response_generator = self.agent.stream_chat(message=messages[-1].content, chat_history=messages[:-1]).chat_stream
for token in response_generator:
yield tokenValueError: generator already executing
response_gen instead of chat_stream it's working flawless. However, i truly need that ChatResponse objectsVectorStoreIndex.from_documents()? I have single JSON ~140mb and it spend 50min on generating index on google colab, before i interrupted it. Now i try to run locally and already 10min of executing. What is the common time it take to generate index?response.tool_calls list is empty, and when listening to the stream of events, I never see the ToolCallResult being output.peek into my chromadb after indexing a handful of sample documents, it returns an empty dict as follows: {'ids': [], 'embeddings': array([], dtype=float64), 'documents': [], 'uris': None, 'data': None, 'metadatas': [], 'included': [<IncludeEnum.embeddings: 'embeddings'>, <IncludeEnum.documents: 'documents'>, <IncludeEnum.metadatas: 'metadatas'>]}. When I print my docstore from index.docstore.docs, it states that I do have documents. I've been debugging it for a bit, playing around with persist paths and other configs but I can't seem to find where the problem resides@step
async def ask(self, ev: StartEvent) -> StopEvent | None:
obj_index = ev.get("obj_index")
query = ev.get("query")
chat_store = ev.get("chat_store")
user = ev.get("user")
if not obj_index or not query:
return None
user_file = f"./conversations/{user}.json"
if not os.path.exists(user_file):
chat_store = SimpleChatStore()
else:
chat_store = SimpleChatStore.from_persist_path(persist_path=user_file)
chat_memory = ChatMemoryBuffer.from_defaults(
token_limit=3000,
chat_store=chat_store,
chat_store_key=user,
)
top_agent = OpenAIAgent.from_tools(
tool_retriever=obj_index.as_retriever(similarity_top_k=3),
system_prompt=PROMPT,
memory=chat_memory,
verbose=True,
)
response = top_agent.query(query)
chat_store.persist(persist_path=user_file)
return StopEvent(result={"response": response, "source_nodes": response.source_nodes})from llama_index.llms.openai_like import OpenAILike
llm = OpenAILike(
model="model",
api_key="Key",
api_base="OpenAI Compatible endpoint",
context_window=16000,
is_chat_model=True,
is_function_calling_model=False,
)
Settings.embed_model = llm
# Create index
index = VectorStoreIndex.from_documents(
documents,
show_progress=True)1AssertionError Traceback (most recent call last)
Cell In[22], line 31
22 documents = SimpleDirectoryReader("../data", required_exts=[".txt"]).load_data()
23 #embed_model = llm
24
25
(...)
29 # api_base="http://tentris-ml.cs.upb.de:8502/v1"
30 # )
---> 31 Settings.embed_model = llm
33 # Create index
34 index = VectorStoreIndex.from_documents(
35 documents,
36 show_progress=True)
File c:\Users\KUNJAN SHAH\AppData\Local\Programs\Python\Python311\Lib\site-packages\llama_index\core\settings.py:74, in _Settings.embed_model(self, embed_model)
71 @embed_model.setter
72 def embed_model(self, embed_model: EmbedType) -> None:
73 """Set the embedding model."""
---> 74 self._embed_model = resolve_embed_model(embed_model)
File c:\Users\KUNJAN SHAH\AppData\Local\Programs\Python\Python311\Lib\site-packages\llama_index\core\embeddings\utils.py:136, in resolve_embed_model(embed_model, callback_manager)
133 print("Embeddings have been explicitly disabled. Using MockEmbedding.")
134 embed_model = MockEmbedding(embed_dim=1)
--> 136 assert isinstance(embed_model, BaseEmbedding)
138 embed_model.callback_manager = callback_manager or Settings.callback_manager
140 return embed_model