使用 LangChain 和 Elasticsearch 实现隐私至上的 AI 搜索

python3 -m venv venv
source venv/bin/activate
pip install --upgrade pip
pip install beautifulsoup4 eland elasticsearch huggingface-hub langchain tqdm torch requests sentence_transformers

Copy

pip install -r requirements.txt

Copy

export ES_SERVER="YOURDESSERVERNAME.es.us-central1.gcp.cloud.es.io"
export ES_USERNAME="YOUR READ WRITE AND INDEX CREATING USER"
export ES_PASSWORD="YOUR PASSWORD"

Copy

source .env
python3 step-1A-scrape-urls.py
python3 step-1B-scrape-content.py

Copy

from pathlib import Path
import pickle


bookFilePath = "starwars_*_data*.pickle"
files = sorted(Path('./Dataset').glob(bookFilePath))
for fn in files:
   with open(fn,'rb') as f:
       part = pickle.load(f)
       for key, value in part.items():
           title = value['title'].strip()
           print(title)

Copy

from langchain.vectorstores import ElasticVectorSearch
from langchain.embeddings import HuggingFaceEmbeddings
from pathlib import Path
import pickle
import os
from tqdm import tqdm


model_name = "sentence-transformers/all-mpnet-base-v2"
hf = HuggingFaceEmbeddings(model_name=model_name)


index_name = "book_wookieepedia_mpnet"
endpoint = os.getenv('ES_SERVER', 'ERROR')
username = os.getenv('ES_USERNAME', 'ERROR')
password = os.getenv('ES_PASSWORD', 'ERROR')
url = f"https://{username}:{password}@{endpoint}:443"
db = ElasticVectorSearch(embedding=hf, elasticsearch_url=url, index_name=index_name)


batchtext = []
bookFilePath = "starwars_*_data*.pickle"
files = sorted(Path('./Dataset').glob(bookFilePath))
for fn in files:
    with open(fn,'rb') as f:
       part = pickle.load(f)
       for ix, (key, value) in tqdm(enumerate(part.items()), total=len(part)):
           paragraphs = value['paragraph']
           for p in paragraphs:
               batchtext.append(p)
       db.from_texts(batchtext,
                     embedding=hf,
                     elasticsearch_url=url,
                     index_name=index_name)

Copy

PUT /book_wookieepedia_mpnet
{
 "settings": {
   "number_of_shards": 4
 },
 "mappings": {
   "properties": {
     "metadata": {
       "type": "object"
     },
     "text": {
       "type": "text"
     },
     "vector": {
       "type": "dense_vector",
       "dims": 768
     }
   }
 }
}

Copy

source .env
python3 step-3A-upload-model.py

Copy

PUT /book_wookieepedia_mpnet
{
 "settings": {
   "number_of_shards": 4
 },
 "mappings": {
   "properties": {
     "metadata": {
       "type": "object"
     },
     "text": {
       "type": "text"
     },
     "vector": {
       "type": "dense_vector",
       "dims": 768
     }
   }
 }
}


PUT _ingest/pipeline/sw-embeddings
{
 "description": "Text embedding pipeline",
 "processors": [
   {
     "inference": {
       "model_id": "sentence-transformers__all-mpnet-base-v2",
       "target_field": "text_embedding",
       "field_map": {
         "text": "text_field"
       }
     }
   },
   {
     "set":{
       "field": "vector",
       "copy_from": "text_embedding.predicted_value"
     }
   },
   {
     "remove": {
       "field": "text_embedding"
     }
   }
 ],
 "on_failure": [
   {
     "set": {
       "description": "Index document to 'failed-<index>'",
       "field": "_index",
       "value": "failed-{{{_index}}}"
     }
   },
   {
     "set": {
       "description": "Set error message",
       "field": "ingest.failure",
       "value": "{{_ingest.on_failure_message}}"
     }
   }
 ]
}

Copy

POST _ingest/pipeline/sw-embeddings/_simulate
{
 "docs": [
   {
     "_source": {
       "text": "Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.",
       "metadata": {
         "a": "b"
       }
     }
   }
 ]
}

Copy

source .env
python3 step-3B-batch-hosted-vectorize.py

Copy

from langchain import PromptTemplate, HuggingFaceHub, LLMChain
from langchain.llms import HuggingFacePipeline
from transformers import AutoTokenizer, pipeline, AutoModelForSeq2SeqLM
from langchain.vectorstores import ElasticVectorSearch
from langchain.embeddings import HuggingFaceEmbeddings
import os


cache_dir = "./cache"
def getFlanLarge():
  
   model_id = 'google/flan-t5-large'
   print(f">> Prep. Get {model_id} ready to go")
   tokenizer = AutoTokenizer.from_pretrained(model_id)
   model = AutoModelForSeq2SeqLM.from_pretrained(model_id, cache_dir=cache_dir)
  
   pipe = pipeline(
       "text2text-generation",
       model=model,
       tokenizer=tokenizer,
       max_length=100
   )
   llm = HuggingFacePipeline(pipeline=pipe)
   return llm


local_llm = getFlanLarge()


def make_the_llm():
   template_informed = """
   I am a helpful AI that answers questions.
   When I don't know the answer I say I don't know.
   I know context: {context}
   when asked: {question}
   my response using only information in the context is: """
   prompt_informed = PromptTemplate(
       template=template_informed,
       input_variables=["context", "question"])
   return LLMChain(prompt=prompt_informed, llm=local_llm)


## continued below

Copy

## continued from above


topic = "Star Wars"
index_name = "book_wookieepedia_mpnet"


# Create the HuggingFace Transformer like before
model_name = "sentence-transformers/all-mpnet-base-v2"
hf = HuggingFaceEmbeddings(model_name=model_name)


## Elasticsearch as a vector db, just like before
endpoint = os.getenv('ES_SERVER', 'ERROR')
username = os.getenv('ES_USERNAME', 'ERROR')
password = os.getenv('ES_PASSWORD', 'ERROR')
url = f"https://{username}:{password}@{endpoint}:443"
db = ElasticVectorSearch(embedding=hf, elasticsearch_url=url, index_name=index_name)


## set up the conversational LLM
llm_chain_informed= make_the_llm()


def ask_a_question(question):
   ## get the relevant chunk from Elasticsearch for a question
   similar_docs = db.similarity_search(question)
   print(f'The most relevant passage: \n\t{similar_docs[0].page_content}')
   informed_context= similar_docs[0].page_content
   informed_response = llm_chain_informed.run(
       context=informed_context,
       question=question)
   return informed_response




# The conversational loop
print(f'I am a trivia chat bot, ask me any question about {topic}')
while True:
   command = input("User Question >> ")
   response= ask_a_question(command)
   print(f"\tAnswer  : {response}")

Copy