
     """
     Prepare the inputs for a task based on its input specifications.
     """
@@ -309,15 +304,11 @@ async def prepare_task_inputs(row, task, task_outputs):
         source = input_spec.get('source', {})
         source_type = source.get('type', '')
         format = input_spec.get('format', 'list')
-        if source_type == 'external':
-            # External source, get from initial input
-            input_data = row.get(input_name, row)
-        elif source_type == 'task_output':
+        if source_type == 'task_output':
             # Get from previous task output
             task_id = source.get('task_id')
             output_key = source.get('output_key')
-            previous_task_output = task_outputs.get(task_id, {})
-            print(f"Previous task output: {previous_task_output} Output key: {output_key}")
+            previous_task_output = task_outputs.get(task_id, {})            
             if isinstance(previous_task_output, dict):
                 output_item = previous_task_output.get(output_key)
                 input_data = output_item['data']
@@ -361,14 +352,17 @@ async def run_task_operation(client, assistant, thread, task, task_inputs):
         args = operation.get('args', [])
         # Prepare prompt by substituting inputs
         
-        formatted_prompt = prompt_template
+        
         for key, value in task_inputs.items():
             format = value.get('format', 'list')
             if format == 'list':
-                for item in value.get('data'):
+                items = value.get('data')
+                for item in items:
+                    formatted_prompt = prompt_template
                     formatted_prompt = formatted_prompt.replace(
                         "{{ inputs." + key + " }}", json.dumps(item))
                     # Run assistant with prompt
+                    print(formatted_prompt)
                     output = await extract_and_structure_data(
                         client, assistant, thread, formatted_prompt, task_inputs, response_type, allowed_tools)
                     outputs.append(output)
@@ -419,7 +413,7 @@ async def store_task_outputs(task, output, task_outputs):
                     local_path = path
 
                     if dest_type == 'google_drive':
-                        local_path = os.path.join('/tmp', path)
+                        local_path = os.path.join('/tmp', task['id'], path)
 
                     if dest_type == 'google_drive' or dest_type == 'local_path':
                         directory = os.path.dirname(local_path)
@@ -429,6 +423,9 @@ async def store_task_outputs(task, output, task_outputs):
                             if output.get("format", "") == 'list':
                                 data_list = [json.loads(item) for item in output.get("data", [])]
                                 if data_list:
+                                    dedup_by = output_spec.get('deduplication_properties', [])
+                                    if dedup_by:
+                                        data_list = deduplicate_list_by_properties(data_list, dedup_by)
                                     # Filter headers to include only simple types
                                     headers = [key for key, value in data_list[0].items() if isinstance(value, (str, int, float, bool))]
                                     writer = csv.DictWriter(file, fieldnames=headers)
@@ -450,6 +447,21 @@ async def store_task_outputs(task, output, task_outputs):
         # If no outputs are defined, store the output under the task id
         task_outputs[task['id']] = output
 
+def deduplicate_list_by_properties(data_list, properties):
+    """
+    Deduplicate a list of dictionaries by a list of properties in order.
+    """
+    for property_name in properties:
+        seen = set()
+        deduplicated_list = []
+        for item in data_list:
+            value = item.get(property_name)
+            if value not in seen:
+                seen.add(value)
+                deduplicated_list.append(item)
+        data_list = deduplicated_list
+    return data_list
+
 async def write_to_google_drive(cloud_path, local_path):
     # Placeholder function for writing to Google Drive
     await write_content_to_googledrive(cloud_path, local_path)

{dhisana-0.0.1.dev4 → dhisana-0.0.1.dev5}/src/dhisana.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: dhisana
-Version: 0.0.1.dev4
+Version: 0.0.1.dev5
 Summary: A Python SDK for Dhisana AI Platform
 Home-page: https://github.com/dhisana-ai/dhisana-python-sdk
 Author: Admin