![]() ![]() You can also install 1.9.1 from source with python setup.py install (see Compilation page). There are some pre release binaries for 64bit windows, and for python 2.7 at Unix Distributionsġ.9.1 has been packaged up for almost all major distributions. windows 64bit users note: use the 32bit python with this 32bit pygame.(optional) Numeric for windows python2.5 (note: Numeric is old, best to use numpy).We changed the type of installer, and there will be issues if you don't uninstall pygame 1.7.1 first (and all old versions). Either using the uninstall feature - or remove the files: c:\python25\lib\site-packages\pygame. NOTE: if you had pygame 1.7.1 installed already, please uninstall it first. You may need to uninstall old versions of pygame first. Get the version of pygame for your version of python. pygame-1.9.1release.zip ~ 1.5M - source/docs/examples in windows format.pygame-1.9. ~ 1.4M - source/docs/examples in unix format. ![]() Wheel packages are also available on PyPI, and may be installed by running pip install wheel 1.9.1 Packages (August 6th 2009) Source Wheel packages are also available on PyPI, and may be installed by running pip install wheel 1.9.3 Packages (January 16th 2017) Source This is a source only release, because the source pygame-1.9.4.tar.gz release contained build artifacts. □ ContributingĪs an open-source project in a rapidly developing field, we are extremely open to contributions, whether it be in the form of a new feature, improved infrastructure, or better documentation.įor detailed information on how to contribute, see the Contributing Guide.Not sure what to download? Read the Installation Notes. LangChain provides some prompts/chains for assisting in this.įor more information on these concepts, please see our full documentation. One new way of evaluating them is using language models themselves to do the evaluation. Generative models are notoriously hard to evaluate with traditional metrics. ![]() LangChain provides a standard interface for memory, a collection of memory implementations, and examples of chains/agents that use memory. Memory refers to persisting state between calls of a chain/agent. LangChain provides a standard interface for agents, a selection of agents to choose from, and examples of end-to-end agents. Examples include summarization of long pieces of text and question/answering over specific data sources.Īgents involve an LLM making decisions about which Actions to take, taking that Action, seeing an Observation, and repeating that until done. LangChain provides a standard interface for chains, lots of integrations with other tools, and end-to-end chains for common applications.ĭata Augmented Generation involves specific types of chains that first interact with an external data source to fetch data for use in the generation step. This includes prompt management, prompt optimization, a generic interface for all LLMs, and common utilities for working with LLMs.Ĭhains go beyond a single LLM call and involve sequences of calls (whether to an LLM or a different utility). ![]() These are, in increasing order of complexity: There are six main areas that LangChain is designed to help with.
0 Comments
Leave a Reply.AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |