Scrapegraph-ai
Scrapegraph-ai copied to clipboard
Python scraper based on AI
Bedrock support is not working due to * missing class (`BedrockEmbeddings`) / `main` branch only * conflict with the Anthropic branch in `_create_llm` when using Claude models
Hi, I use proxy custom URL request using base OpenAI, but ```baseURL``` not working This is my code: ``` graph_config = { "llm": { "api_key": "YOUR_API_KEY", "model": "gpt-3.5-turbo", "temperature": 0,...
I've been working on developing a web scraper model using LLMs (ScrapeGraph-AI) in AzureChatOpenAI - langchain_openai. It's been tested with various webpage URLs and performs admirably. However, there's an issue...
**Describe the bug** When I tried to repreduce the azure openai example using my credentials I faced a bug at the search graph step. **To Reproduce** Steps to reproduce the...
Pre/beta
Adds support to look for answers by following links in input url repeatedly upto n-level deep. Although this works, its far far away from perfect. The biggest issue is the...
**Is your feature request related to a problem? Please describe.** I was playing with Scrapegraph, and I wanted to define my structured output using `tools` both in the `SmartScraperGraph()` function...
Most times when I use a groq model, this is the output I get: ``` ... File "/Users/matthewberman/miniconda3/envs/scrape/lib/python3.10/site-packages/langchain_core/runnables/base.py", line 1626, in _call_with_config context.run( File "/Users/matthewberman/miniconda3/envs/scrape/lib/python3.10/site-packages/langchain_core/runnables/config.py", line 347, in call_func_with_variable_args return...