Added graph intefrace, added neo4j + networkx structure and updates to the notebook

cognitive_architecture/infrastructure/llm/openai/adapter.py

@@ -180,11 +180,11 @@ class OpenAIAdapter(LLMInterface):
 
         return embeddings
 
-    async def acreate_structured_output(self, text_input: str, system_prompt_path: str, response_model: Type[BaseModel], model:str) -> BaseModel:
+    async def acreate_structured_output(self, text_input: str, system_prompt_path: str, response_model: Type[BaseModel]) -> BaseModel:
         """Generate a response from a user query."""
         system_prompt = read_query_prompt(system_prompt_path)
         return self.aclient.chat.completions.create(
-            model=model,
+            model=self.model,
             messages=[
                 {
                     "role": "user",

cognitive_architecture/modules/cognify/llm/classify_content.py

@@ -1,13 +1,15 @@
+from pydantic import BaseModel
+from typing import Type
 from cognitive_architecture.infrastructure.llm.get_llm_client import get_llm_client
+from cognitive_architecture.shared.data_models import ContentPrediction
 
-
+async def content_to_cog_layers(text_input: str,system_prompt_path:str, response_model: Type[BaseModel]):
-async def content_to_cog_layers(memory_name: str, payload: list):
     llm_client = get_llm_client()
 
     # data_points = list()
     # for point in map(create_data_point, payload):
     #     data_points.append(await point)
 
-    return await llm_client.acreate_structured_output(memory_name, payload, model="text-embedding-ada-002")
+    return await llm_client.acreate_structured_output(text_input,system_prompt_path, response_model)
 
 

cognitive_architecture/modules/cognify/llm/content_to_cog_layers.py

@@ -1,14 +1,16 @@
+from typing import Type
+from pydantic import BaseModel
 from cognitive_architecture.infrastructure.llm.get_llm_client import get_llm_client
 
 
-async def content_to_cog_layers(memory_name: str, payload: list):
+async def content_to_cog_layers(text_input: str,system_prompt_path:str, response_model: Type[BaseModel]):
     llm_client = get_llm_client()
 
     # data_points = list()
     # for point in map(create_data_point, payload):
     #     data_points.append(await point)
 
-    return await llm_client.acreate_structured_output(memory_name, payload, model="text-embedding-ada-002")
+    return await llm_client.acreate_structured_output(text_input,system_prompt_path, response_model)
 
 
 

cognitive_architecture/modules/cognify/llm/content_to_propositions.py

@@ -1,9 +1,11 @@
 """ Content to Propositions"""
+from typing import Type
+from pydantic import BaseModel
 from cognitive_architecture.infrastructure.llm.get_llm_client import get_llm_client
 
 
-async def generate_graph(memory_name: str, payload: str):
+async def generate_graph(text_input:str,system_prompt_path:str, response_model: Type[BaseModel]):
     doc_path = "cognitive_architecture/infrastructure/llm/prompts/generate_graph_prompt.txt"
     llm_client = get_llm_client()
-    return await llm_client.generate_graph(memory_name,  doc_path=doc_path,payload= payload)
+    return await llm_client.generate_graph(text_input,system_prompt_path, response_model)
 

cognitive_architecture/shared/data_models.py

@@ -161,7 +161,7 @@ class ProceduralContent(ContentType):
     type = "PROCEDURAL"
     subclass: List[ProceduralSubclass]
 
-class SinglePrediction(BaseModel):
+class ContentPrediction(BaseModel):
     """Class for a single class label prediction."""
 
     label: Union[TextContent, AudioContent, ImageContent, VideoContent, MultimediaContent, Model3DContent, ProceduralContent]