add, from MilvusVectorStore, and insert from Index classes? Both does the same thing?ERROR: Unknown field for GenerationConfig: safety_settings File "/workspaces/CORTEX/.venv/lib/python3.10/site-packages/llama_index/llms/vertex/base.py", line 384, in achat generation = await acompletion_with_retry( File "/workspaces/CORTEX/.venv/lib/python3.10/site-packages/llama_index/llms/vertex/utils.py", line 148, in acompletion_with_retry return await _completion_with_retry(**kwargs)
llamaindex, potentially due to a recent Google update that affected some configurations. However, I am unsure of the root cause.llm = Vertex(...) chat = await llm.achat(...)
pyproject.toml
[tool.poetry]
...
[tool.poetry.dependencies]
python = ">=3.10.11,<=3.11.5"
uvicorn = {extras = ["standard"], version = "^0.25.0"}
fastapi = "^0.109.0"
pyyaml = "^6.0.1"
injector = "^0.21.0"
overrides = "^7.7.0"
langchain = "^0.1.10"
langchain-google-genai = "0.0.8"
json-repair = "^0.9.0"
unstructured = {extras = ["all-docs"], version = "^0.14.2"}
opencv-python-headless = "^4.9.0.80"
jq = "^1.6.0"
pytesseract = "^0.3.10"
pymilvus = "^2.3.6"
langchain-openai = "^0.0.8"
scikit-learn = "^1.4.1.post1"
transformers = "^4.38.2"
ruff = "^0.3.1"
pandas = "^2.2.1"
llama-index = "^0.10.33"
python-multipart = "^0.0.9"
llama-index-vector-stores-milvus = "^0.1.10"
playwright = "^1.43.0"
python-magic = "^0.4.27"
llama-index-llms-gemini = "0.1.6"
opencv-python = "^4.9.0.80"
llama-index-llms-anthropic = "^0.1.11"
llama-index-llms-ollama = "^0.1.5"
llama-index-embeddings-ollama = "^0.1.2"
pymupdf = "^1.24.4"
pypdf = {extras = ["image"], version = "^4.2.0"}
surya-ocr = "^0.4.12"
llama-index-multi-modal-llms-ollama = "^0.1.3"
llama-index-llms-groq = "^0.1.4"
gensim = "^4.3.2"
firebase-admin = "^6.5.0"
demjson3 = "^3.0.6"async def get_docs(self) -> List[Document]:
"""Get the parsed documents from llamaparse."""
documents = []
with tempfile.NamedTemporaryFile(delete=True) as temp:
temp.write(base64.b64decode(self.b64))
temp.flush()
temp.seek(0)
parser = LlamaParse(result_type=self.result_type)
documents = await parser.aload_data(temp.name)
return documentsError while parsing the file '/var/folders/d1/p4s8h3q552xbvq30g272vdbh0000gn/T/tmpqgr4rzp3': Currently, only the following file types are supported: ['.pdf', '.doc', '.docx', '.docm', '.dot', '.dotx', '.dotm', '.rtf', '.wps', '.wpd', '.sxw', '.stw', '.sxg', '.pages', '.mw', '.mcw', '.uot', '.uof', '.uos', '.uop', '.ppt', '.pptx', '.pot', '.pptm', '.potx', '.potm', '.key', '.odp', '.odg', '.otp', '.fopd', '.sxi', '.sti', '.epub', '.html', '.htm']
asyncio.run inside PropertyGraphIndex when running an APIPropertyGraphIndex while running an API that uses llamaindex. However, I encounter a RuntimeError because llamaindex is using asyncio.run inside the SchemaLLMPathExtractor, which conflicts with the running event loop in my API.RuntimeError: asyncio.run() cannot be called from a running event loop
return asyncio.run(self.acall(nodes, show_progress=show_progress, **kwargs))
kg_extractor: SchemaLLMPathExtractor = SchemaLLMPathExtractor( llm=llm, possible_entities=entity.entities.as_literal_typealias(), possible_relations=entity.relationships.as_literal_typealias(), kg_validation_schema=entity.validation_schema, strict=True, num_workers=4, ) index = PropertyGraphIndex.from_existing( property_graph_store=self.client, llm=llm, kg_extractors=[kg_extractor], use_async=False, embed_model=embeddings, show_progress=True, ) for document in documents: index.insert(document)
possible_entities = Optional[List[str]]????read a document from a folder/source -> create a "vector store" based on the documents -> querying the llm using the context of the created vector store