{"id":123,"date":"2023-05-02T03:34:05","date_gmt":"2023-05-02T03:34:05","guid":{"rendered":"https:\/\/vulab.com\/?p=123"},"modified":"2023-05-02T03:34:05","modified_gmt":"2023-05-02T03:34:05","slug":"fine-tuning-llm-with-langchain","status":"publish","type":"post","link":"https:\/\/vulab.com\/index.php\/2023\/05\/02\/fine-tuning-llm-with-langchain\/","title":{"rendered":"Fine tuning LLM with Langchain"},"content":{"rendered":"\n
\n

import os
from pprint import pprint
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores import Chroma
from langchain.text_splitter import TokenTextSplitter
from langchain.llms import OpenAI
from langchain.chains import ChatVectorDBChain
from langchain.document_loaders import UnstructuredURLLoader<\/p>\n\n\n\n

os.environ[“OPENAI_API_KEY”] = ‘your_open_api_key’<\/p>\n\n\n\n

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”
]<\/p>\n\n\n\n

collection_name = “h2o_wave_knowledgebase”
local_directory = “kb-h2o-wave”
persist_directory = os.path.join(os.getcwd(), local_directory)<\/p>\n\n\n\n

loader = UnstructuredURLLoader(urls=h2o_ai_wave_urls)
kb_data = loader.load()<\/p>\n\n\n\n

text_splitter = TokenTextSplitter(chunk_size=1000, chunk_overlap=0)
kb_doc = text_splitter.split_documents(kb_data)<\/p>\n\n\n\n

embeddings = OpenAIEmbeddings()<\/p>\n\n\n\n

kb_db = Chroma.from_documents(kb_doc,
embeddings,
collection_name=collection_name,
persist_directory=persist_directory
)
kb_db.persist()<\/p>\n\n\n\n

kb_qa = ChatVectorDBChain.from_llm(
OpenAI(temperature=0, model_name=”gpt-3.5-turbo”),
vectorstore=kb_db,
top_k_docs_for_context=5,
return_source_documents=True
)<\/p>\n\n\n\n

chat_history = []
query_statement = “What is this document about?”<\/p>\n\n\n\n

—— One question ONLY ——<\/h1>\n\n\n\n

query_results = kb_qa({“question”: query_statement, “chat_history”: chat_history})<\/h1>\n\n\n\n

pprint(query_results[‘answer’])<\/h1>\n\n\n\n

pprint(query_results[‘source_documents’])<\/h1>\n\n\n\n

—— Question Loop ——<\/h1>\n\n\n\n

while query_statement != ‘exit’:
query_statement = input(‘Enter your question here: > ‘)
if query_statement != exit:
result = kb_qa({“question”: query_statement, “chat_history”: chat_history})
# pprint(result[“source_documents”])
pprint(result[“answer”])<\/p>\n\n\n\n

os.environ[“OPENAI_API_KEY”] = ”
print(“———- Life is good —————-“)<\/p>\n<\/div>\n","protected":false},"excerpt":{"rendered":"

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 …<\/p>\n

Fine tuning LLM with Langchain<\/span> Read More »<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"site-sidebar-layout":"default","site-content-layout":"default","ast-global-header-display":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","footnotes":""},"categories":[1],"tags":[],"class_list":["post-123","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"yoast_head":"\nFine tuning LLM with Langchain -<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/vulab.com\/index.php\/2023\/05\/02\/fine-tuning-llm-with-langchain\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Fine tuning LLM with Langchain -\" \/>\n<meta property=\"og:description\" content=\"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 … Fine tuning LLM with Langchain Read More »\" \/>\n<meta property=\"og:url\" content=\"https:\/\/vulab.com\/index.php\/2023\/05\/02\/fine-tuning-llm-with-langchain\/\" \/>\n<meta property=\"article:published_time\" content=\"2023-05-02T03:34:05+00:00\" \/>\n<meta name=\"author\" content=\"admin\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"admin\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"1 minute\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/vulab.com\/index.php\/2023\/05\/02\/fine-tuning-llm-with-langchain\/\",\"url\":\"https:\/\/vulab.com\/index.php\/2023\/05\/02\/fine-tuning-llm-with-langchain\/\",\"name\":\"Fine tuning LLM with Langchain -\",\"isPartOf\":{\"@id\":\"https:\/\/vulab.com\/#website\"},\"datePublished\":\"2023-05-02T03:34:05+00:00\",\"dateModified\":\"2023-05-02T03:34:05+00:00\",\"author\":{\"@id\":\"https:\/\/vulab.com\/#\/schema\/person\/20560f459fee0b370fcbf3e6d4c6a1ed\"},\"breadcrumb\":{\"@id\":\"https:\/\/vulab.com\/index.php\/2023\/05\/02\/fine-tuning-llm-with-langchain\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/vulab.com\/index.php\/2023\/05\/02\/fine-tuning-llm-with-langchain\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/vulab.com\/index.php\/2023\/05\/02\/fine-tuning-llm-with-langchain\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/vulab.com\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Fine tuning LLM with Langchain\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/vulab.com\/#website\",\"url\":\"https:\/\/vulab.com\/\",\"name\":\"\",\"description\":\"House of AI\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/vulab.com\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/vulab.com\/#\/schema\/person\/20560f459fee0b370fcbf3e6d4c6a1ed\",\"name\":\"admin\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/vulab.com\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/2b89f6ea5d0e39e731c1f6895d169f84e505346e20122aeebfff277a7ff91182?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/2b89f6ea5d0e39e731c1f6895d169f84e505346e20122aeebfff277a7ff91182?s=96&d=mm&r=g\",\"caption\":\"admin\"},\"sameAs\":[\"https:\/\/vulab.com\"],\"url\":\"https:\/\/vulab.com\/index.php\/author\/vulab_admin\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Fine tuning LLM with Langchain -","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/vulab.com\/index.php\/2023\/05\/02\/fine-tuning-llm-with-langchain\/","og_locale":"en_US","og_type":"article","og_title":"Fine tuning LLM with Langchain -","og_description":"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 … Fine tuning LLM with Langchain Read More »","og_url":"https:\/\/vulab.com\/index.php\/2023\/05\/02\/fine-tuning-llm-with-langchain\/","article_published_time":"2023-05-02T03:34:05+00:00","author":"admin","twitter_card":"summary_large_image","twitter_misc":{"Written by":"admin","Est. reading time":"1 minute"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/vulab.com\/index.php\/2023\/05\/02\/fine-tuning-llm-with-langchain\/","url":"https:\/\/vulab.com\/index.php\/2023\/05\/02\/fine-tuning-llm-with-langchain\/","name":"Fine tuning LLM with Langchain -","isPartOf":{"@id":"https:\/\/vulab.com\/#website"},"datePublished":"2023-05-02T03:34:05+00:00","dateModified":"2023-05-02T03:34:05+00:00","author":{"@id":"https:\/\/vulab.com\/#\/schema\/person\/20560f459fee0b370fcbf3e6d4c6a1ed"},"breadcrumb":{"@id":"https:\/\/vulab.com\/index.php\/2023\/05\/02\/fine-tuning-llm-with-langchain\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/vulab.com\/index.php\/2023\/05\/02\/fine-tuning-llm-with-langchain\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/vulab.com\/index.php\/2023\/05\/02\/fine-tuning-llm-with-langchain\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/vulab.com\/"},{"@type":"ListItem","position":2,"name":"Fine tuning LLM with Langchain"}]},{"@type":"WebSite","@id":"https:\/\/vulab.com\/#website","url":"https:\/\/vulab.com\/","name":"","description":"House of AI","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/vulab.com\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/vulab.com\/#\/schema\/person\/20560f459fee0b370fcbf3e6d4c6a1ed","name":"admin","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/vulab.com\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/2b89f6ea5d0e39e731c1f6895d169f84e505346e20122aeebfff277a7ff91182?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/2b89f6ea5d0e39e731c1f6895d169f84e505346e20122aeebfff277a7ff91182?s=96&d=mm&r=g","caption":"admin"},"sameAs":["https:\/\/vulab.com"],"url":"https:\/\/vulab.com\/index.php\/author\/vulab_admin\/"}]}},"jetpack_featured_media_url":"","_links":{"self":[{"href":"https:\/\/vulab.com\/index.php\/wp-json\/wp\/v2\/posts\/123","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/vulab.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/vulab.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/vulab.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/vulab.com\/index.php\/wp-json\/wp\/v2\/comments?post=123"}],"version-history":[{"count":1,"href":"https:\/\/vulab.com\/index.php\/wp-json\/wp\/v2\/posts\/123\/revisions"}],"predecessor-version":[{"id":124,"href":"https:\/\/vulab.com\/index.php\/wp-json\/wp\/v2\/posts\/123\/revisions\/124"}],"wp:attachment":[{"href":"https:\/\/vulab.com\/index.php\/wp-json\/wp\/v2\/media?parent=123"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/vulab.com\/index.php\/wp-json\/wp\/v2\/categories?post=123"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/vulab.com\/index.php\/wp-json\/wp\/v2\/tags?post=123"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}