Closed c0derm4n closed 1 month ago
my setting.yaml is
embeddings:
## parallelization: override the global parallelization settings for embeddings
async_mode: threaded # or asyncio
llm:
api_key: ${GRAPHRAG_API_KEY}
type: openai_embedding # or azure_openai_embedding
model: chatfire/bge-m3:q8_0
api_base: http://localhost:11434/api
it can run without the error about model "nomic-embed-text" not found, try pulling it first 我的配置文件可以运行并且没有未发现模型的报错 u can check whether the setting.yaml in the ragtest dir can be changed 首先, 检查你在ragtest文件夹下的配置文件是否修改 and whether the cache has been deleted 你可以尝试清除缓存文件夹重新构建你的项目
finally, my project has a error
{"type": "error", "data": "Error running pipeline!", "stack": "Traceback (most recent call last):\n File \"/home/xuhe/task/2024outsource10/graphrag-local-ollama/graphrag/index/run.py\", line 323, in run_pipeline\n result = await workflow.run(context, callbacks)\n File \"/home/xuhe/miniconda3/envs/graphrag-ollama-local/lib/python3.10/site-packages/datashaper/workflow/workflow.py\", line 369, in run\n timing = await self._execute_verb(node, context, callbacks)\n File \"/home/xuhe/miniconda3/envs/graphrag-ollama-local/lib/python3.10/site-packages/datashaper/workflow/workflow.py\", line 410, in _execute_verb\n result = node.verb.func(**verb_args)\n File \"/home/xuhe/miniconda3/envs/graphrag-ollama-local/lib/python3.10/site-packages/datashaper/engine/verbs/window.py\", line 73, in window\n window = __window_function_map[window_operation](input_table[column])\n File \"/home/xuhe/miniconda3/envs/graphrag-ollama-local/lib/python3.10/site-packages/pandas/core/frame.py\", line 4102, in __getitem__\n indexer = self.columns.get_loc(key)\n File \"/home/xuhe/miniconda3/envs/graphrag-ollama-local/lib/python3.10/site-packages/pandas/core/indexes/range.py\", line 417, in get_loc\n raise KeyError(key)\nKeyError: 'community'\n", "source": "'community'", "details": null}
it looks like a error for language model. I don't know how to solve this problem
The issue is on line 31 of the file "graphrag\llm\openai\openai_embeddings_llm.py", there is an uncleaned "nomic-embed-text". Please change it to the name of the model you are currently using.
Fixed this, now you can specify the model from settings.yaml.
The configuration has been modified in the yaml file to switch to another embedding model, but it's not taking effect!
17:31:12,217 datashaper.workflow.workflow ERROR Error executing verb "text_embed" in create_final_entities: model "nomic-embed-text" not found, try pulling it first
在yaml文件中修改了配置切换为其他的嵌入模型,但是不生效!