Chat With Multiple PDF Documents With Langchain And Google Gemini Pro  

For sure sir I am always there to support valuable content providing by you ❤

Valuable information

hi sir, if possible, could you do a video for scanned multipage pdf which includes images and tables with in it.

what are the prerequisites for this project Sir ?

@krishnaik06 pdf contains images or some figure. Is it possible to get those images as output for user response

am also facing this issue. Do you got any solution

In the function user_input(), replace the line and add allow_dangerous_deserialization=True #Code new_db = FAISS.load_local("faiss_index_react", embeddings, allow_dangerous_deserialization=True)

same, you got solution ?

@@ravikantjain Please check you environment you are working.That might be issue

initially i got the answer but later I am getting similar answers

same error here. Did you manage to find a solution?

First, try this: Increase the context length to 10000 in charactersplitter. If that doesn't happen: Try changing response = chain( {"input_documents": docs, "question": query} , return_only_outputs=True) to response = chain.invoke( {"input_documents": docs, "question": query} , return_only_outputs=True). I just wanted to let you know that this worked for me.

You can use request.files.getlist('parameter') instead of You can use request.files['parameter']

same here do you find solution

I am also facing the same issue.

@krishnaik06 Yes, I am also facing the same problem here, please suggest a solution.

same here do you find solution

i got the solution we need to update the langchain library i am using langchain 0.1.0

Change code into new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)

It worked for me, thanks!@@kanth2223

the same error ....no solution now ..are getting a solution for the problem?

First, try this: Increase the context length to 10000 in charactersplitter. If that doesn't happen: Try changing response = chain( {"input_documents": docs, "question": query} , return_only_outputs=True) to response = chain.invoke( {"input_documents": docs, "question": query} , return_only_outputs=True). I just wanted to let you know that this worked for me.

@@shubhamrathod9969 i tried the code which shown in the video and got IndexError: list index out of range Can you help me with this.

But where we have used the word query ​@@shubhamrathod9969

Even after using above approaches, still facing same problems

Even I'm trying to do same thing, could you help me out please with the code . I have selected this idea as my final year project

me tooo plzz help me

just set the parameter allow_dangerous_deserialization = True i.e. FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)

Bro same here you got it solved? Can you help?

@@srihbalaji7272 Change this line new_db = FAISS.load_local("faiss_index", embeddings) to new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)

Change this line new_db = FAISS.load_local("faiss_index", embeddings) to new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)

@@srihbalaji7272 In the function user_input(), replace the line and add allow_dangerous_deserialization=True #Code new_db = FAISS.load_local("faiss_index_react", embeddings, allow_dangerous_deserialization=True)

I'm also getting same error, any one fixed this issue.

update langchain mine is fixed

After update lanchain, I still get the same error. It looks like the google_api_key become "None"? : `embedding_function` is expected to be an Embeddings object, support for passing in a function will soon be removed. vector_store: Google Generative AI embeddings: model='models/embedding-001' task_type=None google_api_key=None client_options=None transport=None `embedding_function` is expected to be an Embeddings object, support for passing in a function will soon be removed. perform Similarity_Search for user_question: provide a detailed summary of Multi-Head Attention 2024-03-11 22:46:57.585 Uncaught app exception Traceback (most recent call last): File "/home/peter/anaconda3/envs/tf/lib/python3.10/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 534, in _run_script exec(code, module.__dict__) File "/home/peter/AIU/AIU_CS515_LLM/020_Gemini/002_Code/pdf_chatbot.py", line 108, in main() File "/home/peter/AIU/AIU_CS515_LLM/020_Gemini/002_Code/pdf_chatbot.py", line 93, in main user_input(user_question) File "/home/peter/AIU/AIU_CS515_LLM/020_Gemini/002_Code/pdf_chatbot.py", line 71, in user_input docs = new_db.similarity_search(user_question) File "/home/peter/anaconda3/envs/tf/lib/python3.10/site-packages/langchain/vectorstores/faiss.py", line 509, in similarity_search docs_and_scores = self.similarity_search_with_score( File "/home/peter/anaconda3/envs/tf/lib/python3.10/site-packages/langchain/vectorstores/faiss.py", line 390, in similarity_search_with_score embedding = self._embed_query(query) File "/home/peter/anaconda3/envs/tf/lib/python3.10/site-packages/langchain/vectorstores/faiss.py", line 155, in _embed_query return self.embedding_function(text) TypeError: 'GoogleGenerativeAIEmbeddings' object is not callable

need to update the langchain inorder to fix it

same problem

Can you please tell what are the prerequisites for this project

did you found any solution for this ?

yes u can

You got any solution for this?

samee , is it solved?

Yes it can be any number

Have you figured out how one can fine tune Gen AI app with their own data?

can you help me i am getting an error "No module named langchain" 😭

I am guessing your best bet to keep this data private is to host a local LLM (maybe set up an endpoint with LMStudio) and see how it works. Mistral 7 does a good job for me.

Hey This was all working for me for last 2 days, but then I upgraded streamlit and now 'allow_dangerous_deserialization' flag is not required but facing an error - "TypeError: 'GoogleGenerativeAIEmbeddings' object is not callable". can you help to resolve the error?

@@harishsharma9466 Did you resolve the issue?

hey getting same error, were you able to find a resolution?

just set the parameter allow_dangerous_deserialization = True i.e. FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)

You got solution?

Please did you find any solution for that? I'm working on something similar and I want to extract images and interact with them

Is this fixed?? I’m facing this error now. Not able to resolve it. Please help. I’m uploading 2mb pdf. Still i’m getting this error

Try to hard code the google gemini api key

Yes Even me , I think this comment was almost 2 months ago , I am trying to implement it now , even I am getting the same error , Did you figured it out on how we can solve this issue or the error. I know you might be busy but a 2 word reply would mean a lot.

So have you solved 1. Issue yet?

just set the parameter allow_dangerous_deserialization = True i.e. FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)