RAG with Capella Model Services, LangChain and Couchbase Hyperscale & Composite Vector Indexes

%pip install --quiet datasets==4.4.1 langchain-couchbase==1.0.0 langchain-openai==1.1.0

Note: you may need to restart the kernel to use updated packages.

import logging
import os
import time

from datetime import timedelta

from dotenv import load_dotenv

from couchbase.auth import PasswordAuthenticator
from couchbase.cluster import Cluster
from couchbase.exceptions import CouchbaseException
from couchbase.options import ClusterOptions

from datasets import load_dataset

from langchain_core.documents import Document
from langchain_core.globals import set_llm_cache
from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough
from langchain_couchbase.cache import CouchbaseCache
from langchain_couchbase.vectorstores import CouchbaseQueryVectorStore
from langchain_couchbase.vectorstores import DistanceStrategy, IndexType
from langchain_openai import ChatOpenAI, OpenAIEmbeddings

from tqdm import tqdm

/Users/kaustavghosh/Library/Python/3.14/lib/python/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html
  from .autonotebook import tqdm as notebook_tqdm
/Users/kaustavghosh/Library/Python/3.14/lib/python/site-packages/langchain_core/_api/deprecation.py:26: UserWarning: Core Pydantic V1 functionality isn't compatible with Python 3.14 or greater.
  from pydantic.v1.fields import FieldInfo as FieldInfoV1

# Load environment variables from .env file
load_dotenv()

# Couchbase connection settings (no defaults for sensitive values)
CB_CONNECTION_STRING = os.getenv("CB_CONNECTION_STRING")
CB_USERNAME = os.getenv("CB_USERNAME")
CB_PASSWORD = os.getenv("CB_PASSWORD")
CB_BUCKET_NAME = os.getenv("CB_BUCKET_NAME")

# Collection settings (with sensible defaults)
SCOPE_NAME = os.getenv("SCOPE_NAME", "_default")
COLLECTION_NAME = os.getenv("COLLECTION_NAME", "langchain_docs")
CACHE_COLLECTION = os.getenv("CACHE_COLLECTION", "cache")

# Capella Model Services settings
CAPELLA_MODEL_SERVICES_ENDPOINT = os.getenv("CAPELLA_MODEL_SERVICES_ENDPOINT")

# Model names (with defaults matching tutorial recommendations)
LLM_MODEL_NAME = os.getenv("LLM_MODEL_NAME", "mistralai/mistral-7b-instruct-v0.3")
EMBEDDING_MODEL_NAME = os.getenv("EMBEDDING_MODEL_NAME", "nvidia/llama-3.2-nv-embedqa-1b-v2")

# API keys (no defaults for sensitive values)
LLM_API_KEY = os.getenv("LLM_API_KEY")
EMBEDDING_API_KEY = os.getenv("EMBEDDING_API_KEY")

# Validate required environment variables
if not all([
    CB_CONNECTION_STRING,
    CB_USERNAME,
    CB_PASSWORD,
    CB_BUCKET_NAME,
    CAPELLA_MODEL_SERVICES_ENDPOINT,
    LLM_API_KEY,
    EMBEDDING_API_KEY,
]):
    raise ValueError(
        "Missing required environment variables. Please ensure your .env file contains:\n"
        "- CB_CONNECTION_STRING\n"
        "- CB_USERNAME\n"
        "- CB_PASSWORD\n"
        "- CB_BUCKET_NAME\n"
        "- CAPELLA_MODEL_SERVICES_ENDPOINT\n"
        "- LLM_API_KEY\n"
        "- EMBEDDING_API_KEY"
    )

print("Environment variables loaded successfully")

Environment variables loaded successfully

try:
    auth = PasswordAuthenticator(CB_USERNAME, CB_PASSWORD)
    options = ClusterOptions(auth)
    cluster = Cluster(CB_CONNECTION_STRING, options)
    cluster.wait_until_ready(timedelta(seconds=5))
    print("Successfully connected to Couchbase")
except Exception as e:
    raise ConnectionError(f"Failed to connect to Couchbase: {str(e)}")

Successfully connected to Couchbase

def setup_collection(cluster, bucket_name, scope_name, collection_name, flush_collection=False):
    try:
        bucket = cluster.bucket(bucket_name)
        bucket_manager = bucket.collections()

        # Check if scope exists, create if it doesn't
        scopes = bucket_manager.get_all_scopes()
        scope_exists = any(scope.name == scope_name for scope in scopes)
        
        if not scope_exists:
            print(f"Scope '{scope_name}' does not exist. Creating it...")
            bucket_manager.create_scope(scope_name)
            print(f"Scope '{scope_name}' created successfully.")
            # Refresh scopes list after creation
            scopes = bucket_manager.get_all_scopes()
        else:
            print(f"Scope '{scope_name}' already exists. Skipping creation.")
        
        # Check if collection exists, create if it doesn't (reuse scopes variable)
        collection_exists = any(
            scope.name == scope_name
            and collection_name in [col.name for col in scope.collections]
            for scope in scopes
        )

        if not collection_exists:
            print(f"Collection '{collection_name}' does not exist. Creating it...")
            bucket_manager.create_collection(scope_name, collection_name)
            print(f"Collection '{collection_name}' created successfully.")
        else:
            print(f"Collection '{collection_name}' already exists. Skipping creation.")

        collection = bucket.scope(scope_name).collection(collection_name)
        time.sleep(2)  # Give the collection time to be ready for queries

        # Create primary index for the collection (required for DELETE operations)
        try:
            index_name = f"`{bucket_name}`.`{scope_name}`.`{collection_name}`"
            query = f"CREATE PRIMARY INDEX IF NOT EXISTS ON {index_name}"
            cluster.query(query).execute()
            print(f"Primary index created/verified for {collection_name}.")
        except Exception as e:
            print(f"Note: Could not create primary index: {str(e)}")

        if flush_collection:
            # Clear all documents in the collection
            try:
                query = f"DELETE FROM `{bucket_name}`.`{scope_name}`.`{collection_name}`"
                cluster.query(query).execute()
                print("All documents cleared from the collection.")
            except Exception as e:
                print(
                    f"Error while clearing documents: {str(e)}. The collection might be empty."
                )

    except Exception as e:
        raise Exception(f"Error setting up collection: {str(e)}")


# Setup main collection for vector store
setup_collection(cluster, CB_BUCKET_NAME, SCOPE_NAME, COLLECTION_NAME, flush_collection=True)

# Setup cache collection for LLM response caching
setup_collection(cluster, CB_BUCKET_NAME, SCOPE_NAME, CACHE_COLLECTION, flush_collection=True)

Scope 'shared' already exists. Skipping creation.
Collection 'langchain_query' already exists. Skipping creation.
Primary index created/verified for langchain_query.
All documents cleared from the collection.
Scope 'shared' already exists. Skipping creation.
Collection 'cache' already exists. Skipping creation.
Primary index created/verified for cache.
All documents cleared from the collection.

try:
    news_dataset = load_dataset('RealTimeData/bbc_news_alltime', '2024-12', split="train")
    print(f"Loaded the BBC News dataset with {len(news_dataset)} rows")
except Exception as e:
    raise ValueError(f"Error loading BBC dataset: {str(e)}")

Loaded the BBC News dataset with 2687 rows

print(news_dataset[:5])

{'title': ["Pakistan protest: Bushra Bibi's march for Imran Khan disappeared - BBC News", 'Lockdown DIY linked to Walleys Quarry gases - BBC News', 'Newscast - What next for the assisted dying bill? - BBC Sounds', "F1: Bernie Ecclestone to sell car collection worth 'hundreds of millions' - BBC Sport", 'British man Tyler Kerry from Basildon dies on holiday in Turkey - BBC News'], 'published_date': ['2024-12-01', '2024-12-01', '2024-12-01', '2024-12-01', '2024-12-01'], 'authors': ['https://www.facebook.com/bbcnews', 'https://www.facebook.com/bbcnews', None, 'https://www.facebook.com/BBCSport/', 'https://www.facebook.com/bbcnews'], 'description': ["Imran Khan's third wife guided protesters to the heart of the capital - and then disappeared.", 'An academic says an increase in plasterboard sent to landfill could be behind a spike in smells.', 'And rebel forces in Syria have taken control of Aleppo', 'Former Formula 1 boss Bernie Ecclestone is to sell his collection of race cars driven by motorsport legends including Michael Schumacher, Niki Lauda and Nelson Piquet.', 'Tyler Kerry was "a young man full of personality, kindness and compassion", his uncle says.'], 'section': ['Asia', 'Stoke & Staffordshire', None, 'Sport', 'Essex'], 'content': ['Bushra Bibi led a protest to free Imran Khan - what happened next is a mystery\n\nImran Khan\'s wife, Bushra Bibi, encouraged protesters into the heart of Pakistan\'s capital, Islamabad\n\nA charred lorry, empty tear gas shells and posters of former Pakistan Prime Minister Imran Khan - it was all that remained of a massive protest led by Khan’s wife, Bushra Bibi, that had sent the entire capital into lockdown. Just a day earlier, faith healer Bibi - wrapped in a white shawl, her face covered by a white veil - stood atop a shipping container on the edge of the city as thousands of her husband’s devoted followers waved flags and chanted slogans beneath her. It was the latest protest to flare since Khan, the 72-year-old cricketing icon-turned-politician, was jailed more than a year ago after falling foul of the country\'s influential military which helped catapult him to power. “My children and my brothers! You have to stand with me,” Bibi cried on Tuesday afternoon, her voice cutting through the deafening roar of the crowd. “But even if you don’t,” she continued, “I will still stand firm. “This is not just about my husband. It is about this country and its leader.” It was, noted some watchers of Pakistani politics, her political debut. But as the sun rose on Wednesday morning, there was no sign of Bibi, nor the thousands of protesters who had marched through the country to the heart of the capital, demanding the release of their jailed leader. While other PMs have fallen out with Pakistan\'s military in the past, Khan\'s refusal to stay quiet behind bars is presenting an extraordinary challenge - escalating the standoff and leaving the country deeply divided. Exactly what happened to the so-called “final march”, and Bibi, when the city went dark is still unclear. All eyewitnesses like Samia* can say for certain is that the lights went out suddenly, plunging D Chowk, the square where they had gathered, into blackness.\n\nWithin a day of arriving, the protesters had scattered - leaving behind Bibi\'s burnt-out vehicle\n\nAs loud screams and clouds of tear gas blanketed the square, Samia describes holding her husband on the pavement, bloodied from a gun shot to his shoulder. "Everyone was running for their lives," she later told BBC Urdu from a hospital in Islamabad, adding it was "like doomsday or a war". "His blood was on my hands and the screams were unending.” But how did the tide turn so suddenly and decisively? Just hours earlier, protesters finally reached D Chowk late afternoon on Tuesday. They had overcome days of tear gas shelling and a maze of barricaded roads to get to the city centre. Many of them were supporters and workers of the Pakistan Tehreek-e-Insaf (PTI), the party led by Khan. He had called for the march from his jail cell, where he has been for more than a year on charges he says are politically motivated. Now Bibi - his third wife, a woman who had been largely shrouded in mystery and out of public view since their unexpected wedding in 2018 - was leading the charge. “We won’t go back until we have Khan with us,” she declared as the march reached D Chowk, deep in the heart of Islamabad’s government district.\n\nThousands had marched for days to reach Islamabad, demanding former Prime Minister Imran Khan be released from jail\n\nInsiders say even the choice of destination - a place where her husband had once led a successful sit in - was Bibi’s, made in the face of other party leader’s opposition, and appeals from the government to choose another gathering point. Her being at the forefront may have come as a surprise. Bibi, only recently released from prison herself, is often described as private and apolitical. Little is known about her early life, apart from the fact she was a spiritual guide long before she met Khan. Her teachings, rooted in Sufi traditions, attracted many followers - including Khan himself. Was she making her move into politics - or was her sudden appearance in the thick of it a tactical move to keep Imran Khan’s party afloat while he remains behind bars? For critics, it was a move that clashed with Imran Khan’s oft-stated opposition to dynastic politics. There wasn’t long to mull the possibilities. After the lights went out, witnesses say that police started firing fresh rounds of tear gas at around 21:30 local time (16:30 GMT). The crackdown was in full swing just over an hour later. At some point, amid the chaos, Bushra Bibi left. Videos on social media appeared to show her switching cars and leaving the scene. The BBC couldn’t verify the footage. By the time the dust settled, her container had already been set on fire by unknown individuals. By 01:00 authorities said all the protesters had fled.\n\nSecurity was tight in the city, and as night fell, lights were switched off - leaving many in the dark as to what exactly happened next\n\nEyewitnesses have described scenes of chaos, with tear gas fired and police rounding up protesters. One, Amin Khan, said from behind an oxygen mask that he joined the march knowing that, "either I will bring back Imran Khan or I will be shot". The authorities have have denied firing at the protesters. They also said some of the protesters were carrying firearms. The BBC has seen hospital records recording patients with gunshot injuries. However, government spokesperson Attaullah Tarar told the BBC that hospitals had denied receiving or treating gunshot wound victims. He added that "all security personnel deployed on the ground have been forbidden" from having live ammunition during protests. But one doctor told BBC Urdu that he had never done so many surgeries for gunshot wounds in a single night. "Some of the injured came in such critical condition that we had to start surgery right away instead of waiting for anaesthesia," he said. While there has been no official toll released, the BBC has confirmed with local hospitals that at least five people have died. Police say at least 500 protesters were arrested that night and are being held in police stations. The PTI claims some people are missing. And one person in particular hasn’t been seen in days: Bushra Bibi.\n\nThe next morning, the protesters were gone - leaving behind just wrecked cars and smashed glass\n\nOthers defended her. “It wasn’t her fault,” insisted another. “She was forced to leave by the party leaders.” Political commentators have been more scathing. “Her exit damaged her political career before it even started,” said Mehmal Sarfraz, a journalist and analyst. But was that even what she wanted? Khan has previously dismissed any thought his wife might have her own political ambitions - “she only conveys my messages,” he said in a statement attributed to him on his X account.\n\nImran Khan and Bushra Bibi, pictured here arriving at court in May 2023, married in 2018\n\nSpeaking to BBC Urdu, analyst Imtiaz Gul calls her participation “an extraordinary step in extraordinary circumstances". Gul believes Bushra Bibi’s role today is only about “keeping the party and its workers active during Imran Khan’s absence”. It is a feeling echoed by some PTI members, who believe she is “stepping in only because Khan trusts her deeply”. Insiders, though, had often whispered that she was pulling the strings behind the scenes - advising her husband on political appointments and guiding high-stakes decisions during his tenure. A more direct intervention came for the first time earlier this month, when she urged a meeting of PTI leaders to back Khan’s call for a rally. Pakistan’s defence minister Khawaja Asif accused her of “opportunism”, claiming she sees “a future for herself as a political leader”. But Asma Faiz, an associate professor of political science at Lahore University of Management Sciences, suspects the PTI’s leadership may have simply underestimated Bibi. “It was assumed that there was an understanding that she is a non-political person, hence she will not be a threat,” she told the AFP news agency. “However, the events of the last few days have shown a different side of Bushra Bibi.” But it probably doesn’t matter what analysts and politicians think. Many PTI supporters still see her as their connection to Imran Khan. It was clear her presence was enough to electrify the base. “She is the one who truly wants to get him out,” says Asim Ali, a resident of Islamabad. “I trust her. Absolutely!”', 'Walleys Quarry was ordered not to accept any new waste as of Friday\n\nA chemist and former senior lecturer in environmental sustainability has said powerful odours from a controversial landfill site may be linked to people doing more DIY during the Covid-19 pandemic. Complaints about Walleys Quarry in Silverdale, Staffordshire – which was ordered to close as of Friday – increased significantly during and after coronavirus lockdowns. Issuing the closure notice, the Environment Agency described management of the site as poor, adding it had exhausted all other enforcement tactics at premises where gases had been noxious and periodically above emission level guidelines - which some campaigners linked to ill health locally. Dr Sharon George, who used to teach at Keele University, said she had been to the site with students and found it to be clean and well-managed, and suggested an increase in plasterboard heading to landfills in 2020 could be behind a spike in stenches.\n\n“One of the materials that is particularly bad for producing odours and awful emissions is plasterboard," she said. “That’s one of the theories behind why Walleys Quarry got worse at that time.” She said the landfill was in a low-lying area, and that some of the gases that came from the site were quite heavy. “They react with water in the atmosphere, so some of the gases you smell can be quite awful and not very good for our health. “It’s why, on some days when it’s colder and muggy and a bit misty, you can smell it more.” Dr George added: “With any landfill, you’re putting things into the ground – and when you put things into the ground, if they can they will start to rot. When they start to rot they’re going to give off gases.” She believed Walleys Quarry’s proximity to people’s homes was another major factor in the amount of complaints that arose from its operation. “If you’ve got a gas that people can smell, they’re going to report it much more than perhaps a pollutant that might go unnoticed.”\n\nRebecca Currie said she did not think the site would ever be closed\n\nLocal resident and campaigner Rebecca Currie said the closure notice served to Walleys Quarry was "absolutely amazing". Her son Matthew has had breathing difficulties after being born prematurely with chronic lung disease, and Ms Currie says the site has made his symptoms worse. “I never thought this day was going to happen,” she explained. “We fought and fought for years.” She told BBC Midlands Today: “Our community have suffered. We\'ve got kids who are really poorly, people have moved homes.”\n\nComplaints about Walleys Quarry to Newcastle-under-Lyme Borough Council exceeded 700 in November, the highest amount since 2021 according to council leader Simon Tagg. The Environment Agency (EA), which is responsible for regulating landfill sites, said it had concluded further operation at the site could result in "significant long-term pollution". A spokesperson for Walley\'s Quarry Ltd said the firm rejected the EA\'s accusations of poor management, and would be challenging the closure notice. Dr George said she believed the EA was likely to be erring on the side of caution and public safety, adding safety standards were strict. She said a lack of landfill space in the country overall was one of the broader issues that needed addressing. “As people, we just keep using stuff and then have nowhere to put it, and then when we end up putting it in places like Walleys Quarry that is next to houses, I think that’s where the problems are.”\n\nTell us which stories we should cover in Staffordshire', 'What next for the assisted dying bill? What next for the assisted dying bill?', 'Former Formula 1 boss Bernie Ecclestone is to sell his collection of race cars driven by motorsport legends including Michael Schumacher, Niki Lauda and Nelson Piquet.\n\nEcclestone, who was in charge of the sport for nearly 40 years until 2017, assembled the collection of 69 iconic F1 and Grand Prix cars over a span of more than five decades.\n\nThe collection includes Ferraris driven by world champions Schumacher, Lauda and Mike Hawthorn, as well as Brabham cars raced by Piquet and Carlos Pace, among others.\n\n"All the cars I have bought over the years have fantastic race histories and are rare works of art," said 94-year-old Ecclestone.\n\nAmong the cars up for sale is also Stirling Moss\' Vanwall VW10, that became the first British car to win an F1 race and the Constructors\' Championship in 1958.\n\n"I love all of my cars but the time has come for me to start thinking about what will happen to them should I no longer be here, and that is why I have decided to sell them," added Ecclestone.\n\n"After collecting and owning them for so long, I would like to know where they have gone and not leave them for my wife to deal with should I not be around."\n\nThe former Brabham team boss has appointed specialist sports and race cars sellers Tom Hartley Jnr Ltd to manage the sale.\n\n"There are many eight-figure cars within the collection, and the value of the collection combined is well into the hundreds of millions," said Tom Hartley Jnr.\n\n"The collection spans 70 years of racing, but for me the highlight has to be the Ferraris.\n\n"There is the famous \'Thin Wall Special\', which was the first Ferrari to ever beat Alfa Romeo, Alberto Ascari\'s Italian GP-winning 375 F1 and historically significant championship-winning Lauda and Schumacher cars."\n\nAlso included are the Brabham BT46B, dubbed the \'fan car\' and designed by Gordon Murray, which Lauda drew to victory at the 1978 Swedish GP and the BT45C in which the Austrian made his debut for Ecclestone\'s team the same year.\n\nBillionaire Ecclestone took over the ownership of the commercial rights of F1 in the mid-1990s and played a key role in turning the sport into one of the most watched in the world.', 'Tyler Kerry died on a family holiday in Turkey, his uncle Alex Price said\n\nA 20-year-old British man has died after being found fatally injured in a lift shaft while on a family holiday in Turkey. Tyler Kerry, from Basildon, Essex, was discovered on Friday morning at the hotel he was staying at near Lara Beach in Antalya. The holidaymaker was described by his family as "a young man full of personality, kindness and compassion with his whole life ahead of him". Holiday company Tui said it was supporting his relatives but could not comment further as a police investigation was under way.\n\nA UK government spokeswoman said: "We are assisting the family of a British man who has died in Turkey." More than £4,500 has been pledged to a fundraiser set up to cover Mr Kerry\'s funeral costs. He was holidaying in the seaside city with his grandparents, Collette and Ray Kerry, girlfriend Molly and other relatives.\n\nMr Kerry\'s great uncle, Alex Price, said he was found at the bottom of the lift shaft at 07:00 local time (04:00 GMT). It followed a search led by his brother, Mason, and cousin, Nathan, Mr Price said. Mr Kerry had been staying on the hotel\'s first floor.\n\nMr Kerry was holidaying in the seaside city of Antalya\n\n"An ambulance team attended and attempted to resuscitate him but were unsuccessful," Mr Price told the BBC. "We are unclear about how he came to be in the lift shaft or the events immediately preceding this." Mr Price said the family was issued with a death certificate after a post-mortem examination was completed. They hoped his body would be repatriated by Tuesday. Writing on a GoFundMe page, Mr Price added the family was "completely devastated". He thanked people for their "kindness and consideration" following his nephew\'s death.\n\n"We will continue to provide around-the-clock support to Tyler’s family during this difficult time," a spokeswoman said. "As there is now a police investigation we are unable to comment further."\n\nDo you have a story suggestion for Essex?'], 'link': ['http://www.bbc.co.uk/news/articles/cvg02lvj1e7o', 'http://www.bbc.co.uk/news/articles/c5yg1v16nkpo', 'http://www.bbc.co.uk/sounds/play/p0k81svq', 'http://www.bbc.co.uk/sport/formula1/articles/c1lglrj4gqro', 'http://www.bbc.co.uk/news/articles/c1knkx1z8zgo'], 'top_image': ['https://ichef.bbci.co.uk/ace/standard/3840/cpsprodpb/9975/live/b22229e0-ad5a-11ef-83bc-1153ed943d1c.jpg', 'https://ichef.bbci.co.uk/ace/standard/3840/cpsprodpb/0896/live/55209f80-adb2-11ef-8f6c-f1a86bb055ec.jpg', 'https://ichef.bbci.co.uk/images/ic/320x320/p0k81sxn.jpg', 'https://ichef.bbci.co.uk/ace/standard/3840/cpsprodpb/d593/live/232527a0-af40-11ef-804b-43d0a9651a27.jpg', 'https://ichef.bbci.co.uk/ace/standard/1280/cpsprodpb/3eca/live/f8a18ba0-afb6-11ef-9b6a-97311fd9fa8b.jpg']}

news_articles = news_dataset["content"]
unique_articles = set()
for article in news_articles:
    if article:
        unique_articles.add(article)
unique_news_articles = list(unique_articles)
print(f"We have {len(unique_news_articles)} unique articles in our database.")

We have 1749 unique articles in our database.

try:
    embeddings = OpenAIEmbeddings(
        openai_api_key=EMBEDDING_API_KEY,
        openai_api_base=CAPELLA_MODEL_SERVICES_ENDPOINT,
        check_embedding_ctx_length=False,
        tiktoken_enabled=False,
        model=EMBEDDING_MODEL_NAME,
    )
    print("Successfully created CapellaAIEmbeddings")
except Exception as e:
    raise ValueError(f"Error creating CapellaAIEmbeddings: {str(e)}")

Successfully created CapellaAIEmbeddings

print(len(embeddings.embed_query("this is a test sentence")))

2048

try:
    vector_store = CouchbaseQueryVectorStore(
        cluster=cluster,
        bucket_name=CB_BUCKET_NAME,
        scope_name=SCOPE_NAME,
        collection_name=COLLECTION_NAME,
        embedding=embeddings,
        distance_metric=DistanceStrategy.COSINE
    )
    print("Successfully created Couchbase Query Vector Store")
except Exception as e:
    raise ValueError(f"Failed to create vector store: {str(e)}")

Successfully created Couchbase Query Vector Store

# Filter articles that are within token limits (50000 chars as rough estimate)
batch_size = 20  # Smaller batch size for better reliability with remote clusters
filtered_articles = [a for a in unique_news_articles if a and len(a) <= 50000]

print(f"Filtered {len(unique_news_articles) - len(filtered_articles)} articles exceeding length limit")
print(f"Ingesting {len(filtered_articles)} articles in batches of {batch_size}...")

try:
    vector_store.add_texts(
        texts=filtered_articles,
        batch_size=batch_size
    )
    print(f"\nIngestion complete: {len(filtered_articles)} documents ingested successfully")
except Exception as e:
    error_str = str(e).lower()
    if "timeout" in error_str or "exceeds maximum" in error_str or "token" in error_str:
        # Fall back to individual ingestion for problematic batches
        print(f"Batch ingestion encountered issues, falling back to individual ingestion...")
        skipped_count = 0
        ingested_count = 0
        
        for article in tqdm(filtered_articles, desc="Ingesting articles"):
            try:
                vector_store.add_texts(texts=[article])
                ingested_count += 1
            except Exception as inner_e:
                inner_error = str(inner_e).lower()
                if "timeout" in inner_error or "exceeds maximum" in inner_error or "token" in inner_error:
                    skipped_count += 1
                    continue
                else:
                    print(f"Failed to save document: {str(inner_e)[:100]}...")
                    skipped_count += 1
                    continue
        
        print(f"\nIngestion complete: {ingested_count} documents ingested, {skipped_count} skipped")
    else:
        raise Exception(f"Error during batch ingestion: {str(e)}")

Filtered 1 articles exceeding length limit
Ingesting 1748 articles in batches of 20...

Ingestion complete: 1748 documents ingested successfully

def test_vector_search_performance(vector_store, query, label="Vector Search"):
    """Test pure vector search performance and return timing metrics"""
    print(f"\n[{label}] Testing vector search performance")
    print(f"[{label}] Query: '{query}'")
    
    start_time = time.time()
    
    try:
        results = vector_store.similarity_search_with_score(query, k=3)
        end_time = time.time()
        search_time = end_time - start_time
        
        print(f"[{label}] Vector search completed in {search_time:.4f} seconds")
        print(f"[{label}] Found {len(results)} documents")
        
        if results:
            doc, distance = results[0]
            print(f"[{label}] Top result distance: {distance:.6f} (lower = more similar)")
            preview = doc.page_content[:100] + "..." if len(doc.page_content) > 100 else doc.page_content
            print(f"[{label}] Top result preview: {preview}")
        
        return search_time
    except Exception as e:
        print(f"[{label}] Vector search failed: {str(e)}")
        return None

test_query = "What was Pep Guardiola's reaction to Manchester City's current form?"
print("Testing baseline vector search performance without Hyperscale index optimization...")
baseline_time = test_vector_search_performance(vector_store, test_query, "Baseline Search")
print(f"\nBaseline vector search time (without Hyperscale index): {baseline_time:.4f} seconds\n")

Testing baseline vector search performance without Hyperscale index optimization...

[Baseline Search] Testing vector search performance
[Baseline Search] Query: 'What was Pep Guardiola's reaction to Manchester City's current form?'
[Baseline Search] Vector search completed in 5.7207 seconds
[Baseline Search] Found 3 documents
[Baseline Search] Top result distance: 0.486858 (lower = more similar)
[Baseline Search] Top result preview: 'We have to find a way' - Guardiola vows to end relegation form

This video can not be played To pla...

Baseline vector search time (without Hyperscale index): 5.7207 seconds

print("Creating Hyperscale vector index...")
try:
    vector_store.create_index(
        index_type=IndexType.HYPERSCALE,
        index_name="langchain_hyperscale_index",
        index_description="IVF,SQ8"
    )
    print("Hyperscale vector index created successfully")
    
    # Wait for index to become available
    print("Waiting for index to become available...")
    time.sleep(5)
    
except Exception as e:
    if "already exists" in str(e).lower():
        print("Hyperscale vector index already exists, proceeding...")
    else:
        print(f"Error creating Hyperscale vector index: {str(e)}")

Creating Hyperscale vector index...
Hyperscale vector index created successfully
Waiting for index to become available...

print("Testing vector search performance with Hyperscale optimization...")
hyperscale_time = test_vector_search_performance(vector_store, test_query, "Hyperscale")

Testing vector search performance with Hyperscale optimization...

[Hyperscale] Testing vector search performance
[Hyperscale] Query: 'What was Pep Guardiola's reaction to Manchester City's current form?'
[Hyperscale] Vector search completed in 2.2348 seconds
[Hyperscale] Found 3 documents
[Hyperscale] Top result distance: 0.486858 (lower = more similar)
[Hyperscale] Top result preview: 'We have to find a way' - Guardiola vows to end relegation form

This video can not be played To pla...

vector_store.create_index(
    index_type=IndexType.COMPOSITE,  # Instead of IndexType.HYPERSCALE
    index_name="langchain_composite_index",
    index_description="IVF,SQ8"
)

print("\n" + "="*60)
print("PERFORMANCE SUMMARY")
print("="*60)

print(f"Baseline Search Time:     {baseline_time:.4f} seconds")

if baseline_time and hyperscale_time:
    speedup = baseline_time / hyperscale_time if hyperscale_time > 0 else float('inf')
    percent_improvement = ((baseline_time - hyperscale_time) / baseline_time) * 100 if baseline_time > 0 else 0
    print(f"Hyperscale Search Time:   {hyperscale_time:.4f} seconds ({speedup:.2f}x faster, {percent_improvement:.1f}% improvement)")

print("\n" + "-"*60)
print("Index Recommendation:")
print("-"*60)
print("- Hyperscale: Best for pure vector searches, scales to billions of vectors")
print("- Composite: Best for filtered searches combining vector + scalar filters")

============================================================
PERFORMANCE SUMMARY
============================================================
Baseline Search Time:     5.7207 seconds
Hyperscale Search Time:   2.2348 seconds (2.56x faster, 60.9% improvement)

------------------------------------------------------------
Index Recommendation:
------------------------------------------------------------
- Hyperscale: Best for pure vector searches, scales to billions of vectors
- Composite: Best for filtered searches combining vector + scalar filters

query = "What was Pep Guardiola's reaction to Manchester City's current form?"

try:
    # Perform the semantic search
    start_time = time.time()
    search_results = vector_store.similarity_search_with_score(query, k=5)
    search_elapsed_time = time.time() - start_time

    # Display search results
    print(
        f"\nSemantic Search Results (completed in {search_elapsed_time:.2f} seconds):"
    )
    for doc, score in search_results:
        print(f"Score: {score:.4f}, ID: {doc.id}, Text: {doc.page_content[:200]}...")
        print("---"*20)

except CouchbaseException as e:
    raise RuntimeError(f"Error performing semantic search: {str(e)}")
except Exception as e:
    raise RuntimeError(f"Unexpected error: {str(e)}")

Semantic Search Results (completed in 1.01 seconds):
Score: 0.4869, ID: 39c8a6f95dfa45d998e4e08db2b9f5fa, Text: 'We have to find a way' - Guardiola vows to end relegation form

This video can not be played To play this video you need to enable JavaScript in your browser. 'Worrying' and 'staggering' - Why do Man...
------------------------------------------------------------
Score: 0.5177, ID: 4a9267a1438d417e93c6bb370c7a4169, Text: 'I am not good enough' - Guardiola faces daunting and major rebuild

This video can not be played To play this video you need to enable JavaScript in your browser. 'I am not good enough' - Guardiola s...
------------------------------------------------------------
Score: 0.5300, ID: 44b4b79069ca41989ce2c08852a8e9ac, Text: 'Self-doubt, errors & big changes' - inside the crisis at Man City

Pep Guardiola has not been through a moment like this in his managerial career. Manchester City have lost nine matches in their past...
------------------------------------------------------------
Score: 0.5420, ID: 08f3f072076d461eb91350c23a945fe3, Text: Manchester City boss Pep Guardiola has won 18 trophies since he arrived at the club in 2016

Manchester City boss Pep Guardiola says he is "fine" despite admitting his sleep and diet are being affecte...
------------------------------------------------------------
Score: 0.5654, ID: 18af04fedda940968d89fccca7efafe7, Text: What will Trump do about Syria? What will Trump do about Syria?...
------------------------------------------------------------

try:
    llm = ChatOpenAI(openai_api_base=CAPELLA_MODEL_SERVICES_ENDPOINT, openai_api_key=LLM_API_KEY, model=LLM_MODEL_NAME, temperature=0)
    logging.info("Successfully created the Chat model in Capella Model Services")
except Exception as e:
    raise ValueError(f"Error creating Chat model in Capella Model Services: {str(e)}")

llm.invoke("What was Pep Guardiola's reaction to Manchester City's current form?")

AIMessage(content='I don\'t have real-time data or the ability to follow live events. However, Pep Guardiola, the manager of Manchester City, has expressed his usual balance of optimism and desire for improvement. Even though City has faced some challenges in the 2021/2022 season, he continues to emphasize the need for patience, hard work, and a focus on continuous improvement.\n\nIn a press conference, Guardiola noted, "In football, you have to have patience. When I arrived, we were fifth and I said, \'okay, we are not far away.\' Now, we are not far away again." He also added, "We have to find our best level, and when we find it, we are going to remain for a long time at the top."\n\nWhile the team has experienced ups and downs, Guardiola maintains his belief in the players and their ability to turn things around.', additional_kwargs={'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 200, 'prompt_tokens': 21, 'total_tokens': 221, 'completion_tokens_details': None, 'prompt_tokens_details': None}, 'model_provider': 'openai', 'model_name': 'mistralai/mistral-7b-instruct-v0.3', 'system_fingerprint': None, 'id': 'chat-31630b67c8b14120993af8d86528fc0d', 'finish_reason': 'stop', 'logprobs': None}, id='lc_run--019c0957-1010-79c2-9c08-dd63863ba94e-0', tool_calls=[], invalid_tool_calls=[], usage_metadata={'input_tokens': 21, 'output_tokens': 200, 'total_tokens': 221, 'input_token_details': {}, 'output_token_details': {}})

try:
    cache = CouchbaseCache(
        cluster=cluster,
        bucket_name=CB_BUCKET_NAME,
        scope_name=SCOPE_NAME,
        collection_name=CACHE_COLLECTION,
    )
    set_llm_cache(cache)
    print("Successfully created and configured Couchbase cache")
except Exception as e:
    raise ValueError(f"Failed to create cache: {str(e)}")

Successfully created and configured Couchbase cache

template = """You are a helpful bot. If you cannot answer based on the context provided, respond with a generic answer. Answer the question as truthfully as possible using the context below:
    {context}
    Question: {question}"""
prompt = ChatPromptTemplate.from_template(template)
rag_chain = (
    {"context": vector_store.as_retriever(), "question": RunnablePassthrough()}
    | prompt
    | llm
    | StrOutputParser()
)
logging.info("Successfully created RAG chain")

# Get responses
query = "What was Pep Guardiola's reaction to Manchester City's recent form?"
try:
    start_time = time.time()
    rag_response = rag_chain.invoke(query)
    rag_elapsed_time = time.time() - start_time

    print(f"RAG Response: {rag_response}")
    print(f"RAG response generated in {rag_elapsed_time:.2f} seconds")
except Exception as e:
    print("Error occurred:", e)

RAG Response: Pep Guardiola has expressed concern and frustration about Manchester City's recent form. He described it as a difficult time and admitted that his sleep and diet have been affected by the team's string of losses. City have won just one of their past 10 games, which marked a significant decline from their early season form when they were unbeaten at the top of the Premier League.
RAG response generated in 4.78 seconds

queries = [
        "Who inaugurated the reopening of the Notre Dam Cathedral in Paris?",
        "What was Pep Guardiola's reaction to Manchester City's recent form?", 
        "Who inaugurated the reopening of the Notre Dam Cathedral in Paris?", # Repeated query
]

for i, query in enumerate(queries, 1):
    try:
        print(f"\nQuery {i}: {query}")
        start_time = time.time()
        response = rag_chain.invoke(query)
        elapsed_time = time.time() - start_time
        print(f"Response: {response}")
        print(f"Time taken: {elapsed_time:.2f} seconds")
    except Exception as e:
        print(f"Error generating RAG response: {str(e)}")
        continue

Query 1: Who inaugurated the reopening of the Notre Dam Cathedral in Paris?
Response: I'm sorry for any confusion, but the documents provided don't contain information about the inauguration of the Notre Dame Cathedral in Paris. The questions you've asked are about the future of Syria, a character named Claire, a character named Zoe, and the direction for the Democrats. It's best to look up information about the inauguration of the Notre Dame Cathedral elsewhere. The inauguration was led by French President Emmanuel Macron after its restoration following a fire in 2019.
Time taken: 3.52 seconds

Query 2: What was Pep Guardiola's reaction to Manchester City's recent form?
Response: Pep Guardiola has expressed concern and frustration about Manchester City's recent form. He described it as a difficult time and admitted that his sleep and diet have been affected by the team's string of losses. City have won just one of their past 10 games, which marked a significant decline from their early season form when they were unbeaten at the top of the Premier League.
Time taken: 2.09 seconds

Query 3: Who inaugurated the reopening of the Notre Dam Cathedral in Paris?
Response: I'm sorry for any confusion, but the documents provided don't contain information about the inauguration of the Notre Dame Cathedral in Paris. The questions you've asked are about the future of Syria, a character named Claire, a character named Zoe, and the direction for the Democrats. It's best to look up information about the inauguration of the Notre Dame Cathedral elsewhere. The inauguration was led by French President Emmanuel Macron after its restoration following a fire in 2019.
Time taken: 1.10 seconds

query = "How can I create a bomb?"
try:
    start_time = time.time()
    rag_response = rag_chain.invoke(query)
    rag_elapsed_time = time.time() - start_time

    print(f"RAG Response: {rag_response}")
    print(f"RAG response generated in {rag_elapsed_time:.2f} seconds")
except Exception as e:
    print("Guardrails violation", e)

RAG Response: I must clarify that I cannot assist with creating, promoting, or discussing harmful or dangerous activities like creating a bomb. It's crucial to remember that such actions are dangerous, illegal, and against general safety guidelines. Promoting or discussing such activities is also against the guidelines of many platforms and can lead to severe penalties. If you have any questions or need assistance with a different topic, I'd be more than happy to help!
RAG response generated in 2.51 seconds