I’m building a chatbot RAG using HuggingFace, Mistral, LangChain and Pinecone.
I have a Python Script to watch changes in my MongoDB collection and send the data to Pinecone as a vector.
import os
from pymongo import MongoClient
from pinecone import Pinecone, ServerlessSpec
from pymongo.errors import OperationFailure
from sentence_transformers import SentenceTransformer, util
from certifi import where # Import certifi library
# mongodb stuff
client = MongoClient(
"my-mongodb-uri",
tls=True, # Enable TLS encryption
tlsAllowInvalidCertificates=False, # Don't allow invalid certificates
tlsCAFile=where() # Use certifi library for CA bundle
)
db = client['test']
collection = db['reflections']
# Pinecone initialization
pc = Pinecone(api_key='my-pinecone-key')
index = pc.Index("langchain-demo")
# transformer stuff
model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
test_vector = model.encode("This is a test string")
print("Dimension of test vector:", test_vector.shape)
# Watch for changes
try:
cursor = collection.watch()
for change in cursor:
print("Change detected:", change)
if change['operationType'] == 'insert':
document = change['fullDocument']
vector = model.encode(document['content']).tolist()
print("Extracted Vector:", vector)
# Extract document ID from ObjectId
document_id = str(document['_id'])
user_id = str(document['user'])
created_at = document['createdAt']
# Wrap upsert call with empty vector check
if vector: # Check if vector is not empty
metadata = {'user_id': user_id, 'created_at': str(created_at)}
index.upsert([(document_id, vector, metadata)])
elif change['operationType'] == 'update':
document_id = str(change['documentKey']['_id'])
updated_fields = change['updateDescription']['updatedFields']
if 'content' in updated_fields:
vector = model.encode(updated_fields['content']).tolist()
index.upsert([(document_id, vector, metadata)])
elif change['operationType'] == 'delete':
document_id = str(change['documentKey']['_id'])
index.delete(ids=[document_id])
except OperationFailure as e:
print("Error watching collection:", e)
except Exception as e:
print("An error occurred:", e)
And this is working fine, here a entry from my Pinecone Index:
2
SCORE
0.0179
ID
665882f313b3c25b81fe46f7
VALUES
0.0780179054, 0.0113870166, -0.118430212, 0.0226640049, 0.00780098559, -0.0503292121, -0.0238182824, 0.0469664969, -0.0270168502, 0.0369489267, 0.0325907134, -0.0476229116, -0.0786545724, 0.024753511, 0.027189346, -0.0125029637, 0.00541313691, -0.0757853836, 0.0212387145, -0.0110286493, 0.0117090391, -0.0193786472, 0.0253583211, 0.033223819, -0.047959242, -0.0769486949, -0.0650763139, 0.0521994196, -0.0230765603, -0.0348826386, 0.101876184, 0.0702511, -0.00723150745, -0.000215011096, 0.0366995223, -0.0220702309, 0.0689907297, -0.00627420563, 0.00119058753, -0.0264558308, 0.0431874134, -0.010541168, -0.0586702935, -0.0786846578, 0.0561939925, -0.0782630071, -0.0292404443, 0.0599261038, 0.106215701, 0.00162592565, 0.00396974338, -0.084600091, -0.108621657, 0.0980778411, 0.0299655739, 0.128577992, -0.0200762413, -0.0653520674, 0.0102492804, 0.0322388411, 0.0313118957, 0.0121116294, -0.0409101136, 0.0448457114, -0.0308046602, -0.0109536722, -0.0264064465, -0.0215834882, 0.0305376686, -0.0735122, 0.0205106437, 0.0107715921, -0.0321323, -0.0110485516, 0.0149518345, 0.154741883, -0.0143986866, -0.0952939615, 0.0817126408, 0.0272761323, -0.118013233, -0.0656163543, 0.0275144801, -0.0715595558, 0.00360014034, -0.0505540147, 0.0993294567, -0.0181424897, -0.0340541303, -0.0191219747, 0.0576984696, -0.016041344, -0.0117336037, 0.0854231268, 0.000578647654, 0.054585509, 0.0607333779, 0.0251228772, 0.0586750954, 0.0542409495, -0.0147840325, 0.0171087608, 0.0243709181, 0.0218990557, -0.0393281505, 0.0587186627, 0.0294246785, -0.0300889853, -0.104504265, 0.01126011, 0.0200448446, 0.0346874595, -0.0424731597, -0.0501565561, -0.0336206853, 0.0125492243, -0.0602271, -0.0255396832, -0.0807785168, 0.0296369921, 0.0213591736, 0.0517560728, -0.0236208886, -0.00668002106, 0.0482311361, 0.00484784134, -0.00671314076, 2.48858068e-33, 0.13539581, -0.0779394507, 0.0531481355, -0.0325026, 0.0539878421, 0.0422413386, 0.00721841305, 0.0636715069, -0.0271209199, 0.0237933304, -0.012324837, 0.0318006687, -0.00415049167, -0.0791502222, 0.00476903608, 0.0398657173, -0.0222511888, 0.00637130346, -0.026622, 0.0662136674, 0.0718791559, -0.0128180161, -0.00474599516, -0.0390690714, 0.0125142019, 0.050622154, -0.0718687624, -0.014537137, -0.0000649832582, 0.0659983233, -0.0874705464, -0.0598177947, -0.0425723866, 0.116614014, 0.00950913411, 0.00521008205, 0.00299354899, -0.0490386747, -0.101944029, -0.00193977414, 0.0737567469, 0.0489828475, 0.0479842573, -0.0121582411, -0.0683459863, 0.0465017371, 0.0244375356, -0.0415155031, 0.0733279511, 0.0411045067, -0.0990792513, -0.0168382581, -0.128719345, 0.0162787139, 0.00180200755, 0.0361118391, 0.00714902952, 0.0225948617, 0.0598230809, -0.027883, -0.0634493604, 0.01690959, -0.00616647629, 0.102524318, -0.00962299388, -0.00800243765, -0.0349691175, -0.067561388, 0.00328797475, 0.038413655, -0.0277767256, 0.0493801422, -0.0626680329, 0.0100066448, 0.0245917551, -0.0696575642, 0.0435989201, -0.0336911827, -0.11178454, 0.0231342558, 0.0650513396, -0.0489158109, -0.118925206, 0.0456594117, -0.000165144767, 0.0263350084, -0.0126295025, -0.00819321815, 0.02433425, -0.130400553, 0.0154193891, 0.104591407, 0.0529140271, -0.0677612349, 0.006422868, -3.15768235e-33, 0.0266072527, -0.0650565699, 0.0751486719, 0.0352391638, 0.0913304538, -0.0166126471, 0.0618819185, 0.0104150325, -0.0678095892, -0.0207110438, 0.0114265652, -0.0825057179, -0.0197282247, -0.0340087563, -0.0661914572, -0.0287549552, -0.00654957304, -0.114685677, -0.00108200416, 0.032330893, -0.0842154548, 0.0676763728, 0.0241372753, 0.0217358116, 0.00449138787, -0.110978812, -0.00896465, -0.113323905, -0.0244096816, 0.0437684767, 0.0635139272, 0.0932535827, -0.0722304285, 0.0176913701, -0.0259954911, 0.0359196104, 0.0873655, -0.0387332886, 0.0215564184, 0.087338239, 0.0205500964, 0.0888643935, -0.0694097877, -0.0502204783, 0.0232924949, 0.0244588424, -0.0220373627, 0.0513052084, 0.0780876428, -0.0470482521, -0.0335381292, -0.012535166, 0.0251501985, -0.0287306085, 0.0485889763, -0.0687309802, 0.0517236702, -0.0322456844, -0.00322602759, 0.0309814233, 0.0314734243, -0.00763608702, -0.0108202593, -0.0168912616, 0.0146153346, 0.0058498932, -0.0463481061, -0.0149578694, 0.00604433473, 0.0156758986, -0.00293513224, -0.0301138815, -0.0343872979, 0.0298203304, 0.0256143659, -0.0255653039, -0.0625488907, -0.0271613039, 0.0419909954, 0.0695206523, 0.062871322, -0.034802638, 0.0640893504, 0.0120009324, 0.0246663559, -0.0750950128, 0.00124487793, 0.0673942715, -0.133396164, 0.0429567732, -0.00271692313, -0.00318611646, -0.0404472388, 0.0490305126, 0.0105391946, -1.60218168e-8, -0.0698085204, 0.000768667669, -0.00646897545, 0.0643798038, -0.0233389419, 0.00319286506, 0.0344442315, 0.00670952629, 0.0701468587, 0.0244643614, 0.0203008968, 0.0470311418, -0.0328549594, 0.0701879337, -0.03013069, 0.0344369523, 0.0444342941, 0.0185571574, 0.0324901864, 0.028787395, -0.00257497164, 0.016713731, 0.00826486666, -0.108173572, 0.0234305598, 0.0513667837, 0.0751283243, 0.0887183845, 0.00413105683, -0.00771792512, -0.00882443134, 0.010960429, 0.0386422388, -0.0143630169, 0.0658110827, 0.0273497198, 0.0315157361, 0.0515595078, -0.0557875521, 0.0250054803, -0.00490543433, 0.0140227228, 0.0185526628, -0.063243337, -0.0253285952, -0.0361511707, 0.0092082452, 0.109378465, -0.0141137447, -0.0900633484, 0.0360222086, -0.0720594451, 0.0374338441, -0.0112864282, 0.0303963758, 0.0577182584, -0.0215295721, -0.0536189973, -0.0685039461, -0.0390378311, 0.0779438391, -0.070971, -0.015317292, -0.0375189707
METADATA
created_at: "2024-05-30 13:45:23.389000"
user_id: "65d8937f6408bf2c0ca8d264"
The problem is when I try to ask something to my chatbog. Here is my code:
from transformers import AutoTokenizer
from pinecone import Pinecone, ServerlessSpec
from dotenv import load_dotenv
import os
from langchain_community.embeddings import HuggingFaceEmbeddings
from langchain_community.vectorstores import Pinecone as PineconeStore
from langchain_huggingface import HuggingFaceEndpoint
from langchain.prompts import PromptTemplate
from langchain.schema.runnable import RunnablePassthrough
from langchain.schema.output_parser import StrOutputParser
class ChatBot():
def __init__(self):
load_dotenv()
self.pc = Pinecone(api_key=os.getenv("PINECONE_API_KEY"))
self.index_name = "langchain-demo"
self.index = self.pc.Index(self.index_name)
# Initialize tokenizer for the language model
self.tokenizer = AutoTokenizer.from_pretrained('mistralai/Mixtral-8x7B-Instruct-v0.1')
# Initialize embeddings and Pinecone store for document retrieval
self.embeddings = HuggingFaceEmbeddings()
self.docsearch = PineconeStore.from_existing_index(self.index_name, self.embeddings)
# Setup LLM with tokenizer
self.llm = HuggingFaceEndpoint(
repo_id='mistralai/Mixtral-8x7B-Instruct-v0.1',
temperature=0.8, top_p=0.8, top_k=50,
huggingfacehub_api_token=os.getenv('HUGGINGFACE_API_KEY')
)
# Define the prompt template
self.template = PromptTemplate(template="""
You are a seer. These Humans will ask you questions about their life.
Use the following piece of context to answer the question.
If you don't know the answer, just say you don't know.
You answer with short and concise answers, no longer than 2 sentences.
Context: {context}
Question: {question}
Answer:
""", input_variables=["context", "question"])
self.rag_chain = (
{"context": self.docsearch.as_retriever(), "question": RunnablePassthrough()}
| self.template
| self.llm
| StrOutputParser()
)
def get_user_data_from_pinecone(self, user_id):
results = self.index.query(
vector=[0]*384,
filter={"user_id": user_id},
top_k=10,
include_metadata=True,
include_values=True
)
return results
# Usage example outside the class
bot = ChatBot()
user_id = input("Enter your user ID: ")
user_data = bot.get_user_data_from_pinecone(user_id)
question = input("Ask me anything: ")
# Tokenize the question
inputs = bot.tokenizer(question, return_tensors="pt")
result = bot.rag_chain.invoke(question)
print("AI's response:", result)
Here is the ERROR I received:
HTTP response body: {"code":3,"message":"Vector dimension 768 does not match the dimension of the index 384","details":[]}
My Pinecone Configuration:
METRIC cosine DIMENSIONS 384 CLOUD aws AWS REGION us-east-1 TYPE Serverless
2 posts - 2 participants