!pip install -q torch transformers accelerate bitsandbytes sentence-transformers unstructured[all-docs] langchain chromadb langchain_community

!mkdir -p "./documents"
!wget https://www.gov.nl.ca/ecc/files/env-protection-pesticides-business-manuals-applic-chapter7.pdf -O "./documents/env-protection-pesticides-business-manuals-applic-chapter7.pdf"
!wget https://ipm.ifas.ufl.edu/pdfs/Citrus_IPM_090913.pptx -O "./documents/Citrus_IPM_090913.pptx"
!wget https://www.gutenberg.org/ebooks/45957.epub3.images -O "./documents/45957.epub"
!wget https://blog.fifthroom.com/what-to-do-about-harmful-garden-and-plant-insects-and-pests.html -O "./documents/what-to-do-about-harmful-garden-and-plant-insects-and-pests.html"

# Optional cell to reduce the amount of logs

import logging

logger = logging.getLogger("unstructured.ingest")
logger.root.removeHandler(logger.root.handlers[0])

>>> import os

>>> from unstructured.ingest.connector.local import SimpleLocalConfig
>>> from unstructured.ingest.interfaces import PartitionConfig, ProcessorConfig, ReadConfig
>>> from unstructured.ingest.runner import LocalRunner

>>> output_path = "./local-ingest-output"

>>> runner = LocalRunner(
...     processor_config=ProcessorConfig(
...         # logs verbosity
...         verbose=True,
...         # the local directory to store outputs
...         output_dir=output_path,
...         num_processes=2,
...     ),
...     read_config=ReadConfig(),
...     partition_config=PartitionConfig(
...         partition_by_api=True,
...         api_key="YOUR_UNSTRUCTURED_API_KEY",
...     ),
...     connector_config=SimpleLocalConfig(
...         input_path="./documents",
...         # whether to get the documents recursively from given directory
...         recursive=False,
...     ),
... )
>>> runner.run()

!brew install poppler
!brew install tesseract

from unstructured.staging.base import elements_from_json

elements = []

for filename in os.listdir(output_path):
    filepath = os.path.join(output_path, filename)
    elements.extend(elements_from_json(filepath))

from unstructured.chunking.title import chunk_by_title

chunked_elements = chunk_by_title(
    elements,
    # maximum for chunk size
    max_characters=512,
    # You can choose to combine consecutive elements that are too small
    # e.g. individual list items
    combine_text_under_n_chars=200,
)

from langchain_core.documents import Document

documents = []
for chunked_element in chunked_elements:
    metadata = chunked_element.metadata.to_dict()
    metadata["source"] = metadata["filename"]
    del metadata["languages"]
    documents.append(Document(page_content=chunked_element.text, metadata=metadata))

from langchain_community.vectorstores import Chroma
from langchain.embeddings import HuggingFaceEmbeddings

from langchain.vectorstores import utils as chromautils

# ChromaDB doesn't support complex metadata, e.g. lists, so we drop it here.
# If you're using a different vector store, you may not need to do this
docs = chromautils.filter_complex_metadata(documents)

embeddings = HuggingFaceEmbeddings(model_name="BAAI/bge-base-en-v1.5")
vectorstore = Chroma.from_documents(documents, embeddings)
retriever = vectorstore.as_retriever(search_type="similarity", search_kwargs={"k": 3})

from huggingface_hub import notebook_login

notebook_login()

from langchain.prompts import PromptTemplate
from langchain.llms import HuggingFacePipeline
from transformers import pipeline
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
from langchain.chains import RetrievalQA

model_name = "meta-llama/Meta-Llama-3-8B-Instruct"

bnb_config = BitsAndBytesConfig(
    load_in_4bit=True, bnb_4bit_use_double_quant=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16
)

model = AutoModelForCausalLM.from_pretrained(model_name, quantization_config=bnb_config)
tokenizer = AutoTokenizer.from_pretrained(model_name)

terminators = [tokenizer.eos_token_id, tokenizer.convert_tokens_to_ids("<|eot_id|>")]

text_generation_pipeline = pipeline(
    model=model,
    tokenizer=tokenizer,
    task="text-generation",
    temperature=0.2,
    do_sample=True,
    repetition_penalty=1.1,
    return_full_text=False,
    max_new_tokens=200,
    eos_token_id=terminators,
)

llm = HuggingFacePipeline(pipeline=text_generation_pipeline)

prompt_template = """
<|start_header_id|>user<|end_header_id|>
You are an assistant for answering questions using provided context.
You are given the extracted parts of a long document and a question. Provide a conversational answer.
If you don't know the answer, just say "I do not know." Don't make up an answer.
Question: {question}
Context: {context}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
"""

prompt = PromptTemplate(
    input_variables=["context", "question"],
    template=prompt_template,
)


qa_chain = RetrievalQA.from_chain_type(llm, retriever=retriever, chain_type_kwargs={"prompt": prompt})

question = "Are aphids a pest?"

qa_chain.invoke(question)["result"]

Yes, aphids are considered pests because they feed on the nutrient-rich liquids within plants, causing damage and potentially spreading disease. In fact, they're known to multiply quickly, which is why it's essential to control them promptly. As mentioned in the text, aphids can also attract ants, which are attracted to the sweet, sticky substance they produce called honeydew. So, yes, aphids are indeed a pest that requires attention to prevent further harm to your plants!