How To Integrate OpenAI With Azure Vector Search aka Azure Cognitive Search

แชร์
ฝัง
  • เผยแพร่เมื่อ 13 ม.ค. 2025

ความคิดเห็น • 41

  • @shweta-lodha
    @shweta-lodha  ปีที่แล้ว +1

    Code snippets and bit of explanation shweta-lodha.medium.com/step-by-step-tutorial-to-integrate-openai-with-azure-cognitive-search-vector-search-4d75b400675c

  • @jorgeanicama8625
    @jorgeanicama8625 ปีที่แล้ว +3

    Very straight to the point. Just the video i needed to connect many isolated concepts! Thank you very much. !

    • @shweta-lodha
      @shweta-lodha  ปีที่แล้ว

      Glad you find it useful. Stay tuned for more such bites 👍

  • @soubarnobanerjee8257
    @soubarnobanerjee8257 ปีที่แล้ว

    Just loving your contents! There are a lot of grey areas onto the LLMs and how they work if we integrate Azure services, especially the vector DB part. Using FAISS, Chroma, etc are good for POCs, that too performed internally.... but something which gets accepted in enterprise level is the one which you are talking about in this video!!
    Thank you

  • @deepikahari3790
    @deepikahari3790 10 หลายเดือนก่อน +2

    I could not find "generate_embeddings" function definition.

  • @joannezhu101
    @joannezhu101 ปีที่แล้ว

    Thank you Shweta, really helpful for me to understand how the Cognitive search works. I have another question, wouldn't it be easier to use Azure openAI instead of OpenAI as the chat language model towards the end? I'll duplicate the code on my end. Thank you so much for sharing this with us.

  • @KushwanthK
    @KushwanthK 8 หลายเดือนก่อน

    thanks this is really good where is generate_embeddings function located and which embedding model are you using? share the notebook?

  • @MrRugev
    @MrRugev ปีที่แล้ว +1

    Thank u!!!!, your videos have helped me a lot.

  • @nikithajadhav-d2r
    @nikithajadhav-d2r ปีที่แล้ว +1

    Hi Thank you for the video ,i am getting httpresponseerror invalid parameter can u help me with this?

  • @jatinnandwani6678
    @jatinnandwani6678 3 หลายเดือนก่อน

    Thanks Shwetha

  • @joellim1
    @joellim1 ปีที่แล้ว +1

    Hi Shweta, your content is very clear and useful! How might we get the full .ipynb source code so we can try out the solution ourselves? For instance, generate_embeddings function is not shown.Thank you for all that you do!

    • @shweta-lodha
      @shweta-lodha  ปีที่แล้ว

      It is there on my Medium blog. Medium link in present on my profile page

    • @joellim1
      @joellim1 ปีที่แล้ว

      Many thanks@@shweta-lodha

    • @permanazainal6003
      @permanazainal6003 ปีที่แล้ว +1

      @@shweta-lodha medium member only

  • @OleksandrAkimenko
    @OleksandrAkimenko ปีที่แล้ว +1

    This is so good, thank you so much

  • @dheerajsachdeva5735
    @dheerajsachdeva5735 ปีที่แล้ว

    Hi! Can you please share the notebook that you used in the video? The medium site is for members only.

    • @shweta-lodha
      @shweta-lodha  ปีที่แล้ว

      That is the only option I have today. Sorry for that

  • @abhayrajput9546
    @abhayrajput9546 ปีที่แล้ว +1

    What is generate_embeddings ?, not there in your blog

    • @shweta-lodha
      @shweta-lodha  ปีที่แล้ว

      This implementation varies based on your choice - whether you are going with OpenAI embedding, hugging face or any other. Purpose of this function is to generate the embedding for the given text

  • @Haraker21
    @Haraker21 ปีที่แล้ว +1

    Hi, how would you suggest to implement this solution with multiple documents?

    • @shweta-lodha
      @shweta-lodha  ปีที่แล้ว +1

      It doesn’t actually matter from DB side, whether you are taking single or multiple docs. It only differs at a point where you are reading your docs. If you have multiple docs, you can load using some directory loader

  • @Shaikshavali.D
    @Shaikshavali.D 10 หลายเดือนก่อน

    Hi @shweta lodha, can we rename the index name in azure cognitive search.

    • @shweta-lodha
      @shweta-lodha  10 หลายเดือนก่อน

      You can’t

  • @hrishabhgupta7568
    @hrishabhgupta7568 ปีที่แล้ว

    I am following as per the tutorial but getting this error while creating the Index:
    vector_search_configuration is not a known attribute of class and will be ignored

    • @shweta-lodha
      @shweta-lodha  ปีที่แล้ว

      Are you sure, it’s an error and not a warning?

  • @pavan1006
    @pavan1006 ปีที่แล้ว

    In production, how do you deploy this python code ?

    • @shweta-lodha
      @shweta-lodha  ปีที่แล้ว +1

      You can create a web app and do it

  • @HariTummuri
    @HariTummuri 8 หลายเดือนก่อน

    can we use pdf files in the sameway?

    • @shweta-lodha
      @shweta-lodha  8 หลายเดือนก่อน

      No, reader would be different

  • @ssss-u7w
    @ssss-u7w 11 หลายเดือนก่อน

    thanks for the video.

    • @shweta-lodha
      @shweta-lodha  11 หลายเดือนก่อน

      You're welcome

  • @HemantKrSahu
    @HemantKrSahu 4 หลายเดือนก่อน

    Thanks 🙏🏼 to you

    • @shweta-lodha
      @shweta-lodha  4 หลายเดือนก่อน

      Always welcome

  • @OleksandrAkimenko
    @OleksandrAkimenko ปีที่แล้ว +2

    This line is not fully displayed in the video could you kindly provide the rest of the line, please?
    SearchField(name="embedding", type=SearchFieldDataType.Collection (SearchFieldDataType.Single), searchable=True, vector_search)
    Thanks

    • @OleksandrAkimenko
      @OleksandrAkimenko ปีที่แล้ว +1

      as well as generate_embedding function

    • @shweta-lodha
      @shweta-lodha  ปีที่แล้ว +1

      I don't have the complete code, but I hope this snippet would work:
      fields = [
      SimpleField(name="documentId", type=SearchFieldDataType.String, filterable=True, sortable=True, key=True),
      SearchableField(name="content", type=SearchFieldDataType.String),
      SearchField(name="embedding", type=SearchFieldDataType.Collection(SearchFieldDataType.Single), searchable=True, vector_search_dimensions = 1536, vector_search_configuration ="my-vector-config")
      ]
      index = SearchIndex(
      name=index_name,
      fields=fields,
      vector_search=vector_search
      )

    • @shweta-lodha
      @shweta-lodha  ปีที่แล้ว

      response = openai.Embedding.create(
      input="text", engine="text-embedding-ada-002")
      embeddings = response['data'][0]['embedding']

    • @OleksandrAkimenko
      @OleksandrAkimenko ปีที่แล้ว

      Thanks!@@shweta-lodha