1.0https://vulab.comadminhttps://vulab.com/index.php/author/vulab_admin/Fine tuning LLM with Langchain -rich600338<blockquote class="wp-embedded-content" data-secret="5MD2RM8QnC"><a href="https://vulab.com/index.php/2023/05/02/fine-tuning-llm-with-langchain/">Fine tuning LLM with Langchain</a></blockquote><iframe sandbox="allow-scripts" security="restricted" src="https://vulab.com/index.php/2023/05/02/fine-tuning-llm-with-langchain/embed/#?secret=5MD2RM8QnC" width="600" height="338" title="“Fine tuning LLM with Langchain” — " data-secret="5MD2RM8QnC" frameborder="0" marginwidth="0" marginheight="0" scrolling="no" class="wp-embedded-content"></iframe><script>
/*! This file is auto-generated */
!function(d,l){"use strict";l.querySelector&&d.addEventListener&&"undefined"!=typeof URL&&(d.wp=d.wp||{},d.wp.receiveEmbedMessage||(d.wp.receiveEmbedMessage=function(e){var t=e.data;if((t||t.secret||t.message||t.value)&&!/[^a-zA-Z0-9]/.test(t.secret)){for(var s,r,n,a=l.querySelectorAll('iframe[data-secret="'+t.secret+'"]'),o=l.querySelectorAll('blockquote[data-secret="'+t.secret+'"]'),c=new RegExp("^https?:$","i"),i=0;i<o.length;i++)o[i].style.display="none";for(i=0;i<a.length;i++)s=a[i],e.source===s.contentWindow&&(s.removeAttribute("style"),"height"===t.message?(1e3<(r=parseInt(t.value,10))?r=1e3:~~r<200&&(r=200),s.height=r):"link"===t.message&&(r=new URL(s.getAttribute("src")),n=new URL(t.value),c.test(n.protocol))&&n.host===r.host&&l.activeElement===s&&(d.top.location.href=t.value))}},d.addEventListener("message",d.wp.receiveEmbedMessage,!1),l.addEventListener("DOMContentLoaded",function(){for(var e,t,s=l.querySelectorAll("iframe.wp-embedded-content"),r=0;r<s.length;r++)(t=(e=s[r]).getAttribute("data-secret"))||(t=Math.random().toString(36).substring(2,12),e.src+="#?secret="+t,e.setAttribute("data-secret",t)),e.contentWindow.postMessage({message:"ready",secret:t},"*")},!1)))}(window,document);
//# sourceURL=https://vulab.com/wp-includes/js/wp-embed.min.js
</script>
import osfrom pprint import pprintfrom langchain.embeddings.openai import OpenAIEmbeddingsfrom langchain.vectorstores import Chromafrom langchain.text_splitter import TokenTextSplitterfrom langchain.llms import OpenAIfrom langchain.chains import ChatVectorDBChainfrom langchain.document_loaders import UnstructuredURLLoader os.environ[“OPENAI_API_KEY”] = ‘your_open_api_key’ h2o_ai_wave_urls = [“https://github.com/h2oai/wave/releases”,“https://wave.h2o.ai/docs/installation”,“https://wave.h2o.ai/docs/getting-started”,“https://wave.h2o.ai/docs/examples”,“https://github.com/h2oai/wave/issues/693”,“https://github.com/h2oai/wave/blob/master/.github/CONTRIBUTING.md#development-setup”,“https://github.com/h2oai/wave/discussions/1897”,“https://github.com/h2oai/wave/discussions/1888”,“https://github.com/h2oai/wave/discussions/1885”,“https://github.com/h2oai/wave/discussions/1865”] collection_name = “h2o_wave_knowledgebase”local_directory = “kb-h2o-wave”persist_directory = os.path.join(os.getcwd(), local_directory) loader = UnstructuredURLLoader(urls=h2o_ai_wave_urls)kb_data = loader.load() text_splitter = TokenTextSplitter(chunk_size=1000, chunk_overlap=0)kb_doc = text_splitter.split_documents(kb_data) embeddings = OpenAIEmbeddings() kb_db = Chroma.from_documents(kb_doc,embeddings,collection_name=collection_name,persist_directory=persist_directory)kb_db.persist() kb_qa … Read More »