Merge pull request #238 from VinciGit00/gpt4-omni

Author: VinciGit00

docs/assets/omniscrapergraph.png

@@ -10,6 +10,8 @@ Some interesting ones are:
 - `headless`: If set to `False`, the web browser will be opened on the URL requested and close right after the HTML is fetched.
 - `max_results`: The maximum number of results to be fetched from the search engine. Useful in `SearchGraph`.
 - `output_path`: The path where the output files will be saved. Useful in `SpeechGraph`.
+- `loader_kwargs`: A dictionary with additional parameters to be passed to the `Loader` class, such as `proxy`.
+- `max_images`: The maximum number of images to be analyzed. Useful in `OmniScraperGraph` and `OmniSearchGraph`.
 
 Proxy Rotation
 ^^^^^^^^^^^^^^

docs/assets/omnisearchgraph.png

@@ -3,16 +3,80 @@ Graphs
 
 Graphs are scraping pipelines aimed at solving specific tasks. They are composed by nodes which can be configured individually to address different aspects of the task (fetching data, extracting information, etc.).
 
-There are currently three types of graphs available in the library:
+There are three types of graphs available in the library:
 
 - **SmartScraperGraph**: one-page scraper that requires a user-defined prompt and a URL (or local file) to extract information from using LLM.
 - **SearchGraph**: multi-page scraper that only requires a user-defined prompt to extract information from a search engine using LLM. It is built on top of SmartScraperGraph.
 - **SpeechGraph**: text-to-speech pipeline that generates an answer as well as a requested audio file. It is built on top of SmartScraperGraph and requires a user-defined prompt and a URL (or local file).
 
+With the introduction of `GPT-4o`, two new powerful graphs have been created:
+
+- **OmniScraperGraph**: similar to `SmartScraperGraph`, but with the ability to scrape images and describe them.
+- **OmniSearchGraph**: similar to `SearchGraph`, but with the ability to scrape images and describe them.
+
 .. note::
 
    They all use a graph configuration to set up LLM models and other parameters. To find out more about the configurations, check the :ref:`LLM` and :ref:`Configuration` sections.
 
+OmniScraperGraph
+^^^^^^^^^^^^^^^^
+
+.. image:: ../../assets/omniscrapergraph.png
+   :align: center
+   :width: 90%
+   :alt: OmniScraperGraph
+|
+
+First we define the graph configuration, which includes the LLM model and other parameters. Then we create an instance of the OmniScraperGraph class, passing the prompt, source, and configuration as arguments. Finally, we run the graph and print the result.
+It will fetch the data from the source and extract the information based on the prompt in JSON format.
+
+.. code-block:: python
+
+   from scrapegraphai.graphs import OmniScraperGraph
+
+   graph_config = {
+      "llm": {...},
+   }
+
+   omni_scraper_graph = OmniScraperGraph(
+      prompt="List me all the projects with their titles and image links and descriptions.",
+      source="https://perinim.github.io/projects",
+      config=graph_config
+   )
+
+   result = omni_scraper_graph.run()
+   print(result)
+
+OmniSearchGraph
+^^^^^^^^^^^^^^^
+
+.. image:: ../../assets/omnisearchgraph.png
+   :align: center
+   :width: 80%
+   :alt: OmniSearchGraph
+|
+
+Similar to OmniScraperGraph, we define the graph configuration, create multiple of the OmniSearchGraph class, and run the graph.
+It will create a search query, fetch the first n results from the search engine, run n OmniScraperGraph instances, and return the results in JSON format.
+
+.. code-block:: python
+
+   from scrapegraphai.graphs import OmniSearchGraph
+
+   graph_config = {
+      "llm": {...},
+   }
+
+   # Create the OmniSearchGraph instance
+   omni_search_graph = OmniSearchGraph(
+      prompt="List me all Chioggia's famous dishes and describe their pictures.",
+      config=graph_config
+   )
+
+   # Run the graph
+   result = omni_search_graph.run()
+   print(result)
+
 SmartScraperGraph
 ^^^^^^^^^^^^^^^^^
 

docs/source/scrapers/graph_config.rst

@@ -0,0 +1,48 @@
+""" 
+Basic example of scraping pipeline using OmniScraper
+"""
+
+import os, json
+from dotenv import load_dotenv
+from scrapegraphai.graphs import OmniScraperGraph
+from scrapegraphai.utils import prettify_exec_info
+
+load_dotenv()
+
+
+# ************************************************
+# Define the configuration for the graph
+# ************************************************
+
+openai_key = os.getenv("OPENAI_APIKEY")
+
+graph_config = {
+    "llm": {
+        "api_key": openai_key,
+        "model": "gpt-4-turbo",
+    },
+    "verbose": True,
+    "headless": True,
+    "max_images": 5
+}
+
+# ************************************************
+# Create the OmniScraperGraph instance and run it
+# ************************************************
+
+omni_scraper_graph = OmniScraperGraph(
+    prompt="List me all the projects with their titles and image links and descriptions.",
+    # also accepts a string with the already downloaded HTML code
+    source="https://perinim.github.io/projects/",
+    config=graph_config
+)
+
+result = omni_scraper_graph.run()
+print(json.dumps(result, indent=2))
+
+# ************************************************
+# Get graph execution info
+# ************************************************
+
+graph_exec_info = omni_scraper_graph.get_execution_info()
+print(prettify_exec_info(graph_exec_info))

docs/source/scrapers/graphs.rst

@@ -0,0 +1,45 @@
+"""
+Example of OmniSearchGraph
+"""
+
+import os, json
+from dotenv import load_dotenv
+from scrapegraphai.graphs import OmniSearchGraph
+from scrapegraphai.utils import prettify_exec_info
+load_dotenv()
+
+# ************************************************
+# Define the configuration for the graph
+# ************************************************
+
+openai_key = os.getenv("OPENAI_APIKEY")
+
+graph_config = {
+    "llm": {
+        "api_key": openai_key,
+        "model": "gpt-4o",
+    },
+    "max_results": 2,
+    "max_images": 5,
+    "verbose": True,
+}
+
+# ************************************************
+# Create the OmniSearchGraph instance and run it
+# ************************************************
+
+omni_search_graph = OmniSearchGraph(
+    prompt="List me all Chioggia's famous dishes and describe their pictures.",
+    config=graph_config
+)
+
+result = omni_search_graph.run()
+print(json.dumps(result, indent=2))
+
+# ************************************************
+# Get graph execution info
+# ************************************************
+
+graph_exec_info = omni_search_graph.get_execution_info()
+print(prettify_exec_info(graph_exec_info))
+

examples/openai/omni_scraper_openai.py

@@ -19,7 +19,7 @@
 graph_config = {
     "llm": {
         "api_key": openai_key,
-        "model": "gpt-3.5-turbo",
+        "model": "gpt-4o",
     },
     "verbose": True,
     "headless": False,
@@ -30,7 +30,7 @@
 # ************************************************
 
 smart_scraper_graph = SmartScraperGraph(
-    prompt="List me all the projects with their description.",
+    prompt="List me all the projects with their description",
     # also accepts a string with the already downloaded HTML code
     source="https://perinim.github.io/projects/",
     config=graph_config

examples/openai/omni_search_graph_openai.py

@@ -0,0 +1,54 @@
+"""
+Example of ImageToTextNode
+"""
+
+import os
+from dotenv import load_dotenv
+from scrapegraphai.nodes import ImageToTextNode
+from scrapegraphai.models import OpenAIImageToText
+
+load_dotenv()
+
+# ************************************************
+# Define the configuration for the graph
+# ************************************************
+
+openai_key = os.getenv("OPENAI_APIKEY")
+
+graph_config = {
+    "llm": {
+        "api_key": openai_key,
+        "model": "gpt-4o",
+        "temperature": 0,
+    },
+}
+
+# ************************************************
+# Define the node
+# ************************************************
+
+llm_model = OpenAIImageToText(graph_config["llm"])
+
+image_to_text_node = ImageToTextNode(
+    input="img_url",
+    output=["img_desc"],
+    node_config={
+        "llm_model": llm_model,
+        "headless": False
+    }
+)
+
+# ************************************************
+# Test the node
+# ************************************************
+
+state = {
+    "img_url": [
+        "https://perinim.github.io/assets/img/rotary_pybullet.jpg",
+        "https://perinim.github.io/assets/img/value-policy-heatmaps.jpg",
+    ],
+}
+
+result = image_to_text_node.execute(state)
+
+print(result)

examples/openai/smart_scraper_openai.py

@@ -13,3 +13,5 @@
 from .json_scraper_graph import JSONScraperGraph
 from .csv_scraper_graph import CSVScraperGraph
 from .pdf_scraper_graph import PDFScraperGraph
+from .omni_scraper_graph import OmniScraperGraph
+from .omni_search_graph import OmniSearchGraph

examples/single_node/image2text_node.py

@@ -30,8 +30,8 @@ def _create_graph(self):
         Creates the graph of nodes representing the workflow for web scraping.
         """
         fetch_node = FetchNode(
-            input="csv",
-            output=["doc"],
+            input="csv | csv_dir",
+            output=["doc", "link_urls", "img_urls"],
         )
         parse_node = ParseNode(
             input="doc",