The Chromadb doesn't work whenever i try to put it in the RetreivalQA.from_chain_type as a retreiver , it gives me this error :
'NoneType' object has no attribute 'info'

although it is the same code as you , only the importings is different due to LangChain different versions
Thanks in advance

index.storage_context.persist() is not storing the vector_store and creating thevector_store.json file

When I try to load from disk and run sc2 = StorageContext.from_defaults(persist_dir='./storage'), i get the following error:

No existing llama_index.vector_stores.simple found at ./storage/vector_store.json, skipping load.

I only have 1 document in my documents directory... Your example had 2. I wonder if that has soemthing to do with the issue?

Full Code:

with open('KPMGOutlook/kpmgoutlook.text', 'w') as file: file.write(kpmg_text)

documents = SimpleDirectoryReader('KPMGOutlook').load_data()

vector_store = ChromaVectorStore(chroma_collection)
storage_context = StorageContext.from_defaults(vector_store=vector_store,persist_dir='storage')

index = GPTVectorStoreIndex.from_documents(documents, storage_context=storage_context)

index.storage_context.persist()

query_engine = index.as_query_engine()

#Querying document. this works fine
r = query_engine.query("Which economy has the most positive outlook?")
print(r)

#This line gives me the error
sc2 = StorageContext.from_defaults(persist_dir='./storage')

Hi there, I was trying to get the 07_custom.py program to run with the facebook/opt-iml-1.3b model and I can see it loads the cache correctly and I put in enough print statements to see that it also was able to get the LLMPredictor, create the service context, and load the index from disk. However when it tries to call execute_query the program seemingly hangs. I can see my RAM usage spike for an extended period of time but no matter how long I wait (20 minutes?) I don't get a response from the model. Note that I am running with an AMD GPU so when creating the pipeline I removed the CUDA device specification because as far as I can tell CUDA Is not supported with AMD GPUs. Do I need a more powerful computer or CUDA to run this?

Here are my specifications:

OS: Windows 11
Processor AMD Ryzen 7 5800H with Radeon Graphics 3.20 GHz
Installed RAM 16.0 GB (13.9 GB usable)
Device ID XXXXXXXXXXXXXX
Product ID 00342-20715-34612-AAOEM
System type 64-bit operating system, x64-based processor
GPU 0: AMD radeon RX 6600M
GPU1: AMD Radeon(TM) Graphcis
Pen and touch Pen support

Thanks for your help!

I have seen this error with other projects (not yours) when the python version was in mismatch. I currently have 3.9.6 (errors were reported with 3.11.x)...so not sure what may be going on here.

Collecting uvloop==0.17.0 (from -r requirements.txt (line 112))
Using cached uvloop-0.17.0.tar.gz (2.3 MB)
Preparing metadata (setup.py) ... error
error: subprocess-exited-with-error

× python setup.py egg_info did not run successfully.
│ exit code: 1
╰─> [6 lines of output]
Traceback (most recent call last):
File "", line 2, in
File "", line 34, in
File "C:\Users\patbh\AppData\Local\Temp\pip-install-qa53rwky\uvloop_94d9148e502f4a8689747849ae1f0a57\setup.py", line 8, in
raise RuntimeError('uvloop does not support Windows at the moment')
RuntimeError: uvloop does not support Windows at the moment
[end of output]

note: This error originates from a subprocess, and is likely not a problem with pip.
error: metadata-generation-failed

× Encountered error while generating package metadata.
╰─> See above for output.

note: This is an issue with the package mentioned above, not pip.
hint: See above for details.

https://docs.trychroma.com/embeddings

create a Chroma vector store, by default operating purely in-memory

chroma_client = chromadb.Client()

create a collection

chroma_collection = chroma_client.create_collection("newspieces")

https://docs.trychroma.com/api-reference

print(chroma_collection.count())

documents = SimpleDirectoryReader('news').load_data()

index = GPTVectorStoreIndex.from_documents(documents, chroma_collection=chroma_collection)
print(chroma_collection.count())
print(chroma_collection.get()['documents'])
print(chroma_collection.get()['metadatas'])
output：
0
0
[]
[]

Hello,

I love all of your Youtube content upon reviewing your repo I've noticed that this repository currently doesn't have a license.

It would be very helpful if you could add a license to this repository. If you're unsure about which license to choose, GitHub has a guide here.

Thank you

when using the following code to create index, I got errors such as 'ListIndex' object has no attribute 'query' and AttributeError: 'ListIndex' object has no attribute 'save_to_disk'.

@timeit()
def create_index():
    print("Creating index")
    # Wrapper around an LLMChain from Langchaim
    llm = LLMPredictor(llm=LocalOPT())
    # Service Context: a container for your llamaindex index and query
    # https://gpt-index.readthedocs.io/en/latest/reference/service_context.html
    service_context = ServiceContext.from_defaults(
        llm_predictor=llm, prompt_helper=prompt_helper
    )
    docs = SimpleDirectoryReader("news").load_data()
    index = GPTListIndex.from_documents(docs, service_context=service_context)
    print("Done creating index", index)
    return index
  

File "demo9.py", line 101, in execute_query
response = index.query(
AttributeError: 'ListIndex' object has no attribute 'query'

On a fresh install - day old computer - Windows 11, VS Code 1.81.1 and Python 3.11 - Creating a virtual environment for this repo using requirements.txt failed on triton=2.0.0 and uvloop=0.17.0. Commented these out hoping that they are not critical for every tutorial (descriptions do not suggest as such).

Additionally, this answer from Stack Overflow was required to install C++ Build Tools.

i am facing these 2 errors, kindly help me out what I am missing ?

_script.py", line 47, in
prompt_helper = PromptHelper(
TypeError: PromptHelper.init() got an unexpected keyword argument 'max_input_size'
_script.py", line 47, in
prompt_helper = PromptHelper(
TypeError: PromptHelper.init() got an unexpected keyword argument 'max_chunk_overlap'

#code

prompt_helper = PromptHelper(
# maximum input size
max_input_size=2048,
# number of output tokens
num_output=256,
# the maximum overlap between chunks.
max_chunk_overlap=20,
)