Reducing the costs of the integration of models during the scaling of artificial intelligence: offers the open ecosystem for Langchain where closed sellers cannot

LinjshenOne of the leaders in the context of artificial intelligence and the area of ​​synchronization intends to remain committed to the open source ecosystems, especially because it enhances its bone position.

Harrison Chase, co -founder and CEO of Langchain, told Venturebeat that the success of its various platforms could be attributed to developers who demand the selection of the model and not to stay in a closed provider.

“The strength of the Langchain framework is in its integration and the ecosystem,” said Chis. “The size of the ecosystem is enormous, and many of this became possible through the framework being open source.”

Chis said that Langishen’s downloads reached 72.3 million last month, compared to competitors such as Openai‘s SDK agents. He added that Langchain Python and JS “have 4,500 contributors, and this is more contributors than Spark.”

Langchain, founded in 2022, has grown beyond his initial frameworkWhich helped developers to build artificial intelligence applications. In February last year, she issued the test and evaluation platform LangsmithA second frame called Langgraph Langgraph platform to help spread independent factors.

Langchain has been open source and salt for sellers and models throughout its growth. For example, it is partner with multiple companiesHe loves Google and Cisco, around The interfering operating factor. When the institutions began to experience artificial intelligence agents, Chis said that Langishen saw an opportunity to provide the publication options that were considered Developer options.

“Over the year and a half of the past year or so, more and more institutions and companies look forward to entering production. So we set all our offers, not only Langchain open source, but all our offers are combined as a company to meet this request and make it as easy as possible to build agent applications,” he said.

Langgraph Platform extends open source offers

One The new open source Langchain platforms are the Langgraph platform, which has become Available in general this week. The Langgraph platform allows developers to manage and start publishing Long -term or state factors. These agents rely on what Cis call “the surrounding agents”, or agents who work in the background and are operated by some events.

“We have tried to focus a lot on some of the most difficult infrastructure problems that surround these agents,” said Chis. “Langgraph is useful for long -term state agents, so if you are publishing a simple application, you do not want to use the Langgraph platform.”

He added that the company wants to bet on the surrounding or long -term agents, as you find this more independent agent and independent judgment a more interesting challenge in infrastructure.

Through the Langgraph platform, institutions can publish agents with one click publishing, horizontal expansion to deal with “traffic and long -term”, which is a stability layer to support the agent memory and the ends of the applications programming interface for customization and original access to the Langgraph Studio to choose any customers.

You may find the same organizations to bring more and more agents online. Langgraph Platform includes an administrative control unit that places all agents currently published and allows users to find agents, reuse joint agents and create multiple agents. “

“One of the big benefits of Langgraph is that it gives the agent’s creator full control of cognitive engineering. If there is a LLM (Great Language Model) procedure to do properly, then a good tool that you must impose quality is to create an evaluation within the episode directly in your Langgraph application.”

Cass added that with Langgraph, developers can reach a “good format frame” to build agents and bring these reliable factors to the Langgraph platform for publication.

During the best test, Chis said that more than 370 teams used the Langgraph platform. Langchain offers Three levels To use the Langgraph platform, with prices that depend on how to plan developers to host the service.

The broader Langchain system is open source

For Chase, one of Langchain’s strengths is its ability to create an ecosystem to completely develop the app.

Langsmith, the company’s test platform and monitoring, works with Langgraph and Langgraph Platform to track the agent’s standards. Since many agents who are designed and operated using Langgraph Platform in the long run, companies need to check if they continue to perform according to the specifications constantly.

Chase boasts that Langgraph is “the framework of the most adopted agent on a large scale” and claimed that it was downloaded More than automatic from Microsoft and Caraway The agent platformOnce again, citing the open source of its success.

“Langgraph is often chosen by the teams that need to build two or very dazzling customers (LinkedIn, Uber and Gitlab)-the reason is that you will not expand in Langgraph because it is low-level, which can be controlled significantly, which is required in order to get more adopted, which needs to be needed for reliable. For power,” he said.

Daily visions about business use cases with VB daily

If you want to persuade your boss at work, you have covered VB Daily. We give you the internal journalistic precedence over what companies do with obstetric artificial intelligence, from organizational transformations to practical publishing operations, so that you can share visions of the maximum return on investment.

Read with us privacy policy

Thanks for subscribing. Check more VB news bulletins here.

An error occurred.