From 41516f0e1d04e552ef4da869cb5b452169be4c49 Mon Sep 17 00:00:00 2001 From: amaan-ai20 Date: Mon, 27 Jan 2025 15:25:47 +0530 Subject: [PATCH] docs: add dappier tool docs --- docs/mint.json | 2 + docs/tools/dappierairecommendationstool.mdx | 108 ++++++++++++++++++++ docs/tools/dappierrealtimesearchtool.mdx | 85 +++++++++++++++ 3 files changed, 195 insertions(+) create mode 100644 docs/tools/dappierairecommendationstool.mdx create mode 100644 docs/tools/dappierrealtimesearchtool.mdx diff --git a/docs/mint.json b/docs/mint.json index 585fc0abd..db56f1aae 100644 --- a/docs/mint.json +++ b/docs/mint.json @@ -120,6 +120,8 @@ "tools/composiotool", "tools/csvsearchtool", "tools/dalletool", + "tools/dappierrealtimesearchtool", + "tools/dappierairecommendationstool", "tools/directorysearchtool", "tools/directoryreadtool", "tools/docxsearchtool", diff --git a/docs/tools/dappierairecommendationstool.mdx b/docs/tools/dappierairecommendationstool.mdx new file mode 100644 index 000000000..6d736bbac --- /dev/null +++ b/docs/tools/dappierairecommendationstool.mdx @@ -0,0 +1,108 @@ +--- +title: Dappier AI Recommendations +description: The `DappierAIRecommendationsTool` fetches ai recommendations accross Sports and Lifestyle News to niche favorites like I Heart Dogs, I Heart Cats, WishTV and many more. +icon: message +--- + +## Description + +[Dappier](https://dappier.com) connects any LLM or your Agentic AI to real-time, rights-cleared, proprietary data from trusted sources, making your AI an expert in anything. Our specialized models include Real-Time Web Search, News, Sports, Financial Stock Market Data, Crypto Data, and exclusive content from premium publishers. Explore a wide range of data models in our marketplace at [marketplace.dappier.com](https://marketplace.dappier.com). + +## Key Features: + +- **AI-Powered Recommendations**: + Search for recommendations in a wide variety of topics, including Sports, Lifestyle News, and niche topics like I Heart Dogs and WishTV, powered by advanced AI models. + +- **Customizable Data Model**: + Use different data models to tailor recommendations to specific interests. The tool supports a wide range of pre-configured models, and the model ID can be customized for different types of recommendations. + +- **Flexible Search Algorithms**: + Choose between several search algorithms, including: + + - `most_recent`: Retrieve the latest articles. + - `semantic`: Retrieve articles based on semantic similarity to the query. + - `most_recent_semantic`: Combine both the most recent and semantic search methods. + - `trending`: Get trending articles based on user interest and activity. + +- **Top-K Document Retrieval**: + Control the number of results returned by setting the `similarity_top_k` parameter, ensuring that the most relevant content is retrieved based on similarity. + +- **Reference Site Customization**: + Optionally specify a reference domain (`ref`) where AI recommendations should be displayed. You can also control the number of articles returned from the reference site (`num_articles_ref`), while the remaining articles will come from other sources in the RAG model. + +- **Real-Time AI Recommendations**: + Leverage real-time AI-powered recommendations to stay up-to-date with the latest articles, news, and trends across your preferred categories. + +For more information about Dappier, please visit the [Dappier website](https://dappier.com) or if you want to check out the docs, you can visit the [Dappier docs](https://docs.dappier.com). + +## Installation + +- Head to [Dappier](https://platform.dappier.com/profile/api-keys) to sign up and generate an API key. Once you've done this set the `DAPPIER_API_KEY` environment variable or you can pass it to the `DappierAIRecommendationsTool` constructor. +- Install the `dappier` package. + +```bash +pip install dappier 'crewai[tools]' +``` + +## Example + +Utilize the DappierAIRecommendationsTool as follows to allow your agent to access ai recommendations across Sports, Lifestyle News, and niche favorites like I Heart Dogs, I Heart Cats, WishTV, and many more.: + +```python Code +from crewai_tools import DappierAIRecommendationsTool + +tool = DappierAIRecommendationsTool() + +response = tool.run( + query="latest sports news", + data_model_id="dm_01j0pb465keqmatq9k83dthx34", + similarity_top_k=3, + ref="sportsnaut.com", + num_articles_ref=2, + search_algorithm="most_recent", +) + +# [ +# { +# "author": "Matt Weaver", +# "image_url": "https://images.dappier.com/dm_01j0pb465keqmatq9k83dthx34/Screenshot_20250117_021643_Gallery_.jpg?width=428&height=321", +# "pubdate": "Fri, 17 Jan 2025 08:04:03 +0000", +# "source_url": "https://sportsnaut.com/chili-bowl-thursday-bell-column/", +# "summary": "Chili Bowl unpredictability highlights key moments and drivers' challenges...", +# "title": "Chili Bowl proves every lap counts..." +# }, +# { +# "author": "Matt Higgins", +# "image_url": "https://images.dappier.com/dm_01j0pb465keqmatq9k83dthx34/Pete-Alonso-24524027_.jpg?width=428&height=321", +# "pubdate": "Fri, 17 Jan 2025 02:48:42 +0000", +# "source_url": "https://sportsnaut.com/new-york-mets-news-pete-alonso-rejected-last-ditch-contract-offer/", +# "summary": "Alonso rejects Mets' offer, shifting focus to other teams and possible trade for Guerrero Jr....", +# "title": "Mets' last-ditch offer to Alonso rejected..." +# }, +# { +# "author": "Jim Cerny", +# "image_url": "https://images.dappier.com/dm_01j0pb465keqmatq9k83dthx34/NHL-New-York-Rangers-at-Utah-25204492_.jpg?width=428&height=321", +# "pubdate": "Fri, 17 Jan 2025 05:10:39 +0000", +# "source_url": "https://www.foreverblueshirts.com/new-york-rangers-news/stirring-5-3-comeback-win-utah-close-road-trip/", +# "summary": "Rangers rally for comeback win, pushing forward in playoff race...", +# "title": "Rangers score 3rd-period goals for comeback win..." +# } +# ] + +``` + +## Arguments + +`__init__` arguments: + +- `api_key`: Optional. Specifies the Dappier API key. If not provided, it will default to the `DAPPIER_API_KEY` environment variable. + - Can be passed directly during instantiation or set as an environment variable. + +`_run` arguments: + +- `query`: The user-provided input string for AI recommendations across various domains like Sports, Lifestyle News, and niche favorites. +- `data_model_id`: Optional. Specifies the data model ID to use for recommendations. Defaults to `"dm_01j0pb465keqmatq9k83dthx34"`. Multiple data models are available at [Dappier Marketplace](https://marketplace.dappier.com/marketplace). +- `similarity_top_k`: Optional. The number of top documents to retrieve based on similarity. Defaults to `9`. +- `ref`: Optional. Specifies the site domain where AI recommendations should be displayed. Defaults to `None`. +- `num_articles_ref`: Optional. Specifies the minimum number of articles to return from the specified reference domain (`ref`). Defaults to `0`. +- `search_algorithm`: Optional. Specifies the search algorithm to use for retrieving articles. Defaults to `"most_recent"`. Options include `"most_recent"`, `"semantic"`, `"most_recent_semantic"`, and `"trending"`. diff --git a/docs/tools/dappierrealtimesearchtool.mdx b/docs/tools/dappierrealtimesearchtool.mdx new file mode 100644 index 000000000..49438805a --- /dev/null +++ b/docs/tools/dappierrealtimesearchtool.mdx @@ -0,0 +1,85 @@ +--- +title: Dappier Real Time Search +description: The `DappierRealTimeSearchTool` is desinged to search real time data, including web search results, financial information, news, weather, and more, with AI-powered insights and updates. +icon: message +--- + +## Description + +[Dappier](https://dappier.com) connects any LLM or your Agentic AI to real-time, rights-cleared, proprietary data from trusted sources, making your AI an expert in anything. Our specialized models include Real-Time Web Search, News, Sports, Financial Stock Market Data, Crypto Data, and exclusive content from premium publishers. Explore a wide range of data models in our marketplace at [marketplace.dappier.com](https://marketplace.dappier.com). + +## Key Features: + +- **Real-Time Web Search Results**: + Fetch up-to-date search results from Google, including the latest news, weather updates, travel information, and deals. +- **Stock Market and Financial Data**: + Retrieve real-time financial news, stock prices, and trades powered by Polygon.io, along with AI-powered insights for better decision-making in the financial domain. +- **Comprehensive Data Access**: + Access a wide range of data from trusted, proprietary sources, including premium content from leading publishers across verticals like news, sports, finance, and weather. +- **LLM-Ready Retrieval-Augmented Generation (RAG) Models**: + Utilize pre-trained RAG models that ensure your AI-driven applications can return factual, relevant responses based on the most current data available. + +- **Flexible API Integration**: + Integrate seamlessly with Dappier’s real-time data APIs to enhance your AI models and applications with up-to-date content from various sectors. + +- **Scalable Data Queries**: + Tailor search queries to focus on specific data sources, enabling applications to respond to real-time demands in areas such as finance, sports, news, and weather. + +For more information about Dappier, please visit the [Dappier website](https://dappier.com) or if you want to check out the docs, you can visit the [Dappier docs](https://docs.dappier.com). + +## Installation + +- Head to [Dappier](https://platform.dappier.com/profile/api-keys) to sign up and generate an API key. Once you've done this set the `DAPPIER_API_KEY` environment variable or you can pass it to the `DappierRealTimeSearchTool` constructor. +- Install the `dappier` package. + +```bash +pip install dappier 'crewai[tools]' +``` + +## Example + +Utilize the DappierRealTimeSearchTool as follows to allow your agent to access real time data: + +```python Code +from crewai_tools import DappierRealTimeSearchTool + +tool = DappierRealTimeSearchTool() + +response = tool.run(query="crew ai latest news") + +# Using Tool: Dappier real time search tool + +# Here’s the latest on Crew AI: + +# - **Integration with NVIDIA**: Crew AI has teamed up with NVIDIA to +# enhance their production-grade AI agents, making workflows even smoother! +# This was announced on January 7, 2025. + +# - **Collaboration with Cloudera**: They’re also working with Cloudera +# to bring precision to enterprise workflows using AI agents. + +# - **New Features**: They just launched version 0.70.1, which includes +# a cool feature called `crewai chat` that allows real conversations +# with AI crews! + +# - **Funding Success**: Crew AI recently secured $18 million in Series A funding +# to boost their growth, and they now have over 10 million agents automating +# complex workflows across various platforms. + +# - **No-Code Assistant**: They’re promoting a no-code assistant that helps +# users build and deploy automated workflows easily. + +# Looks like Crew AI is on a roll! 🚀✨ +``` + +## Arguments + +`__init__` arguments: + +- `api_key`: Optional. Specifies the Dappier API key. If not provided, it will default to the `DAPPIER_API_KEY` environment variable. + - Can be passed directly during instantiation or set as an environment variable. + +`_run` arguments: + +- `query`: The user-provided input string for retrieving real-time data, including web search results, financial information, news, weather, and more, with AI-powered insights and updates. +- `ai_model_id`: Optional. Specifies the AI model ID to use for the query. Defaults to `"am_01j06ytn18ejftedz6dyhz2b15"`. Multiple AI models are available at [Dappier Marketplace](https://marketplace.dappier.com/marketplace).