# Need help combining weaviate with langchain

**URL:** <https://forum.weaviate.io/t/need-help-combining-weaviate-with-langchain/646>\
**Category:** Support\
**Created:** [September 10, 2023, 10:15am UTC](https://forum.weaviate.io/t/need-help-combining-weaviate-with-langchain/646 "2023-09-10T10:15:26Z")\
**Posts on this page:** 9\
**Page:** 1

<div class="post-metadata">

**Author:** ![ananthan-123](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/ananthan-123/32/451_2.png) [@ananthan-123](https://forum.weaviate.io/u/ananthan-123)\
**Post date:** [September 10, 2023, 10:15am UTC](https://forum.weaviate.io/t/need-help-combining-weaviate-with-langchain/646/1 "2023-09-10T10:15:26Z")

</div>

I have a usecase where the users will have many documents. No user will be able to access any other users documents. Also each user can select which files they can access .  
I am using weaviate-python client , langchain (RetrievalQAWithSourcesChain).

First I tried to create a single class “Data” which has properties “content” and “source” , then user will be ble to filter the data using the “source” property. But this method has a problem. Even after filtering , the user is able to access other users files.

Then I tried another method. A class for each user and inside the user class , there will be a “data” field that will be linking to the “Data” class.  
Below is the schema.

```auto
    "classes": [
{
        "class": username,
        "description": f"Class for user {username}",
        "properties": [
            {
                "name": "username",
                "description": "Username of the user",
                "dataType": ["text"]
            },
            {
                "name": "data",
                "description": "Data associated with the user",
                "dataType": ["Data"]
            }
        ]
    },
        {
            "class": "Data",
            "description": "Documents/data in the system",
            "vectorizer": "text2vec-openai",
            "moduleConfig": {"text2vec-openai": {"model": "ada", "type": "text"}},
            "properties": [
                {
                    "name": "content",
                     "description": "The content of the paragraph",
                    "dataType": ["text"],

                    "moduleConfig": {
                        "text2vec-openai": {
                            "skip": False,
                            "vectorizePropertyName": False,
                        }
                    },
                }, {
                    "name": "source",
                    "description": "The link to the document",
                    "dataType": ["text"]
                }
            ],
        }
    ]

```

I am using the below code to create a vectorstore .

vectorstore = Weaviate(client, user, “data{ … on Data { source content }}”, attributes=[‘data { … on Data { source } }’], embedding=embed)

1. I am getting the below error

```auto
KeyError: 'data{ ... on Data { source content }}'

```

1. How can I retrieve specific data using the “source” from the user class? Is filtering a good approach?

can anyone help me with this? Thanks in advance.

---

<div class="post-metadata">

**Author:** ![DudaNogueira](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/dudanogueira/32/7846_2.png) [@DudaNogueira](https://forum.weaviate.io/u/DudaNogueira)\
**Post date:** [September 11, 2023, 6:08pm UTC](https://forum.weaviate.io/t/need-help-combining-weaviate-with-langchain/646/2 "2023-09-11T18:08:55Z")

</div>

Hi @ananthan-123 !

Welcome to our community 🤗

This is a great use case for the new [multi tenant feature in Weaviate](https://weaviate.io/developers/weaviate/manage-data/multi-tenancy). So each user will be a tenant and can be added to the class, but with the data isolated from each other.

However, multi tenancy is **not yet** supported in Langchain.  
I have started a PR and Issue here for that:

> <https://github.com/langchain-ai/langchain/issues/9956>
>
> \### Feature request
> 
> Weaviate introduced multi-tenancy support in version 1.20
> …https://weaviate.io/blog/multi-tenancy-vector-search
> 
> \### Motivation
> 
> This can help users using Langchain + Weaviate at scale, ingesting documents and attaching tenants to it.
> 
> \### Your contribution
> 
> I have implemented, but would need some help to check if everything is ok and in accordance with LangChain.
> 
> Also, I would like help on the as\_retriver, as I was not able to implement multitenant on it, Yet.
> 
> the code is living here: https://github.com/dudanogueira/langchain/tree/weaviate-multitenant

With that said, filtering is a possible solution.

Creating one class per user is not the best approach. It will result in multiple vectors spaces for each user, making it hard to scale.

This is how you would get relevant documents with filtering with the current langchain, extracted from here:

> <https://github.com/langchain-ai/langchain/blob/8b5662473f4c7daeef1ad7dbbb95b758acbfcd43/libs/langchain/tests/integration_tests/retrievers/test_weaviate_hybrid_search.py#L113C9-L113C81>

```auto
from weaviate import Client
from langchain.docstore.document import Document
from langchain.retrievers.weaviate_hybrid_search import WeaviateHybridSearchRetriever

texts = ["foo", "bar", "baz"]
metadatas = [{"page": i} for i in range(len(texts))]

client = Client("http://localhost:8080")

retriever = WeaviateHybridSearchRetriever(
    client=client,
    index_name=f"TestLangRetriever",
    text_key="text",
    attributes=["page"],
)
for i, text in enumerate(texts):
    retriever.add_documents(
        [Document(page_content=text, metadata=metadatas[i])]
    )
where_filter = {"path": ["page"], "operator": "Equal", "valueNumber": 0}

output = retriever.get_relevant_documents("foo", where_filter=where_filter)
print(output)

```

Output: _[Document(page\_content=‘foo’, metadata={‘page’: 0})]_

let me know if this helps 🙂

---

<div class="post-metadata">

**Author:** ![Lucia\_Urcelay](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/lucia_urcelay/32/841_2.png) [@Lucia\_Urcelay](https://forum.weaviate.io/u/Lucia_Urcelay)\
**Post date:** [January 17, 2024, 3:29pm UTC](https://forum.weaviate.io/t/need-help-combining-weaviate-with-langchain/646/3 "2024-01-17T15:29:14Z")

</div>

Hi! I want to filter my Weaviate instance butI am using a ConversationalRetrieverChain defined as follows:

```auto
rag_chain = ConversationalRetrievalChain.from_llm(
        llm = llm,
        memory = memory,
        retriever = vectorstore.as_retriever(k=k_top_chunks),
        verbose = True,
        combine_docs_chain_kwargs={'prompt': prompt_template},
        get_chat_history = lambda h : h
    )

```

How can I integrate the following line in my chain?

```auto
retriever.get_relevant_documents("foo", where_filter=where_filter)

```

Also, is there any way to filter my vectorestore using the simple dense search retriever from LangChain and not WeaviateHybridSearchRetriever?

---

<div class="post-metadata">

**Author:** ![DudaNogueira](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/dudanogueira/32/7846_2.png) [@DudaNogueira](https://forum.weaviate.io/u/DudaNogueira)\
**Post date:** [January 17, 2024, 3:35pm UTC](https://forum.weaviate.io/t/need-help-combining-weaviate-with-langchain/646/4 "2024-01-17T15:35:34Z")

</div>

Hi!

I believe that this will help you:

> <https://github.com/weaviate/recipes/blob/main/integrations/langchain/loading-data/langchain-simple-pdf.ipynb>

Also note that a new langchain integration is unde development here:

> **[GitHub - langchain-ai/langchain-weaviate](https://github.com/langchain-ai/langchain-weaviate/)**
>
> Contribute to langchain-ai/langchain-weaviate development by creating an account on GitHub.

Let me know if that helps!

Thanks!

---

<div class="post-metadata">

**Author:** ![Lucia\_Urcelay](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/lucia_urcelay/32/841_2.png) [@Lucia\_Urcelay](https://forum.weaviate.io/u/Lucia_Urcelay)\
**Post date:** [January 17, 2024, 3:49pm UTC](https://forum.weaviate.io/t/need-help-combining-weaviate-with-langchain/646/5 "2024-01-17T15:49:50Z")

</div>

Hi!  
Thanks for the fast response. That helps a lot but I wanted to pass the filter parameters when I run the chain, not when I instanciate it. Is there any way to do that?  
Thanks in advance!

---

<div class="post-metadata">

**Author:** ![DudaNogueira](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/dudanogueira/32/7846_2.png) [@DudaNogueira](https://forum.weaviate.io/u/DudaNogueira)\
**Post date:** [January 17, 2024, 6:18pm UTC](https://forum.weaviate.io/t/need-help-combining-weaviate-with-langchain/646/6 "2024-01-17T18:18:09Z")

</div>

On that example I did it like:

```auto
# Let's answer some question
#source_file = "brazil-wikipedia-article-text.pdf"
source_file = "netherlands-wikipedia-article-text.pdf"
where_filter = {
      "operator": "Equal",
      "path": ["source"],
      "valueText": source_file
  }

# we want our retriever to filter the results
retriever = db.as_retriever(search_kwargs={"where_filter": where_filter})

qa = RetrievalQA.from_chain_type(llm=Cohere(model="command-nightly", temperature=0), 
                                 chain_type="stuff", 
                                 retriever=retriever, 
                                 chain_type_kwargs=chain_type_kwargs, 
                                 return_source_documents=True)
                                 
answer = qa({"query": "What is the traditional food of this country?"})
print(answer)

```

You mean I would like to filter while running the qa?

---

<div class="post-metadata">

**Author:** ![Lucia\_Urcelay](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/lucia_urcelay/32/841_2.png) [@Lucia\_Urcelay](https://forum.weaviate.io/u/Lucia_Urcelay)\
**Post date:** [January 19, 2024, 11:14am UTC](https://forum.weaviate.io/t/need-help-combining-weaviate-with-langchain/646/7 "2024-01-19T11:14:53Z")

</div>

Exactly, I mean passing the filter while running the qa. Something like this:

```auto
answer = qa(
{"query": "What is the traditional food of this country?"}, 
search_kwargs={"where_filter": where_filter}
)

```

Is there a way to do this?  
In my application the user should be able to make queries selecting different properties to filter from, it would be convenient if I don’t have to re-initialize the qa chain every time the user changes the filter properties.

---

<div class="post-metadata">

**Author:** ![DudaNogueira](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/dudanogueira/32/7846_2.png) [@DudaNogueira](https://forum.weaviate.io/u/DudaNogueira)\
**Post date:** [January 22, 2024, 9:42pm UTC](https://forum.weaviate.io/t/need-help-combining-weaviate-with-langchain/646/8 "2024-01-22T21:42:29Z")

</div>

I don’t believe this is possible.

Does it add a lot of overhead?

AFAIK this all should be lazy, meaning, it will only do the queries at the last momment.

---

<div class="post-metadata">

**Author:** ![hari0205](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/hari0205/32/1247_2.png) [@hari0205](https://forum.weaviate.io/u/hari0205)\
**Post date:** [April 5, 2024, 1:34pm UTC](https://forum.weaviate.io/t/need-help-combining-weaviate-with-langchain/646/9 "2024-04-05T13:34:10Z")

</div>

You can try this

```auto
search_filter=weviate.classes.query.Filter.by_property("userid").equal(userid)
    retriver = db.as_retriever(search_kwargs={"filters":search_filter})
    llm = ChatOpenAI(model="gpt-4-turbo-preview",temperature=0)
    
    qa_chain = RetrievalQA.from_chain_type(llm,retriever=retriver)
    res=qa_chain.invoke({"query":query})

```