open_deep_research
open_deep_research copied to clipboard
langchain-ai
Hey there! This PR adds web search using the Linkup API. It also removes the `TavilyClient` which wasn't used anywhere and moved the `AsyncTavilyClient` instantiation within the `tavily_search_async` method to...
From YouTube video comments: ``` I think the next step for these agents is to give them more functionalities and tools. For example: - download a pdf, read it, find...
Include granular in-line sourcing like OpenAI and Gemini. Requires prompt engineering of the [section writer](https://github.com/langchain-ai/open_deep_research/blob/c4349b29da48d3551e14700b84a7620c4092e9dd/src/open_deep_research/prompts.py#L97).
`Error code: 429 - {'type': 'error', 'error': {'type': 'rate_limit_error', 'message': 'This request would exceed the rate limit for your organization (#########) of 40,000 input tokens per minute. For details, refer...
Provide using Thinking (sonnet-3.7) / Reasoning Level (o3-mini) configuration for Planner / Writer model
Make it possible to fetch X number of results from multiple search providers e.g. 2 from 5 providers instead of 10 from one provider. 2 from perplixity 2 from pubmed...
It would be more versatile and better if we could set chat_model as configurable so that we could freely change chat_model-specific parameters (such as extended shinking in Claude 3.7 Sonnet...
#40 I made changes to add support for custom chat models in the configuration. However, I was unable to get it to work as expected with the OpenAI o1-mini model...