Add files via upload
This commit is contained in:
commit
a4f7ca4f01
272
Untitled-1.ipynb
Normal file
272
Untitled-1.ipynb
Normal file
@ -0,0 +1,272 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Note: you may need to restart the kernel to use updated packages.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"ERROR: Could not find a version that satisfies the requirement faiss-gpu (from versions: none)\n",
|
||||
"ERROR: No matching distribution found for faiss-gpu\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"%pip install -q unstructured-client unstructured[all-docs] langchain transformers accelerate bitsandbytes sentence-transformers faiss-gpu"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"ename": "ModuleNotFoundError",
|
||||
"evalue": "No module named 'unstructured_client'",
|
||||
"output_type": "error",
|
||||
"traceback": [
|
||||
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
|
||||
"\u001b[1;31mModuleNotFoundError\u001b[0m Traceback (most recent call last)",
|
||||
"Cell \u001b[1;32mIn[5], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01munstructured_client\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m UnstructuredClient \u001b[38;5;66;03m# type: ignore\u001b[39;00m\n\u001b[0;32m 3\u001b[0m unstructured_api_key \u001b[38;5;241m=\u001b[39m os\u001b[38;5;241m.\u001b[39menviron\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mUNSTRUCTURED_API_KEY\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m 5\u001b[0m client \u001b[38;5;241m=\u001b[39m UnstructuredClient(\n\u001b[0;32m 6\u001b[0m api_key_auth\u001b[38;5;241m=\u001b[39munstructured_api_key,\n\u001b[0;32m 7\u001b[0m \u001b[38;5;66;03m# if using paid API, provide your unique API URL:\u001b[39;00m\n\u001b[0;32m 8\u001b[0m \u001b[38;5;66;03m# server_url=\"YOUR_API_URL\",\u001b[39;00m\n\u001b[0;32m 9\u001b[0m )\n",
|
||||
"\u001b[1;31mModuleNotFoundError\u001b[0m: No module named 'unstructured_client'"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from unstructured_client import UnstructuredClient # type: ignore\n",
|
||||
"\n",
|
||||
"unstructured_api_key = os.environ.get(\"UNSTRUCTURED_API_KEY\")\n",
|
||||
"\n",
|
||||
"client = UnstructuredClient(\n",
|
||||
" api_key_auth=unstructured_api_key,\n",
|
||||
" # if using paid API, provide your unique API URL:\n",
|
||||
" # server_url=\"YOUR_API_URL\",\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"ename": "ModuleNotFoundError",
|
||||
"evalue": "No module named 'unstructured_client'",
|
||||
"output_type": "error",
|
||||
"traceback": [
|
||||
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
|
||||
"\u001b[1;31mModuleNotFoundError\u001b[0m Traceback (most recent call last)",
|
||||
"Cell \u001b[1;32mIn[7], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01munstructured_client\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mmodels\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m shared \u001b[38;5;66;03m# type: ignore\u001b[39;00m\n\u001b[0;32m 2\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01munstructured_client\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mmodels\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01merrors\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m SDKError \u001b[38;5;66;03m# type: ignore\u001b[39;00m\n\u001b[0;32m 3\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01munstructured\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mstaging\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mbase\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m dict_to_elements \u001b[38;5;66;03m# type: ignore\u001b[39;00m\n",
|
||||
"\u001b[1;31mModuleNotFoundError\u001b[0m: No module named 'unstructured_client'"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from unstructured_client.models import shared # type: ignore\n",
|
||||
"from unstructured_client.models.errors import SDKError # type: ignore\n",
|
||||
"from unstructured.staging.base import dict_to_elements # type: ignore\n",
|
||||
"\n",
|
||||
"path_to_pdf=\"PATH_TO_YOUR_PDF_FILE\"\n",
|
||||
"\n",
|
||||
"with open(path_to_pdf, \"rb\") as f:\n",
|
||||
" files=shared.Files(\n",
|
||||
" content=f.read(),\n",
|
||||
" file_name=path_to_pdf,\n",
|
||||
" )\n",
|
||||
" req = shared.PartitionParameters(\n",
|
||||
" files=files,\n",
|
||||
" chunking_strategy=\"by_title\",\n",
|
||||
" max_characters=512,\n",
|
||||
" )\n",
|
||||
" try:\n",
|
||||
" resp = client.general.partition(req)\n",
|
||||
" except SDKError as e:\n",
|
||||
" print(e)\n",
|
||||
"\n",
|
||||
"elements = dict_to_elements(resp.elements)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"ename": "ModuleNotFoundError",
|
||||
"evalue": "No module named 'langchain_core'",
|
||||
"output_type": "error",
|
||||
"traceback": [
|
||||
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
|
||||
"\u001b[1;31mModuleNotFoundError\u001b[0m Traceback (most recent call last)",
|
||||
"Cell \u001b[1;32mIn[8], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mlangchain_core\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mdocuments\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m Document\n\u001b[0;32m 2\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mlangchain\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mvectorstores\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m FAISS\n\u001b[0;32m 3\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mlangchain\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01membeddings\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m HuggingFaceEmbeddings\n",
|
||||
"\u001b[1;31mModuleNotFoundError\u001b[0m: No module named 'langchain_core'"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain_core.documents import Document\n",
|
||||
"from langchain.vectorstores import FAISS\n",
|
||||
"from langchain.embeddings import HuggingFaceEmbeddings\n",
|
||||
"\n",
|
||||
"documents = []\n",
|
||||
"for element in elements:\n",
|
||||
" metadata = element.metadata.to_dict()\n",
|
||||
" documents.append(Document(page_content=element.text, metadata=metadata))\n",
|
||||
"\n",
|
||||
"db = FAISS.from_documents(documents, HuggingFaceEmbeddings(model_name=\"BAAI/bge-base-en-v1.5\"))\n",
|
||||
"retriever = db.as_retriever(search_type=\"similarity\", search_kwargs={\"k\": 4})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"ename": "ModuleNotFoundError",
|
||||
"evalue": "No module named 'huggingface_hub'",
|
||||
"output_type": "error",
|
||||
"traceback": [
|
||||
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
|
||||
"\u001b[1;31mModuleNotFoundError\u001b[0m Traceback (most recent call last)",
|
||||
"Cell \u001b[1;32mIn[9], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mhuggingface_hub\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mhf_api\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m HfFolder\n\u001b[0;32m 3\u001b[0m HfFolder\u001b[38;5;241m.\u001b[39msave_token(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mYOUR_HF_TOKEN\u001b[39m\u001b[38;5;124m'\u001b[39m)\n",
|
||||
"\u001b[1;31mModuleNotFoundError\u001b[0m: No module named 'huggingface_hub'"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from huggingface_hub.hf_api import HfFolder\n",
|
||||
"\n",
|
||||
"HfFolder.save_token('YOUR_HF_TOKEN')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"ename": "ModuleNotFoundError",
|
||||
"evalue": "No module named 'torch'",
|
||||
"output_type": "error",
|
||||
"traceback": [
|
||||
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
|
||||
"\u001b[1;31mModuleNotFoundError\u001b[0m Traceback (most recent call last)",
|
||||
"Cell \u001b[1;32mIn[10], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mtorch\u001b[39;00m\n\u001b[0;32m 2\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtransformers\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig\n\u001b[0;32m 4\u001b[0m model_name \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmeta-llama/Meta-Llama-3-8B-Instruct\u001b[39m\u001b[38;5;124m\"\u001b[39m\n",
|
||||
"\u001b[1;31mModuleNotFoundError\u001b[0m: No module named 'torch'"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import torch\n",
|
||||
"from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig\n",
|
||||
"\n",
|
||||
"model_name = \"meta-llama/Meta-Llama-3-8B-Instruct\"\n",
|
||||
"\n",
|
||||
"bnb_config = BitsAndBytesConfig(\n",
|
||||
" load_in_4bit=True, bnb_4bit_use_double_quant=True, bnb_4bit_quant_type=\"nf4\", bnb_4bit_compute_dtype=torch.bfloat16\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"model = AutoModelForCausalLM.from_pretrained(model_name, quantization_config=bnb_config)\n",
|
||||
"tokenizer = AutoTokenizer.from_pretrained(model_name)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.llms import HuggingFacePipeline\n",
|
||||
"from langchain.prompts import PromptTemplate\n",
|
||||
"from transformers import pipeline\n",
|
||||
"from langchain_core.output_parsers import StrOutputParser\n",
|
||||
"from langchain_core.runnables import RunnablePassthrough\n",
|
||||
"\n",
|
||||
"terminators = [\n",
|
||||
" tokenizer.eos_token_id,\n",
|
||||
" tokenizer.convert_tokens_to_ids(\"<|eot_id|>\")\n",
|
||||
"]\n",
|
||||
"\n",
|
||||
"text_generation_pipeline = pipeline(\n",
|
||||
" model=model,\n",
|
||||
" tokenizer=tokenizer,\n",
|
||||
" task=\"text-generation\",\n",
|
||||
" temperature=0.2,\n",
|
||||
" do_sample=True,\n",
|
||||
" repetition_penalty=1.1,\n",
|
||||
" return_full_text=False,\n",
|
||||
" max_new_tokens=200,\n",
|
||||
" eos_token_id=terminators,\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"llm = HuggingFacePipeline(pipeline=text_generation_pipeline)\n",
|
||||
"\n",
|
||||
"prompt_template = \"\"\"\n",
|
||||
"<|start_header_id|>user<|end_header_id|>\n",
|
||||
"You are an assistant for answering questions about IPM.\n",
|
||||
"You are given the extracted parts of a long document and a question. Provide a conversational answer.\n",
|
||||
"If you don't know the answer, just say \"I do not know.\" Don't make up an answer.\n",
|
||||
"Question: {question}\n",
|
||||
"Context: {context}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n",
|
||||
"\"\"\"\n",
|
||||
"\n",
|
||||
"prompt = PromptTemplate(\n",
|
||||
" input_variables=[\"context\", \"question\"],\n",
|
||||
" template=prompt_template,\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"def format_docs(docs):\n",
|
||||
" return \"\\n\\n\".join(doc.page_content for doc in docs)\n",
|
||||
"\n",
|
||||
"rag_chain = (\n",
|
||||
" {\"context\": retriever | format_docs, \"question\": RunnablePassthrough()}\n",
|
||||
" | prompt\n",
|
||||
" | llm\n",
|
||||
" | StrOutputParser()\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"question = \"What is best practices for RAG ?\"\n",
|
||||
"rag_chain.invoke(question)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.12.3"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
Loading…
x
Reference in New Issue
Block a user