add new model for gpt

examples/openai/smart_scraper_schema_openai.py

@@ -5,7 +5,7 @@ Basic example of scraping pipeline using SmartScraper with schema
 import os, json
 from typing import List
 from dotenv import load_dotenv
-from pydantic import BaseModel, Field
+from langchain_core.pydantic_v1 import BaseModel, Field
 from scrapegraphai.graphs import SmartScraperGraph
 
 load_dotenv()
@@ -30,7 +30,7 @@ openai_key = os.getenv("OPENAI_APIKEY")
 graph_config = {
     "llm": {
         "api_key":openai_key,
-        "model": "chatgpt-4o-latest",
+        "model": "gpt-4o-mini",
     },
     "verbose": True,
     "headless": False,

pyproject.toml

@@ -14,12 +14,12 @@ authors = [
 ]
 
 dependencies = [
-    "langchain>=0.2.10",
+    "langchain==0.2.14",
     "langchain-fireworks>=0.1.3",
     "langchain_community>=0.2.9",
     "langchain-google-genai>=1.0.7",
     "langchain-google-vertexai>=1.0.7",
-    "langchain-openai>=0.1.17",
+    "langchain-openai==0.1.22",
     "langchain-groq>=0.1.3",
     "langchain-aws>=0.1.3",
     "langchain-anthropic>=0.1.11",

requirements-dev.lock

@@ -179,7 +179,6 @@ graphviz==0.20.3
     # via scrapegraphai
 greenlet==3.0.3
     # via playwright
-    # via sqlalchemy
 groq==0.9.0
     # via langchain-groq
 grpc-google-iam-v1==0.13.1
@@ -255,7 +254,7 @@ jsonschema-specifications==2023.12.1
     # via jsonschema
 kiwisolver==1.4.5
     # via matplotlib
-langchain==0.2.12
+langchain==0.2.14
     # via langchain-community
     # via scrapegraphai
 langchain-anthropic==0.1.22
@@ -264,7 +263,7 @@ langchain-aws==0.1.16
     # via scrapegraphai
 langchain-community==0.2.11
     # via scrapegraphai
-langchain-core==0.2.29
+langchain-core==0.2.33
     # via langchain
     # via langchain-anthropic
     # via langchain-aws
@@ -292,7 +291,7 @@ langchain-mistralai==0.1.12
     # via scrapegraphai
 langchain-nvidia-ai-endpoints==0.2.1
     # via scrapegraphai
-langchain-openai==0.1.21
+langchain-openai==0.1.22
     # via scrapegraphai
 langchain-text-splitters==0.2.2
     # via langchain

requirements.lock

@@ -133,7 +133,6 @@ graphviz==0.20.3
     # via scrapegraphai
 greenlet==3.0.3
     # via playwright
-    # via sqlalchemy
 groq==0.9.0
     # via langchain-groq
 grpc-google-iam-v1==0.13.1
@@ -178,6 +177,7 @@ jinja2==3.1.4
     # via torch
 jiter==0.5.0
     # via anthropic
+    # via openai
 jmespath==1.0.1
     # via boto3
     # via botocore
@@ -187,7 +187,7 @@ jsonpatch==1.33
     # via langchain-core
 jsonpointer==3.0.0
     # via jsonpatch
-langchain==0.2.11
+langchain==0.2.14
     # via langchain-community
     # via scrapegraphai
 langchain-anthropic==0.1.20
@@ -196,7 +196,7 @@ langchain-aws==0.1.12
     # via scrapegraphai
 langchain-community==0.2.10
     # via scrapegraphai
-langchain-core==0.2.28
+langchain-core==0.2.33
     # via langchain
     # via langchain-anthropic
     # via langchain-aws
@@ -224,7 +224,7 @@ langchain-mistralai==0.1.12
     # via scrapegraphai
 langchain-nvidia-ai-endpoints==0.1.7
     # via scrapegraphai
-langchain-openai==0.1.17
+langchain-openai==0.1.22
     # via scrapegraphai
 langchain-text-splitters==0.2.2
     # via langchain
@@ -264,7 +264,7 @@ numpy==1.26.4
     # via sentence-transformers
     # via shapely
     # via transformers
-openai==1.37.0
+openai==1.41.0
     # via langchain-fireworks
     # via langchain-openai
 orjson==3.10.6

scrapegraphai/nodes/generate_answer_node.py

@@ -88,8 +88,10 @@ class GenerateAnswerNode(BaseNode):
         # Initialize the output parser
         if self.node_config.get("schema", None) is not None:
             output_parser = JsonOutputParser(pydantic_object=self.node_config["schema"])
-            if isinstance(self.llm_model, ChatOpenAI):
-                self.llm_model = self.llm_model.with_structured_output(self.node_config["schema"], method="json_mode")
+            if isinstance(self.llm_model, ChatOpenAI) and (self.llm_model.model_name=="gpt-4o-mini" or self.llm_model.model_name=="gpt-4o-2024-08-06"):
+                self.llm_model = self.llm_model.with_structured_output(
+                    schema = self.node_config["schema"],
+                    method="json_schema")
 
         else:
             output_parser = JsonOutputParser()