agent.md

mkdocs.yml

@@ -96,7 +96,7 @@ nav:
   - swarms.structs:
     - Overview: "swarms/structs/overview.md"
     - AutoScaler: "swarms/swarms/autoscaler.md"
-    - Flow: "swarms/structs/flow.md"
+    - Agent: "swarms/structs/agent.md"
     - SequentialWorkflow: 'swarms/structs/sequential_workflow.md'
   - swarms.memory:
     - PineconeVectorStoreStore: "swarms/memory/pinecone.md"

playground/demos/xray/xray.py

@@ -54,7 +54,7 @@ def generate_treatment_plan(diagnosis):
 xray_image_path = "playground/demos/xray/xray2.jpg"
 
 
-# Diagnosis 
+# Diagnosis
 diagnosis = analyze_xray_agent.run(
     task="Analyze the following XRAY", img=xray_image_path
 )

swarms/memory/qdrant.py

@@ -6,6 +6,23 @@ from qdrant_client.http.models import Distance, VectorParams, PointStruct
 
 
 class Qdrant:
+    """
+    Qdrant class for managing collections and performing vector operations using QdrantClient.
+
+    Attributes:
+        client (QdrantClient): The Qdrant client for interacting with the Qdrant server.
+        collection_name (str): Name of the collection to be managed in Qdrant.
+        model (SentenceTransformer): The model used for generating sentence embeddings.
+
+    Args:
+        api_key (str): API key for authenticating with Qdrant.
+        host (str): Host address of the Qdrant server.
+        port (int): Port number of the Qdrant server. Defaults to 6333.
+        collection_name (str): Name of the collection to be used or created. Defaults to "qdrant".
+        model_name (str): Name of the model to be used for embeddings. Defaults to "BAAI/bge-small-en-v1.5".
+        https (bool): Flag to indicate if HTTPS should be used. Defaults to True.
+    """
+
     def __init__(
         self,
         api_key: str,
@@ -15,22 +32,6 @@ class Qdrant:
         model_name: str = "BAAI/bge-small-en-v1.5",
         https: bool = True,
     ):
-        """
-        Qdrant class for managing collections and performing vector operations using QdrantClient.
-
-        Attributes:
-            client (QdrantClient): The Qdrant client for interacting with the Qdrant server.
-            collection_name (str): Name of the collection to be managed in Qdrant.
-            model (SentenceTransformer): The model used for generating sentence embeddings.
-
-        Args:
-            api_key (str): API key for authenticating with Qdrant.
-            host (str): Host address of the Qdrant server.
-            port (int): Port number of the Qdrant server. Defaults to 6333.
-            collection_name (str): Name of the collection to be used or created. Defaults to "qdrant".
-            model_name (str): Name of the model to be used for embeddings. Defaults to "BAAI/bge-small-en-v1.5".
-            https (bool): Flag to indicate if HTTPS should be used. Defaults to True.
-        """
         try:
             self.client = QdrantClient(url=host, port=port, api_key=api_key)
             self.collection_name = collection_name

swarms/structs/agent.py

@@ -15,6 +15,7 @@ from swarms.utils.parse_code import extract_code_in_backticks_in_string
 from swarms.prompts.multi_modal_autonomous_instruction_prompt import (
     MULTI_MODAL_AUTO_AGENT_SYSTEM_PROMPT_1,
 )
+from swarms.utils.pdf_to_text import pdf_to_text
 
 # System prompt
 FLOW_SYSTEM_PROMPT = f"""
@@ -252,6 +253,10 @@ class Agent:
         self_healing_enabled: Optional[bool] = False,
         code_interpreter: Optional[bool] = False,
         multi_modal: Optional[bool] = None,
+        pdf_path: Optional[str] = None,
+        list_of_pdf: Optional[str] = None,
+        tokenizer: Optional[str] = None,
+        *args,
         **kwargs: Any,
     ):
         self.llm = llm
@@ -282,6 +287,9 @@ class Agent:
         self.self_healing_enabled = self_healing_enabled
         self.code_interpreter = code_interpreter
         self.multi_modal = multi_modal
+        self.pdf_path = pdf_path
+        self.list_of_pdf = list_of_pdf
+        self.tokenizer = tokenizer
 
         # The max_loops will be set dynamically if the dynamic_loop
         if self.dynamic_loops:
@@ -351,10 +359,6 @@ class Agent:
 
         return "\n".join(params_str_list)
 
-    # def parse_tool_command(self, text: str):
-    #     # Parse the text for tool usage
-    #     pass
-
     def get_tool_description(self):
         """Get the tool description"""
         if self.tools:
@@ -1111,6 +1115,31 @@ class Agent:
         run_code = self.code_executor.run(parsed_code)
         return run_code
 
+    def pdf_connector(self, pdf: str = None):
+        """Transforms the pdf into text
+
+        Args:
+            pdf (str, optional): _description_. Defaults to None.
+
+        Returns:
+            _type_: _description_
+        """
+        pdf = pdf or self.pdf_path
+        text = pdf_to_text(pdf)
+        return text
+
+    def pdf_chunker(self, text: str = None):
+        """Chunk the pdf into sentences
+
+        Args:
+            text (str, optional): _description_. Defaults to None.
+
+        Returns:
+            _type_: _description_
+        """
+        text = text or self.pdf_connector()
+        pass
+
     def tools_prompt_prep(self, docs: str = None, scenarios: str = None):
         """
         Prepare the tool prompt