fix(schema): fixed json output

Author: PeriniM

requirements-dev.lock

@@ -185,10 +185,6 @@ idna==3.7
     # via yarl
 imagesize==1.4.1
     # via sphinx
-importlib-metadata==7.1.0
-    # via sphinx
-importlib-resources==6.4.0
-    # via matplotlib
 iniconfig==2.0.0
     # via pytest
 jinja2==3.1.4
@@ -475,7 +471,6 @@ typing-extensions==4.12.0
     # via pyee
     # via sf-hamilton
     # via sqlalchemy
-    # via starlette
     # via streamlit
     # via typer
     # via typing-inspect
@@ -507,6 +502,3 @@ win32-setctime==1.1.0
     # via loguru
 yarl==1.9.4
     # via aiohttp
-zipp==3.19.1
-    # via importlib-metadata
-    # via importlib-resources

scrapegraphai/nodes/generate_answer_csv_node.py

@@ -8,7 +8,7 @@
 
 # Imports from Langchain
 from langchain.prompts import PromptTemplate
-from langchain_core.output_parsers import JsonOutputParser, PydanticOutputParser
+from langchain_core.output_parsers import JsonOutputParser
 from langchain_core.runnables import RunnableParallel
 from tqdm import tqdm
 
@@ -96,7 +96,7 @@ def execute(self, state):
 
         # Initialize the output parser
         if self.node_config.get("schema", None) is not None:
-            output_parser = PydanticOutputParser(pydantic_object=self.node_config.get("schema", None))
+            output_parser = JsonOutputParser(pydantic_object=self.node_config["schema"])
         else:
             output_parser = JsonOutputParser()
 
@@ -150,9 +150,6 @@ def execute(self, state):
             single_chain = list(chains_dict.values())[0]
             answer = single_chain.invoke({"question": user_prompt})
 
-        if type(answer) == PydanticOutputParser:
-            answer = answer.model_dump()
-
         # Update the state with the generated answer
         state.update({self.output[0]: answer})
         return state

scrapegraphai/nodes/generate_answer_node.py

@@ -7,10 +7,11 @@
 
 # Imports from Langchain
 from langchain.prompts import PromptTemplate
-from langchain_core.output_parsers import JsonOutputParser, PydanticOutputParser
+from langchain_core.output_parsers import JsonOutputParser
 from langchain_core.runnables import RunnableParallel
 from tqdm import tqdm
 
+
 from ..utils.logging import get_logger
 from ..models import Ollama
 # Imports from the library
@@ -81,8 +82,8 @@ def execute(self, state: dict) -> dict:
         doc = input_data[1]
 
         # Initialize the output parser
-        if self.node_config.get("schema",None) is not None:
-            output_parser = PydanticOutputParser(pydantic_object=self.node_config.get("schema", None))
+        if self.node_config.get("schema", None) is not None:
+            output_parser = JsonOutputParser(pydantic_object=self.node_config["schema"])
         else:
             output_parser = JsonOutputParser()
 
@@ -129,9 +130,6 @@ def execute(self, state: dict) -> dict:
             single_chain = list(chains_dict.values())[0]
             answer = single_chain.invoke({"question": user_prompt})
 
-        if type(answer) == PydanticOutputParser:
-            answer = answer.model_dump()
-
         # Update the state with the generated answer
         state.update({self.output[0]: answer})
         return state

scrapegraphai/nodes/generate_answer_omni_node.py

@@ -7,7 +7,7 @@
 
 # Imports from Langchain
 from langchain.prompts import PromptTemplate
-from langchain_core.output_parsers import JsonOutputParser, PydanticOutputParser
+from langchain_core.output_parsers import JsonOutputParser
 from langchain_core.runnables import RunnableParallel
 from tqdm import tqdm
 from ..models import Ollama
@@ -82,7 +82,7 @@ def execute(self, state: dict) -> dict:
 
         # Initialize the output parser
         if self.node_config.get("schema", None) is not None:
-            output_parser = PydanticOutputParser(pydantic_object=self.node_config.get("schema", None))
+            output_parser = JsonOutputParser(pydantic_object=self.node_config["schema"])
         else:
             output_parser = JsonOutputParser()
 
@@ -141,9 +141,6 @@ def execute(self, state: dict) -> dict:
             single_chain = list(chains_dict.values())[0]
             answer = single_chain.invoke({"question": user_prompt})
 
-        if type(answer) == PydanticOutputParser:
-            answer = answer.model_dump()
-
         # Update the state with the generated answer
         state.update({self.output[0]: answer})
         return state

scrapegraphai/nodes/generate_answer_pdf_node.py

@@ -7,7 +7,7 @@
 
 # Imports from Langchain
 from langchain.prompts import PromptTemplate
-from langchain_core.output_parsers import JsonOutputParser, PydanticOutputParser
+from langchain_core.output_parsers import JsonOutputParser
 from langchain_core.runnables import RunnableParallel
 from tqdm import tqdm
 from ..models import Ollama
@@ -96,8 +96,8 @@ def execute(self, state):
         doc = input_data[1]
 
         # Initialize the output parser
-        if self.node_config.get("schema",None) is not None:
-            output_parser = PydanticOutputParser(pydantic_object=self.node_config.get("schema", None))
+        if self.node_config.get("schema", None) is not None:
+            output_parser = JsonOutputParser(pydantic_object=self.node_config["schema"])
         else:
             output_parser = JsonOutputParser()
 

scrapegraphai/nodes/merge_answers_node.py

@@ -8,7 +8,7 @@
 
 # Imports from Langchain
 from langchain.prompts import PromptTemplate
-from langchain_core.output_parsers import JsonOutputParser, PydanticOutputParser
+from langchain_core.output_parsers import JsonOutputParser
 from tqdm import tqdm
 
 from ..utils.logging import get_logger
@@ -80,10 +80,8 @@ def execute(self, state: dict) -> dict:
             answers_str += f"CONTENT WEBSITE {i+1}: {answer}\n"
 
         # Initialize the output parser
-        if self.node_config["schema"] is not None:
-            output_parser = PydanticOutputParser(
-                pydantic_object=self.node_config["schema"]
-            )
+        if self.node_config.get("schema", None) is not None:
+            output_parser = JsonOutputParser(pydantic_object=self.node_config["schema"])
         else:
             output_parser = JsonOutputParser()
 
@@ -111,9 +109,6 @@ def execute(self, state: dict) -> dict:
         merge_chain = prompt_template | self.llm_model | output_parser
         answer = merge_chain.invoke({"user_prompt": user_prompt})
 
-        if type(answer) == PydanticOutputParser:
-            answer = answer.model_dump()
-
         # Update the state with the generated answer
         state.update({self.output[0]: answer})
         return state