client = qdrant_client.QdrantClient(path=vector_store_path)
        client.create_collection(collection_name=VECTOR_COLLECTION_NAME,vectors_config=models.VectorParams(size=param_size,distance=models.Distance.COSINE))
        return client
# other code here...
transformations=[
                TitleExtractor(nodes=3,llm=llm,num_workers=1),
                QuestionsAnsweredExtractor(questions=3,llm=llm,num_workers=1),
                SummaryExtractor(summaries=["prev","self","next"],llm=llm,num_workers=1),
                KeywordExtractor(llm=llm,num_workers=1),
                SentenceSplitter(chunk_size=2048,chunk_overlap=512),
                # TokenTextSplitter(chunk_size=1024,chunk_overlap=256),
                HuggingFaceEmbedding(model_name=embed_model)
                ],
                vector_store=vector_store
            )
            nodes = pipeline.run(documents=docs,show_progress=True)

tmp lock file

async def astreamer(response,model_used):
    try:
        for i in response.response_gen:
            if response._is_done:
                print("IS DONE!")
            else:
                print("IS NOT DONE!")
            yield json.dumps(i)
            create_json_response()
            await asyncio.sleep(.1)
    except asyncio.CancelledError as e:
        print('cancelled')

@app.post("/chat")
async def chat(request:Request):
  ...
  response = chat_engine_dict["engine"].stream_chat(query)
  return StreamingResponse(astreamer(response,model_used=model_used),media_type="text/event-stream")

ValueError: Metadata length (379349) is longer than chunk size (2048). Consider increasing the chunk size or decreasing the size of your metadata to avoid this.

ValueError: shapes (0,512) and (384,) not aligned: 512 (dim 1) != 384 (dim 0)

# We will be using local storage instead of a host qdrant server
client = qdrant_client.QdrantClient(path="./sfa_test",)
client.create_collection(collection_name="SFA",vectors_config=models.VectorParams(size=512,distance=models.Distance.COSINE))

vector_store = QdrantVectorStore(client=client,collection_name="SFA")
storage_context = StorageContext.from_defaults(vector_store=vector_store,)

from llama_index.core import ServiceContext,Document
docs = SimpleDirectoryReader("./data/").load_data()
# docs = docs [150:160]
docs = [Document(text="Hello world"), Document(text="Hello there")]
Settings.embed_model = resolve_embed_model("local:BAAI/bge-small-en-v1.5")
Settings.llm = Ollama(model="mistral")
embed = resolve_embed_model("local:BAAI/bge-small-en-v1.5")
llm = Ollama(model="mistral")

SERVICE_CONTEXT = ServiceContext.from_defaults(embed_model=embed,llm=llm)

pipeline = IngestionPipeline(
    transformations=[
        KeywordExtractor(llm=llm),
        TokenTextSplitter(chunk_size=512,chunk_overlap=256)
    ],
    vector_store=vector_store
)
nodes = pipeline.run(documents=docs,num_workers=16,)

index = VectorStoreIndex.from_vector_store(vector_store=vector_store,embed_model=embed)

query_engine = index.as_query_engine(llm=llm)
response = query_engine.query("Give me a random example")
print(response)

client.create_collection(collection_name="SFA",vectors_config=models.VectorParams(size=512,distance=models.Distance.COSINE))