Chat with MySQL Database with Python | LangChain Tutorial

[@alejandro_ao]

🔥Join the AI Engineer Bootcamp: Hey there! The second edition of the AI Engineering Cohort is starting soon! 🚀 - Learn with step-by-step lessons and exercises - Join a community of like-minded and amazing people - I'll be there to personally answer all your questions 🤓 - The spots are limited since I'll be directly interacting with you You can join the waitlist now 👉 course.alejandro-ao.com/ Cheers!

[@chercm]

I am Not able to get the schema of the db

[@palanikumarmsc]

Thank you for this wonderful tutorial. Using this tutorial, I integrated Chat with database with MySQL, MS SQL, PostgreSQL, and MongoDB using HuggingFace's mistralai/Mistral-7B-Instruct-v0.3.

[@davidtindell950]

Hi, I reviewed this "Chat with MySQL DB" tutorial yet again and decided to try a more difficult SQL query: "determine the most popular artist in the database based upon total sales.". Of course, I manually ran the full Select -- with three table joins -- to make sure that this new query would work and produce the correct answer(s). To my surprise, the "natural language query" was properly processed by my modified version of your program and produced the correct response: " Iron Maiden with total sales of $138.60 " ! To further test the program, I changed the question to "top three most popular artists". The correct result was again returned: "Iron Maiden, U2, and Metallica" ! Glad to see 'U2' near the top ! Since "langchain-openai" is only at version 0.0.8 and "SQLDatabase" at 0.0.26, we may expect even more NLP Query improvements in the near future [i.e., if 'Altman' & 'Musk' do not mess everything up for all of us !?!]. P.S. Looking forward to the next MySQL vid(s) that you post !

[@EricLofland]

I got an error when I tried your first query - the query was correct (validated in database) but it was prepended by "sql" like this: [SQL: ```sql SELECT a.Name AS Artist, SUM(il.UnitPrice * il.Quantity) AS TotalSales FROM Artist a JOIN Album al ON a.ArtistId = al.ArtistId JOIN Track t ON al.AlbumId = t.AlbumId JOIN InvoiceLine il ON t.TrackId = il.TrackId JOIN Invoice i ON il.InvoiceId = i.InvoiceId GROUP BY a.Name ORDER BY TotalSales DESC LIMIT 1; ```]

[@davidtindell950]

@@EricLofland Thank You! For the feedback. The natural language query worked well for me and ChatGPT4 validated the SQL Query. I have since moved on to testing SQLite and also saving query vectors in ChromaDB. Later, I will try to re-check and reproduce the MySQL Database query and compare it to your results.

[@davidtindell950]

​@@EricLofland I reset my laptop for my extension of Alejandro's "Chat with MySQL" Python program. It ran as before and produced both the SQL and Natural Language Query. SQL: run_query("select artist.Name AS ArtistName, COUNT(*) AS TotalSales from \ invoiceline join track on invoiceline.TrackId = track.TrackId \ join album on track.AlbumId = album.AlbumId \ join artist on album.ArtistId = artist.ArtistId \ group by artist.Name order by TotalSales desc limit 3;") NLQ: user_question = 'determine the top three most popular artists in the database based upon total sales.' BOTH Results were very similar: "'The top three most popular artists in the database based on total sales are Iron Maiden with $138.60, U2 with $105.93, and Metallica with $90.09.". Further, I researched any conditions under which "sql" would be prepended to the SELECT statement. I did NOT find any examples of this artifact, however, I did find a good very recent "Medium" article on this subject by " Senthil E " at " levelup.gitconnected.com/llms-meet-sql-revolutionizing-data-querying-with-natural-language-processing-52487337f043 ". As we say "Hope This Helps!" and thanks again for your detailed feedback.

[@warrenmarkham8891]

@@davidtindell950 Are you writing up any of your experiments/tests? I'd be interested in seeing the caching of queries and responses into a vector database.

[@davidtindell950]

​@@warrenmarkham8891 Hi, I expect to write a new "Medium" article fairly soon, however, I am still currently continuing my R&D. In addition to Alejandro's excellent tutorials, I have found another good tutorial that includes the employment of PyTorch for fast processing of large vector databases: " Maximize ChromaDB Embedding Vectorization Speed with NVidia CUDA GPU and Python Multiprocessing " " Johnny Code " " kzbin.info/www/bejne/bXfZlaqtq9alepY " and " kzbin.info/www/bejne/bXfZlaqtq9alepYsi=a18-dKxTYk2UvRMT ". Also, there are several good current "Medium" articles available on this research subject.

[@imranonthenet]

I really love your tutorials, you are teaching us to create such powerful AI tools in Python that are really useful. I'm surprised that you have only 26K subscribers, you should have millions.

[@alejandro_ao]

thank you man! i hope i will get there someday!

[@davidtindell950]

Thanks for including MySQL and not just SQLite.

[@alejandro_ao]

sure :)

[@jatinnandwani6678]

Thanks Alejandro!

[@alejandro_ao]

Thank you man, you are amazing

[@p80mod]

THANK YOU SO MUCH ALEJANDRO! I've struggled quite a bit for the following reasons: 1. I use Azure Open AI instead of Open AI, which is a little different. 2. GPT-4o returned a wordy answer ("to answer that question, you could use the following query...") from the SQL chain instead of query only, and that couldn't be passed to the full chain - had to work with that. 3. Had to reinstall several LangChain libraries. Nevertheless at the end it works beautifully, answering questions based on our MSSQL database. This video was a tremendous help. Thank you!

[@1sanak]

Nice, looking forward to part 2!

[@alejandro_ao]

Coming soon! 😎

[@atagymx]

Thank you so much for this Tutorial, you have no idea how much i have been struggling on some basic things like ports or pip installing and etc. and you have showed ALL the STEPS unlike the other videos/channels, i really appreciate it. I finally could understood and made an AI Project thanks to you, keep up the good work man!

[@alejandro_ao]

i'm very glad to hear you got this working! great job man! i'll keep posting more tutorials here :)

[@madhutera298]

Thanks!

[@madhutera298]

Hi - how does this work when the response returns table data - example - show me top 10 artists by song streaming count?

[@alejandro_ao]

hey there! thank you so much for the tip!! it totally would work. the results are always a table actually. what happens is that the LLM receives a table-like prompt and reads it as though it were simple text. so in this case, your LLM would receive the table in the prompt and return something like "the top 10 artists are...." and it may even give you more details depending on your initial instructions :)

[@funmiemore194]

First time here and I'm glad I gound your channel.Thanks for sharing!

[@alejandro_ao]

hey there! welcome to the channel :) very happy to have you here :)

[@funmiemore194]

@@alejandro_ao Thanks!!

[@krisograbek]

Loving this video, Alejandro! 2 things I'd like to add: 1. I removed the {schema} part from the full_chain prompt and it works great. Only the sql_chain needs schema (to produce the sql query). 2. Your website is down :( Thanks for explaining every bit of your code so well!

[@dgm1949]

Thank you for your videos. As a subscriber to your channel, I look forward to each new one. I would like to make a comment, and perhaps a suggestion for a future video. As a Finance Manager for the last 40+ years, I have come to find these three areas important as it relates to the retrieval of information. What every office need is a way to search: 1) URL's , EXCEL, and PDF on the internet. 2) EXCEL and CSV files locally. (and Securely) 3) PDF and DOC documents locally. (and Securely) And nowadays, you could never get a NON GUI program adopted by the office staff. And of course, all three of the search types would be incorporated into the same GUI. Python based program would be the preferred language. OLLAMA based. NO DOCKER. No wrapper programs like streamlit, etc. Thanks for your time, and keep up the good work.

[@alejandro_ao]

Hey there, thanks for following the channel and for your suggestions! I see what you mean and agree that in order to get an app adopted internally, it should be very straightforward and easy to use. However, I don't see why it shouldn't use streamlit? Streamlit is just a way to build the GUI in a few lines of code. And if what you are interested in is the privacy, you can totally host it internally and have your data never leave your network.

[@shreyasb.s3819]

Really wonderful explanation and presentation.. Each and every line of code explanation is mind bowling.. I liked it❤ thank you so much

[@amitabhranjan9668]

Thank you so much for this. It worked flawlessly

[@alejandro_ao]

thanks! that's great! keep it up 💪

[@tannerdio333]

Dude, incredible tutorial, right on the money for what i needed.

[@zhiouzhu202]

Hi, i have a question that, i have created one model by myself and i want to use it for communication with lanchain how can i do that? I have tried to change the llm = OpenAI() to the path that point to my model directory but its doesn't work.

[@JayasuriyaM-z8v]

Thanks mate.is that allows Executing the CRUD opeartions in DB?

[@alejandro_ao]

absolutely. but be careful about allowing your LLM to perform write operations. you probably want a human in the loop to validate the queries before they are executed

[@_deepak__jangra]

@@alejandro_ao or you can have the readonly access of db

[@SanjayRoy-vz5ih]

Have done it with SAP Hana DB 6 month back..issue related hallucinations are faced and token size limit is also a constraint with open ai GPT 3.5 turbo

[@kaiser_the_emperor]

Did you make it work at the end? Or was not worth the struggle?

[@SanjayRoy-vz5ih]

@@kaiser_the_emperor Not much work done on that further but of course you can use combination of SQL agent and combinations of prompt techniques but the issues is different as you SAP would not support or recommend working directly with SQL tables but I would still try it as Q&A bot simply as an "art of possible" solution...I am now trying to do the same using combination of OData API and through BTP using function calls and agent architecture

[@adnank4980]

Love your videos, started watching all your langchain and it really has helped me and I wanted to say thanks. I would also like to see the use of agents if it isnt too much to ask

[@alejandro_ao]

hey there! thank you for telling me this :) keep it up and keep learning 🚀 i'll bring up agents here very soon!

[@AIWALABRO]

can you tell me at timestamp 14:29 what is grep SQL, i confused when I was doing , it shows it not recognizing

[@alejandro_ao]

hey there, that's just to only return the lines that contain the string "sql" when doing 'pip freeze'. otherwise i would get the huge list of all the packages installed. 'grep' is a unix command that allows you to filter the output text and return only the lines that contain the passed string 👍

[@victorchrist9899]

for the GUI, what tool would you suggest one can use to return a table, just like in mysql

[@msssouza2]

Hi Alejandro. Great post! It helped me a lot. I was trying to find a Gemini alternative to a solution that I learned from a Udemy course, using LangChain and OpenAI Agents to access a SQLite database and pass the results to the OpenAI LLM. I searched for days and found nothing, until I saw your video. Now my code is running and I can see many possibilities for accessing enterprise databases to enable users to obtain results using generative AI. Thank you and greetings from Brazil.

[@anismairi865]

When i write the code in py file, the schema variable in full_chain function s returning an error (it expect dict type and get_schema return str), do you have any idea on how to fix it ? i've checked langchain doc + you article but i still cant find a solution... thanks for all the tutorials i've learned a lot, keep going !

[@justinchang3573]

Having the same issue

[@BrandonFoltz]

Fabulous!

[@alejandro_ao]

hey Brandon! thanks!

[@heaton922]

Love to watch your tutorials. It's very details.

[@alejandro_ao]

thanks! keep it up!

[@abhishekbourai1832]

Thanks for such amazing resource, Alejandro.. i am getting this error: attributeerror : dict object has no attribute get_table_info.. when i try to invoke chain

[@alejandro_ao]

seems to me like your database instance is not being created. try logging the type of your SQL client to see if it was actually defined

[@mazinzain7121]

I love your content, thanks for all your efforts ❤

[@alejandro_ao]

i appreciate it! let me know what you want to see next

[@tanzeelmohammed9157]

Hi Alejandro I have been trying to do the same thing. The problem I do not have credit in OpenAI and i wanted to know if there is any other way using opensource models to achieve the same result..specially in LangChain. Is there any other way?

[@noustelo]

Awesome. Looking forward to part 2....

[@onurolce]

Your code halts to Kernel and it does not work. So there is a problem about "prompt.format(schema="my schema", question="how many users are there?"). what is "my schema" in this because kernel halts when I try to run database connection functions.

[@onurolce]

I've found the solution. it is using pymysql library instead of mysqlconnector library. So first install pymysql library and change db_uri. It is : db_uri = "mysql+pymysql://root:password@localhost:3306/Chinook"

[@bwilliams060]

Your videos are the best!

[@alejandro_ao]

you are the best

[@teddyperera8531]

This is a great tutorial. Thanks for explaining it in a way that's easy to understand

[@alejandro_ao]

thanks Teddy! i’m glad it was useful!

[@bitcoinjc]

Will this work with a Microsoft SQL relational database that is much bigger too?

[@Rajat_Jaiswal]

Thanks works well . Amazing tutorial

[@alejandro_ao]

Great to hear! All the best!

[@chercm]

Hi sir I am not able to get the database scheme output even though it is connected

[@wg5920]

Amazing Video. Great job

[@arishasaeed]

Can we add memory to this architecture? So this bot is conversational

[@rameshh3821]

Could you please let me know if it's possible to use LangChain to query multiple tables and generate data visualizations on the chatbot interface? I've seen solutions for a single CSV file using PandasAI or LIDA, but I haven't found anything that works with multiple tables stored in a database.

[@Aidev7876]

Thanks. What about long ot short term memory during conversation?

[@chercm]

hi do you any thing for chat with Microsoft SQL DB ?

[@yashtrisha5919]

Thanks but i follow the tutorial and i am getting this error "xcept MySQLInterfaceError as err:", do i need to replace " " in query full_chain function?

[@brunocarvalho3229]

Hey Alejandro! Amazing content, it helped a lot with the application we're building on my company right now. One question, let's say that the user wants to give some feedback on the output and wants to generate again? Would I have to run the full chain again ? Do you already have another walkthrough on this memory context? Thanks!

[@batigol_9]

I was wondering if your calendly link is working for consultations ?it seems that its down

[@sam-uw3gf]

great as always bro

[@alejandro_ao]

thank you bro

[@neelarahimi1053]

Thank you for the amazing video. I have seen practices where they make "vector stores" from DB schema, using LangChain's vectorization and provide that to LLM in the prompt, rather than sql-generated schema. Which practice is preferred?

[@alejandrocano5323]

how to manage that the first chain doest find the information in the SQL Schema?

[@artislove491]

Great stuff! Many thanks 💪

[@alejandro_ao]

No problem 👍

[@machinelearningzone.6230]

Awesome tutorial! I tried to implement the same on collar, using a sqlite database(chinook). but consistently get the error:"'NoneType' object has no attribute 'get_table_info'" when I try to ge the table schema. Any work arounds?

[@RedWhiteBlue209]

Could you please post your requirements.txt? When running your code, I got this error: ImportError: cannot import name 'LangSmithParams' from 'langchain_core.language_models.chat_models'

[@scratch-9097]

Hey , is it possible to run DML queries using chains or agents?

[@tinytube4me-z8h]

When running your code, I got this error: ImportError: cannot import name 'LangSmithParams' from 'langchain_core.language_models.chat_models'. Could you please post your requirements.txt? Thank you!

[@chercm]

Hi . It is great video . Is it possible to use azure open ai and Microsoft sql with this ?

[@Soneone-kz4fp]

I want to do the same thing for mongodb, how can I do that?

[@arunsnmimtimt]

@alejandro_ao,can you kindly let me know whether it can be done with out API. that is to run the same locally on desktop?

[@07-bmanohar70]

Does this can be implemented to the large Databases ?

[@alejandro_ao]

absolutely, just be careful that these two things fall within your context window: - the table schemas of your database (unless you have a humungous number of tables, it should be fine). - the results from your query (as they they will be sent back to the model for interpretation). the second point is more tricky than the first one. you may want to update your prompt to make sure that it does not allow to query more than X number of records at a time.

[@MrJaczes]

@@alejandro_ao i thought about this topic to use Views to handle sets form large database and pre-agregate it there

[@ishanagrawal396]

Thanks! This is helpful! How can we create it with Open Source model instead of Open AI as it is paid? Also, Is there a github repo for this?

[@Jaypatel512]

Hey, thanks for the video. However, few questions if you don't mind: 1. Do we need to assign the sql_chain inputs again when building a full_chain ? Won't it remember from its own structure. I see that as complexity grows, we end up adding a whole bunch of assignment in full chain. 2. For full chain, is there a way to use pipe operator to let the sql_chain response be passed to the next step where you run_query ? Basically, RunnablePassthrough.assign(sql_chain) | run_query | prompt | llm | StrOutput... ? Thanks again for your wonderful tutorials.

[@reinerzufall3123]

you just think too complicated 😉

[@AbhinavKumar-tx5er]

Will it work with large dataset? lets say more than 20GB?

[@Matepediaoficial]

I love you!! You are the best!!!

[@alejandro_ao]

i love you more

[@RicardoIturra-w8y]

Excellent! ♥

[@alejandro_ao]

i really need to update my video on memory. i'll look into it!

[@frankfromthebulb6181]

Great job! Your Calendly link in the description isn't working. How can I get in contact with you for a project?

[@isvic007]

Can we not using Oracle DB for this test?

[@chibuzoemelike6403]

Thank you so much for this video, this is really helpful!! Looking forward to using huggingface models

[@alejandro_ao]

Great! Which models in particular are you interested in?

[@palanikumarmsc]

Mistral AI

[@legilord3786]

thanks for the great video, does it matter how big the database is? or can a database be too big? in my case i have a database with a size of about 300mb

[@abhaypkyek]

You really made my day. i was trying to figure out this code from Langchain templates from many days. But you gave a perfect clarity giving step by step understanding. Thanks alot for that. Can u further enhance this in your next video as said in the end of the video with ollama & vizualization from the response using PandasAI or LIDA AI or something better please.

[@alejandro_ao]

it's great to hear this! thank you for letting me know. and congrats for finally getting through it! keep it up 👍 that's actually a great idea. i'll see if i can put it in the next video or make a dedicated video about this!

[@natawebmaster]

Thanks for useful video)

[@alejandro_ao]

it's my pleasure :)

[@v.svishnu2380]

I have a doubt, Is it safe to connect langchain with production database ?

[@alejandro_ao]

I would recommend that you only do this after thorough testing. and very importantly, do not give write privileges to the MySQL user that you are using to access the database. You don’t want your LLM to be able to update or delete data in your database 👍

[@TS-ml4dp]

Hey Alejandro , your guides are great , the best in the net. I would like to ask if you think that replace the schema with Knowledge graph is a good Idea , the reason is that in practice in large DB and DWH the meta data on tables & fields name are not align with business terms and the idea is to leverage the meta data via knowledge graph. what do you think? can you do some guide about KG?

[@warrenmarkham8891]

Thanks for the content. The link to your blog post doesn't work for me.

[@alejandro_ao]

hey there, can you try again? i think my dns server was giving me trouble last week

[@warrenmarkham8891]

@@alejandro_ao Still not working I'm afraid.

[@alejandro_ao]

@@warrenmarkham8891 just refreshed the DNS settings on netlify! Should be up now!!

[@warrenmarkham8891]

@@alejandro_ao Yep, you punched the right ticket that time. It is now working great.

[@lucasgrandini1776]

teria como conversar com o sqlite de um zabbix-server?

[@drummermike5150]

Great tutorial as usual Alejandro! Is it possible to do this with SQL Server? I look at the documentation and it doesn't appear so but maybe I'm missing something.

[@alejandro_ao]

Thanks! I am not sure how it would work with MS SQL Server. I suppose you would need a driver to connect it. Since SQLAlchemy supports it, I suppose that it can be done. Maybe if you add the driver to the URI like we did here, but instead of adding the MySQL driver, you add one for MS SQL Server? I checked and this driver might work, but I am not on Windows, so I have no way of testing it right away: ```python from langchain_community.utilities import SQLDatabase db_uri = "mssql+pyodbc://username:password@hostname:port/DatabaseName?driver=SQL+Server" db = SQLDatabase.from_uri(db_uri) ```

[@drummermike5150]

@@alejandro_aoI'll give that a try. Thanks much!!

[@dswithanand]

I made the sqldb chatbot using fastapi and every thing is working fine except that the chat memory history. Can you suggest how can we implement memory with fastapi.

[@dswithanand]

Can you please answer this

[@dr.aravindacvnmamit3770]

Hey very nice, I had one query , LLM based Application to assess the quality of language being used by parents and give practice sessions to improve them. Can you show us "It is a kind of Therapy for special children to make understand the words

[@av1743]

Thanks for posting this. Very helpful. is there any open source LLM which can convert Natural language to SQL ? would Llama, Flan T5 etc work instead of gpt ?

[@batyratamamedov7633]

Thank you for the video, can you please make a video or guide to implement it with Ollama and postgres database? Thanks in advance!

[@MrYorii]

Great! Thanks

[@monishamonisha-zt3uy]

When I execute full_chain.invoke ({"question": "how many albums are there in the database?"}) it returns {'question': 'how many albums are there in the database?'}

[@kartiksaini-xn6ke]

i am facing the same issue, did you get any solution ?

[@guanjwcn]

Awesome. Could you include streaming in part 2 as well?

[@alejandro_ao]

streaming is coming very soon 😎

[@fbravoc9748]

Amazing video!! Thanks for creating it!! Is there a way to apply the same principles but with another LLMs (open-source)?? If I had gone over all the database I am working with and I had identified the queries related to the most frequent questions, how can I finetune my queries to these frequent questions? ..should I think about adding RAG logic to it?

[@uplifting_sounds]

Love the idea, tried it but constraints from openai.

[@MADMAX-rw7jx]

There is no password in my SQL server what to put in db_uri sir

[@MuhammadAhmad-o4q]

Will this method work with multiple db's and 500+ tables ? If not than what can be a way

[@alejandro_ao]

as long as the db ERD schema fits into the context window, you should be good!

[@SandhiniGopinathan]

It's a wonderful session but the link to your blog post doesn't working.

[@alejandro_ao]

just fixed it! DNS propagation problem after meddling with some records on netlify :S

[@prashu25925]

Can I DEPLOY this in my company ? Or it can cause data breaches?

[@alejandro_ao]

there is some data going to the OpenAI servers. if you are fine with that, go for it! else, you can either use a secure deployment on Azure OpenAI or host your own model :)

[@youngchrisyang]

Thanks so much Alejandro! Great contents. Btw seems your website is down today>?

[@alejandro_ao]

hey there, thanks! can you check again? i think my dns has been struggling with some changes i did recently :S

[@youngchrisyang]

@@alejandro_ao Thank you Alejandro. All works fine now!

[@dswithanand]

I have a question: If the database belongs to an e-commerce website with a substantial product inventory, and a user query such as 'SHOW ME PRODUCTS' risks exceeding the ChatGPT token limit of 60000, how can this issue be effectively managed?

[@alejandro_ao]

Yeah, maybe that will require a bit of prompt engineering to make sure that you never index more than X number of records. You could add something like "if you are selecting records, please never call more than 100 records in a single query" or something like that. another alternative would be to use an agent, that would make it more flexible

[@dswithanand]

@@alejandro_ao Thanks for reply.. I tested this and it actually worked. Thanks bro

[@geekyprogrammer4831]

Can you create langchain based streaming chatbot? Would be very helpful. Thanks for creating high quality contents!

[@alejandro_ao]

coming very soon!

[@matten_zero]

Can you do this with NoSQL like MongoDB🙏?

[@alejandro_ao]

great idea

[@KurskikhA]

Hi, been following you for a long time, very cool content. Can you please tell me how to use Langchain for MSSQL or Postgres?

[@alejandro_ao]

hey there! thanks for following the content :) i'll be putting up a video about postgres soon. i actually haven't tested if this would work using a mssql driver. but look, apparently you can pass in a driver just like we did here with mysql, but for MSSQL: docs.sqlalchemy.org/en/20/dialects/mssql.html#module-sqlalchemy.dialects.mssql.pyodbc

[@AdhisashanJ]

Nice, how to do column mapping. Like "How many creator are there" as input question but we have artist instead. I tried as below but still it not works sql_chain = ( RunnablePassthrough.assign(schema=get_schema, column_mapping=get_column_mapping) | prompt | llm.bind(stop=["\ SQLResult:"]) | StrOutputParser() ) column_mapping = { r'creator|artists': 'artist', # Add more mappings as needed } def get_column_mapping(_): column_mapping_str = " ".join([f"{key}: {value}" for key, value in column_mapping.items()]) return column_mapping_str

[@jimgsewell]

Thank you. This is a real interesting idea. I wonder how complex of a question you can ask it. Can it come up with a query which requires a merging of tables, or returning multiple values? You have me curious.

[@mwdcodeninja]

I have used this method to join across a db of 34 tables to form a master document archive for customer data. I was happy with it.

[@alejandro_ao]

absolutely, it all depends on your LLM's accuracy at executing the queries. in my experience, GPT3 16k is very good. as @sanjayojha1 mentioned, a coding-specific LLM might give you even better results. just don't forget to limit the scope of your MySQL user to avoid security problems!

[@chibuzoemelike6403]

@@mwdcodeninja wow, it's glad you've been able to use this before and it performs a join. I'm working on a project with bigquery which has so many data, it doesn't give the desired output as it doesn't perform join, I'll be glad if we can connect and work on it together. Thank you in advance

[@chibuzoemelike6403]

@@alejandro_ao please how do we implement a code specific LLM to the chain.

[@mwdcodeninja]

@@chibuzoemelike6403 would you be able to share the schema?

[@Sunny-tk2fu]

No doubt your tutorial is awesome but i want to just suggest that you should minimize the sibilant sound through davinci resolve or other video editing software to be making video more compelling

[@alejandro_ao]

this is a great suggestion. i actually use resolve but didn't know i could do that. thank you!

[@marvinmarkham8405]

Videos are exceptional just very high level and the mic seems close when speaking so its not pleaseant for me to watch the vids with that type of mic calibration. Luckily the website is a better walkthough for me. Thanks for your work

[@alejandro_ao]

hey thank you for the feedback, glad you found the tutorial useful mate. i’ll improve the sound in future vids :)

[@muneerAbro]

Very Informative video ❤, can you create this video in PHP

[@alejandro_ao]

hey, thanks! i would like to but unfortunately langchain does not have a PHP version that I know of :( if you are trying to create something like this for a PHP app, I would create an API that deals with these processes in python or js and then have my PHP app query this API

[@muneerAbro]

@@alejandro_ao welcome dear, I tried in php/ laravel, it is working fine but some time it shows response "Unable to generate query". So I am very afraid of this, If I deploy this chat on live server, If I get such response, it will be bad experience for me, can you suggest me How I get rid of this error? this error comes from chatgpt-4o openAi

[@Astar-o5k]

is open ai compulsary?

[@alejandro_ao]

absolutely not. you can import any language model that langchain supports: python.langchain.com/docs/integrations/chat/

[@StnImg]

❤❤Can u apply RAG on schema to accommodate bigger Databases with huge tables in next video?

[@sanjayojha1]

Great as always. I personally find the RunnablePassthrough ugly syntax and confusing. Also, using a coding specific LLM we might get better SQL query with less hallucination.

[@alejandro_ao]

hey good to see you again. thanks! i totally agree with you that RunnablePassthrough could be better. and about the LLM, totally. not only better, but also faster, as it would be a smaller model 🤔

[@chibuzoemelike6403]

Please what do you mean by coding specific LLM?

[@monica.b181]

Awesome videos.. really appreciate your efforts 👍 Could you please make a video to create a chat bot for WordPress websites.. because scrapping the content from WordPress websites is a bit tricky and passing them to divide into chunks are throwing errors...please help

[@monica.b181]

@UC1oXUA7qgs0GZc_yk46K2OQ hi, I am grateful you replied to my comment 😊🙏 Actually I don't have access to deal with database..the idea of my project is to create a webchat bot for dynamic WordPress websites, where I can scrape all the content from sitemap.xml and then divide it into chunks -> store in any database like faiss or vector store and finally with streamlit I would able to chat with the content on the site. So I need your help in this, as I am beginner and new to these technologies. Please

[@monica.b181]

@UC1oXUA7qgs0GZc_yk46K2OQ hi, I am grateful you replied to my comment 😊🙏 Actually I don't have access to deal with database..the idea of my project is to create a webchat bot for dynamic WordPress websites, where I can scrape all the content from sitemap.xml and then divide it into chunks -> store in any database like faiss or vector store and finally with streamlit I would able to chat with the content on the site. So I need your help in this, as I am beginner and new to these technologies. Please

[@nazarmohammed5681]

chatting with website using gemini pro plz make a video on this???????