!pip install langchain langchain_groq langchain_ollama langchain_community pymupdf pypdf

!mkdir ./data
!mkdir ./chunk_caches
!wget "https://www.binasss.sa.cr/int23/8.pdf" -O "./data/fibromyalgia.pdf"

from langchain_groq import ChatGroq
from langchain_ollama import ChatOllama
import os
os.environ["GROQ_API_KEY"] = "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"

llm_relevancy = ChatGroq(
    model="llama-3.3-70b-versatile",
    temperature=0,
)

llm = ChatOllama(
    model="deepseek-r1:14b",
    temperature=0.6,
    max_tokens=3000,
)

REAG_SYSTEM_PROMPT = """
# 角色和目標(biāo)
你是一個智能知識檢索助手。你的任務(wù)是分析提供的文檔或網(wǎng)址，為用戶查詢提取最相關(guān)的信息。

# 指令
1. 仔細(xì)分析用戶的查詢，確定關(guān)鍵概念和要求。
2. 在提供的來源中搜索相關(guān)信息，并在“content”字段中輸出相關(guān)部分。
3. 如果你在文檔中找不到必要的信息，返回“isIrrelevant: true”，否則返回“isIrrelevant: false”。

# 約束
- 不要超出可用數(shù)據(jù)進行假設(shè)
- 明確指出是否未找到相關(guān)信息
- 在選擇來源時保持客觀
"""

rag_prompt = """你是一個問答任務(wù)助手。使用以下檢索到的上下文片段來回答問題。如果你不知道答案，就說不知道。最多用三句話，保持回答簡潔。
問題：{question} 
上下文：{context} 
答案：
"""

from pydantic import BaseModel, Field
from typing import List
from langchain_core.output_parsers import JsonOutputParser

class ResponseSchema(BaseModel):
    content: str = Field(..., description="文檔中與回答所提問題相關(guān)或足以回答問題的頁面內(nèi)容")
    reasoning: str = Field(..., description="針對所提問題選擇該頁面內(nèi)容的原因")
    is_irrelevant: bool = Field(..., description="如果文檔中的內(nèi)容不足以或與回答所提問題無關(guān)，指定為“True”；如果上下文或頁面內(nèi)容與回答問題相關(guān)，則指定為“False”")

class RelevancySchemaMessage(BaseModel):
    source: ResponseSchema

relevancy_parser = JsonOutputParser(pydantic_object=RelevancySchemaMessage)

from langchain_community.document_loaders import PyMuPDFLoader

file_path = "./data/fibromyalgia.pdf"
loader = PyMuPDFLoader(file_path)
docs = loader.load()
print(len(docs))
print(docs[0].metadata)

8
{'producer': 'Acrobat Distiller 6.0 for Windows',
'creator': 'Elsevier',
'creationdate': '2023-01-20T09:25:19-06:00',
'source': './data/fibromyalgia.pdf',
'file_path': './data/fibromyalgia.pdf',
'total_pages': 8,
'format': 'PDF 1.7',
'title': 'Fibromyalgia: Diagnosis and Management',
'author': 'Bradford T. Winslow MD',
'subject': 'American Family Physician, 107 (2023) 137-144',
'keywords': '',
'moddate': '2023-02-27T15:02:12+05:30',
'trapped': '',
'modDate': "D:20230227150212+05'30'",
'creationDate': "D:20230120092519-06'00'",
'page': 0}

from langchain.schema import Document

def format_doc(doc: Document) -> str:
    return f"Document_Title: {doc.metadata['title']}\nPage: {doc.metadata['page']}\nContent: {doc.page_content}"

from langchain_core.prompts import PromptTemplate

def extract_relevant_context(question, documents):
    result = []
    for doc in documents:
        formatted_documents = format_doc(doc)
        system = f"{REAG_SYSTEM_PROMPT}\n\n# Available source\n\n{formatted_documents}"
        prompt = f"""Determine if the 'Avaiable source' content supplied is sufficient and relevant to ANSWER the QUESTION asked.
        QUESTION: {question}
        #INSTRUCTIONS TO FOLLOW
        1. Analyze the context provided thoroughly to check its relevancy to help formulizing a response for the QUESTION asked.
        2, STRICTLY PROVIDE THE RESPONSE IN A JSON STRUCTURE AS DESCRIBED BELOW:
            ```json
               {{"content":<<The page content of the document that is relevant or sufficient to answer the question asked>>,
                 "reasoning":<<The reasoning for selecting The page content with respect to the question asked>>,
                 "is_irrelevant":<<Specify 'True' if the content in the document is not sufficient or relevant.Specify 'False' if the page content is sufficient to answer the QUESTION>>
                 }}
            ```
         """
        messages =[ {"role": "system", "content": system},
                       {"role": "user", "content": prompt},
                    ]
        response = llm_relevancy.invoke(messages)    
        print(response.content)
        formatted_response = relevancy_parser.parse(response.content)
        result.append(formatted_response)
    final_context = []
    for items in result:
        if (items['is_irrelevant'] == False) or ( items['is_irrelevant'] == 'false') or (items['is_irrelevant'] == 'False'):
            final_context.append(items['content'])
    return final_context

question = "What is Fibromyalgia?"
final_context = extract_relevant_context(question, docs)
print(len(final_context))

def generate_response(question, final_context):
    prompt = PromptTemplate(template=rag_prompt,
                                     input_variables=["question","context"],)
    chain  = prompt | llm
    response = chain.invoke({"question":question,"context":final_context})
    print(response.content.split("\n\n")[-1])
    return response.content.split("\n\n")[-1]

final_response = generate_response(question, final_context)
final_response

'Fibromyalgia is a chronic condition characterized by widespread musculoskeletal pain, fatigue, disrupted sleep, and cognitive difficulties like "fibrofog." It is often associated with heightened sensitivity to pain due to altered nervous system processing. Diagnosis considers symptoms such as long-term pain, fatigue, and sleep issues without underlying inflammation or injury.'

question =  "What are the causes of Fibromyalgia?"
final_context = extract_relevant_context(question, docs)
final_response = generate_response(question, final_context)

Fibromyalgia likely results from disordered central pain processing leading to heightened sensitivity (hyperalgesia and allodynia). Possible causes include dysfunction of the hypothalamic-pituitary-adrenal axis, inflammation, glial activation, small fiber neuropathy, infections like Epstein-Barr virus or Lyme disease, and a genetic component. Other conditions, such as infections or medication side effects, may also contribute to similar symptoms.

question =  "Do people suffering from rheumatologic conditions may have fibromyalgia?"
final_context = extract_relevant_context(question, docs)
final_response = generate_response(question, final_context)

Yes, people with rheumatologic conditions, such as rheumatoid arthritis or psoriatic arthritis, may also have fibromyalgia. This is because they share overlapping symptoms, making diagnosis challenging.

question =  "Mention the nonpharmacologic treatment for fibromyalgia?"
final_context = extract_relevant_context(question, docs)
final_response = generate_response(question, final_context)

Nonpharmacologic treatments for fibromyalgia include patient education, exercise, and cognitive behavior therapy (CBT).

question =  "According to 2016 American College of Rheumatology Fibromyalgia what is the Diagnostic Criteria for Fibromyalgia?"
final_context = extract_relevant_context(question, docs)
final_response = generate_response(question, final_context)

The 2016 American College of Rheumatology diagnostic criteria for fibromyalgia require generalized pain in at least four of five body regions for at least three months. Additionally, patients must meet either a Widespread Pain Index (WPI) score of ≥7 with a Symptom Severity Scale (SSS) score of ≥5 or a WPI score of ≥4 with an SSS score of ≥9. Other disorders that could explain the symptoms must be ruled out.

question =  "What is the starting dosage of Amitriptyline?"
final_context = extract_relevant_context(question, docs)
final_response = generate_response(question, final_context)

The starting dosage of Amitriptyline for adults is usually between 25 to 50 mg per day, often beginning with a lower dose of 5 to 10 mg at night to minimize side effects before gradually increasing.

question = "What has been mentioned about AAPT 2019 Diagnostic Criteria for Fibromyalgia"
final_context = extract_relevant_context(question, docs)
final_response = generate_response(question, final_context)

The AAPT 2019 criteria for fibromyalgia include multisite pain in at least six of nine specified areas, moderate to severe sleep problems or fatigue, and symptoms lasting three months or more.

question =  "What are the medications and doses for Fibromyalgia?"
final_context = extract_relevant_context(question, docs)
print(final_context)
final_response = generate_response(question, final_context)

['Duloxetine, milnacipran, pregabalin, and amitriptyline are potentially effective medications for fibromyalgia. Nonsteroidal anti-inflammatory drugs and opioids have not demonstrated benefits for fibromyalgia and have significant limitations.',
 'Amitriptyline, cyclobenzaprine, duloxetine (Cymbalta), milnacipran (Savella), and pregabalin (Lyrica) are effective for pain in fibromyalgia.43,46-48,50,52,54',
 'Amitriptyline (tricyclic antidepressant) - 5 to 10 mg at night, 20 to 30 mg at night. Cyclobenzaprine (muscle relaxant; tricyclic derivative) - 5 to 10 mg at night, 10 to 40 mg daily in 1 to 3 divided doses. Duloxetine (Cymbalta; serotonin-norepinephrine reuptake inhibitor) - 20 to 30 mg every morning, 60 mg every morning. Milnacipran (Savella; serotonin-norepinephrine reuptake inhibitor) - 12.5 mg every morning, 50 mg twice daily. Pregabalin (Lyrica; gabapentinoid) - 25 to 50 mg at bedtime, 150 to 450 mg at bedtime.',
 'Fibromyalgia is often treated with medications such as pregabalin (Lyrica) and duloxetine (Cymbalta). Pregabalin can be started at a dose of 75 mg twice daily, with a maximum dose of 450 mg/day. Duloxetine can be initiated at a dose of 30 mg once daily, with a target dose of 60 mg/day.',
 'Fibromyalgia is often treated with medications such as pregabalin (Lyrica) and duloxetine (Cymbalta). Pregabalin can be started at a dose of 75 mg twice daily, with a maximum dose of 450 mg/day. Duloxetine can be initiated at a dose of 30 mg once daily, with a target dose of 60 mg/day.']

The medications commonly used to treat fibromyalgia include:

1. **Amitriptyline**: A tricyclic antidepressant typically taken at night in doses ranging from 5 to 30 mg.

2. **Cyclobenzaprine**: A muscle relaxant and tricyclic derivative, usually administered in doses up to 40 mg daily in divided doses.

3. **Duloxetine (Cymbalta)**: A serotonin-norepinephrine reuptake inhibitor taken in the morning, starting at 20-30 mg and increasing to 60 mg if needed.

4. **Milnacipran (Savella)**: Another serotonin-norepinephrine reuptake inhibitor, starting at 12.5 mg in the morning and potentially increased to 50 mg twice daily.

5. **Pregabalin (Lyrica)**: A gabapentinoid taken at bedtime, beginning with 75 mg twice daily and up to a maximum of 450 mg/day.

These medications are effective for managing pain associated with fibromyalgia. It's important to note that dosages should be adjusted under medical supervision, starting low and increasing as necessary. Additionally, NSAIDs and opioids are not recommended for treating fibromyalgia due to limited effectiveness and potential side effects.