Merge pull request #686 from ScrapeGraphAI/main

allginement

Author: VinciGit00

CHANGELOG.md

@@ -1,3 +1,10 @@
+## [1.21.1](https://github.com/ScrapeGraphAI/Scrapegraph-ai/compare/v1.21.0...v1.21.1) (2024-09-21)
+
+
+### Bug Fixes
+
+* removed faiss ([86f6877](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/86f68770e920d800fb14d14ee34bf0d1a9cefd51))
+
 ## [1.21.0](https://github.com/ScrapeGraphAI/Scrapegraph-ai/compare/v1.20.1...v1.21.0) (2024-09-19)
 
 

README.md

@@ -42,7 +42,7 @@ Additional dependecies can be added while installing the library:
 This group allows you to use additional language models like Fireworks, Groq, Anthropic, Together AI, Hugging Face, and Nvidia AI Endpoints.
 ```bash
 pip install scrapegraphai[other-language-models]
-
+  ```
 - <b>Semantic Options</b>: this group includes tools for advanced semantic processing, such as Graphviz.
 
   ```bash
@@ -55,6 +55,12 @@ pip install scrapegraphai[other-language-models]
   pip install scrapegraphai[more-browser-options]
   ```
 
+- <b>faiss Options</b>: this group includes faiss integration
+
+  ```bash
+  pip install scrapegraphai[faiss-cpu]
+  ```
+
 </details>
 
 

examples/openai/script_generator_openai.py

@@ -20,6 +20,7 @@
         "api_key": os.getenv("OPENAI_API_KEY"),
         "model": "openai/gpt-4o",
     },
+    "library": "beautifulsoup",
     "verbose": True,
     "headless": False,
 }

examples/openai/script_generator_schema_openai.py

@@ -32,7 +32,7 @@ class Projects(BaseModel):
 graph_config = {
     "llm": {
         "api_key": openai_key,
-        "model": "openai/gpt-3.5-turbo",
+        "model": "openai/gpt-4o"
     },
     "library": "beautifulsoup",
     "verbose": True,

examples/openai/search_graph_schema_openai.py

@@ -31,7 +31,7 @@ class Dishes(BaseModel):
 graph_config = {
     "llm": {
         "api_key": openai_key,
-        "model": "openai/gpt-3.5-turbo",
+        "model": "openai/gpt-4o"
     },
     "max_results": 2,
     "verbose": True,

pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 name = "scrapegraphai"
 
-version = "1.21.0"
+version = "1.21.1"
 
 description = "A web scraping library based on LangChain which uses LLM and direct graph logic to create scraping pipelines."
 authors = [
@@ -19,7 +19,6 @@ dependencies = [
     "langchain-aws>=0.1.3",
     "mistral-common>=1.4.0",
     "html2text>=2024.2.26",
-    "faiss-cpu>=1.8.0",
     "beautifulsoup4>=4.12.3",
     "pandas>=2.2.2",
     "python-dotenv>=1.0.1",
@@ -100,6 +99,11 @@ screenshot_scraper = [
     "pillow>=10.4.0",
 ]
 
+# Group 5: Faiss CPU
+faiss-cpu = [
+    "faiss-cpu>=1.8.0",
+]
+
 [build-system]
 requires = ["hatchling"]
 build-backend = "hatchling.build"

requirements-dev.lock

@@ -80,8 +80,6 @@ docutils==0.19
 exceptiongroup==1.2.2
     # via anyio
     # via pytest
-faiss-cpu==1.8.0.post1
-    # via scrapegraphai
 fastapi==0.112.0
     # via burr
 fastapi-pagination==0.12.26
@@ -251,7 +249,6 @@ narwhals==1.3.0
     # via altair
 numpy==1.26.4
     # via contourpy
-    # via faiss-cpu
     # via langchain
     # via langchain-aws
     # via langchain-community
@@ -274,7 +271,6 @@ orjson==3.10.7
     # via langsmith
 packaging==24.1
     # via altair
-    # via faiss-cpu
     # via huggingface-hub
     # via langchain-core
     # via marshmallow

requirements.lock

@@ -49,8 +49,6 @@ distro==1.9.0
     # via openai
 exceptiongroup==1.2.2
     # via anyio
-faiss-cpu==1.8.0.post1
-    # via scrapegraphai
 filelock==3.15.4
     # via huggingface-hub
     # via transformers
@@ -176,7 +174,6 @@ multiprocess==0.70.16
 mypy-extensions==1.0.0
     # via typing-inspect
 numpy==1.26.4
-    # via faiss-cpu
     # via langchain
     # via langchain-aws
     # via langchain-community
@@ -192,7 +189,6 @@ opencv-python-headless==4.10.0.84
 orjson==3.10.6
     # via langsmith
 packaging==24.1
-    # via faiss-cpu
     # via huggingface-hub
     # via langchain-core
     # via marshmallow

scrapegraphai/nodes/generate_answer_node.py

@@ -91,7 +91,7 @@ def execute(self, state: dict) -> dict:
 
             if isinstance(self.llm_model, (ChatOpenAI, ChatMistralAI)):
                 self.llm_model = self.llm_model.with_structured_output(
-                    schema = self.node_config["schema"])                
+                    schema = self.node_config["schema"])          
                 output_parser = get_structured_output_parser(self.node_config["schema"])
                 format_instructions = "NA"
             else: