search

microsoft / graphrag

A modular graph-based Retrieval-Augmented Generation (RAG) system
https://microsoft.github.io/graphrag/
MIT License
17.43k stars 1.66k forks source link

[Bug]: Fail to run with a local LLM (Ollama) #1186

Open horaceho opened 1 day ago

horaceho commented 1 day ago

Do you need to file an issue?

Describe the bug

Fail to run with locally installed Ollama ...

Steps to reproduce

Ollama

ollama list
NAME                         ID              SIZE      MODIFIED       
llama3.1:latest              42182419e950    4.7 GB    31 seconds ago 
nomic-embed-text:latest      0a109f422b47    274 MB    3 days ago

Input

mkdir -p ./t2/input
cp the-heart-sutra.txt ./t2/input/

the-heart-sutra.txt

Init

python -m graphrag.index --init --root t2
Initializing project at t2

Modify settings.yaml to use local llama2:latest and nomic-embed-text:

llm:
  model: llama3.1:latest
  model_supports_json: true # recommended if this is available for your model.
  api_base: http://localhost:11434/v1
embeddings:
  llm:
    model: nomic-embed-text
    api_base: http://localhost:11434/api

Index

python -m graphrag.index --root t2

Expected Behavior

GraphRAG should index the text file ...

GraphRAG Config Used


encoding_model: cl100k_base
skip_workflows: []
llm:
  api_key: ${GRAPHRAG_API_KEY}
  type: openai_chat # or azure_openai_chat
  model: llama3.1:latest
  model_supports_json: true # recommended if this is available for your model.
  # max_tokens: 4000
  # request_timeout: 180.0
  api_base: http://localhost:11434/v1
  # api_version: 2024-02-15-preview
  # organization: <organization_id>
  # deployment_name: <azure_model_deployment_name>
  # tokens_per_minute: 150_000 # set a leaky bucket throttle
  # requests_per_minute: 10_000 # set a leaky bucket throttle
  # max_retries: 10
  # max_retry_wait: 10.0
  # sleep_on_rate_limit_recommendation: true # whether to sleep when azure suggests wait-times
  # concurrent_requests: 25 # the number of parallel inflight requests that may be made
  # temperature: 0 # temperature for sampling
  # top_p: 1 # top-p sampling
  # n: 1 # Number of completions to generate

parallelization:
  stagger: 0.3
  # num_threads: 50 # the number of threads to use for parallel processing

async_mode: threaded # or asyncio

embeddings:
  ## parallelization: override the global parallelization settings for embeddings
  async_mode: threaded # or asyncio
  # target: required # or all
  # batch_size: 16 # the number of documents to send in a single request
  # batch_max_tokens: 8191 # the maximum number of tokens to send in a single request
  llm:
    api_key: ${GRAPHRAG_API_KEY}
    type: openai_embedding # or azure_openai_embedding
    model: nomic-embed-text
    api_base: http://localhost:11434/api
    # api_version: 2024-02-15-preview
    # organization: <organization_id>
    # deployment_name: <azure_model_deployment_name>
    # tokens_per_minute: 150_000 # set a leaky bucket throttle
    # requests_per_minute: 10_000 # set a leaky bucket throttle
    # max_retries: 10
    # max_retry_wait: 10.0
    # sleep_on_rate_limit_recommendation: true # whether to sleep when azure suggests wait-times
    # concurrent_requests: 25 # the number of parallel inflight requests that may be made

chunks:
  size: 1200
  overlap: 100
  group_by_columns: [id] # by default, we don't allow chunks to cross documents

input:
  type: file # or blob
  file_type: text # or csv
  base_dir: "input"
  file_encoding: utf-8
  file_pattern: ".*\\.txt$"

cache:
  type: file # or blob
  base_dir: "cache"
  # connection_string: <azure_blob_storage_connection_string>
  # container_name: <azure_blob_storage_container_name>

storage:
  type: file # or blob
  base_dir: "output/${timestamp}/artifacts"
  # connection_string: <azure_blob_storage_connection_string>
  # container_name: <azure_blob_storage_container_name>

reporting:
  type: file # or console, blob
  base_dir: "output/${timestamp}/reports"
  # connection_string: <azure_blob_storage_connection_string>
  # container_name: <azure_blob_storage_container_name>

entity_extraction:
  ## strategy: fully override the entity extraction strategy.
  ##   type: one of graph_intelligence, graph_intelligence_json and nltk
  ## llm: override the global llm settings for this task
  ## parallelization: override the global parallelization settings for this task
  ## async_mode: override the global async_mode settings for this task
  prompt: "prompts/entity_extraction.txt"
  entity_types: [organization,person,geo,event]
  max_gleanings: 1

summarize_descriptions:
  ## llm: override the global llm settings for this task
  ## parallelization: override the global parallelization settings for this task
  ## async_mode: override the global async_mode settings for this task
  prompt: "prompts/summarize_descriptions.txt"
  max_length: 500

claim_extraction:
  ## llm: override the global llm settings for this task
  ## parallelization: override the global parallelization settings for this task
  ## async_mode: override the global async_mode settings for this task
  # enabled: true
  prompt: "prompts/claim_extraction.txt"
  description: "Any claims or facts that could be relevant to information discovery."
  max_gleanings: 1

community_reports:
  ## llm: override the global llm settings for this task
  ## parallelization: override the global parallelization settings for this task
  ## async_mode: override the global async_mode settings for this task
  prompt: "prompts/community_report.txt"
  max_length: 2000
  max_input_length: 8000

cluster_graph:
  max_cluster_size: 10

embed_graph:
  enabled: false # if true, will generate node2vec embeddings for nodes
  # num_walks: 10
  # walk_length: 40
  # window_size: 2
  # iterations: 3
  # random_seed: 597832

umap:
  enabled: false # if true, will generate UMAP embeddings for nodes

snapshots:
  graphml: false
  raw_entities: false
  top_level_nodes: false

local_search:
  # text_unit_prop: 0.5
  # community_prop: 0.1
  # conversation_history_max_turns: 5
  # top_k_mapped_entities: 10
  # top_k_relationships: 10
  # llm_temperature: 0 # temperature for sampling
  # llm_top_p: 1 # top-p sampling
  # llm_n: 1 # Number of completions to generate
  # max_tokens: 12000

global_search:
  # llm_temperature: 0 # temperature for sampling
  # llm_top_p: 1 # top-p sampling
  # llm_n: 1 # Number of completions to generate
  # max_tokens: 12000
  # data_max_tokens: 12000
  # map_max_tokens: 1000
  # reduce_max_tokens: 2000
  # concurrency: 32

Logs and screenshots

Logging enabled at /home/ohho/codes/python/try/graphrag/t2/output/indexing-engine.log
/home/ohho/conda/envs/graphrag/lib/python3.10/site-packages/numpy/core/fromnumeric.py:59: FutureWarning: 
'DataFrame.swapaxes' is deprecated and will be removed in a future version. Please use 'DataFrame.transpose' instead.
  return bound(*args, **kwds)
๐Ÿš€ create_base_text_units
                                 id  ... n_tokens
0  6d2823d11f18b1dbb3e9c4d3a1a7b3bf  ...      401

[1 rows x 5 columns]
๐Ÿš€ create_base_extracted_entities
                                        entity_graph
0  <graphml xmlns="http://graphml.graphdrawing.or...
๐Ÿš€ create_summarized_entities
                                        entity_graph
0  <graphml xmlns="http://graphml.graphdrawing.or...
โŒ create_base_entity_graph
None
โ ‡ GraphRAG Indexer 
โ”œโ”€โ”€ Loading Input (text) - 1 files loaded (0 filtered) โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ” 100% 0:00:00 0:00:00
โ”œโ”€โ”€ create_base_text_units
โ”œโ”€โ”€ create_base_extracted_entities
โ”œโ”€โ”€ create_summarized_entities
โ””โ”€โ”€ create_base_entity_graph
โŒ Errors occurred during the pipeline run, see logs for more details.

Additional Information

horaceho commented 1 day ago

"Error Invoking LLM"

horaceho commented 1 day ago

Embeddings API

curl http://localhost:11434/api/embeddings -d '{
>  "model": "nomic-embed-text",
>  "prompt": "Good morning"
> }'

{"embedding":[-0.9532470703125,-0.457611083984375,-3.6005859375,-0.163177490234375,-0.8304443359375,0.8436279296875,0.058013916015625,-0.48779296875,-0.018356800079345703,-1.24462890625,1.359619140625,1.21435546875,1.44140625,1.5159912109375,0.13267135620117188,0.0018310546875,0.4750518798828125,-0.78692626953125,-0.859893798828125,0.2451019287109375,-0.203155517578125,-0.639617919921875,-0.5706787109375,-0.975341796875,2.3072509765625,0.2158203125,-0.3594932556152344,1.658447265625,-0.6072998046875,0.0201263427734375,1.76953125,-0.388092041015625,-0.047771453857421875,-1.15771484375,-0.362335205078125,-0.082794189453125,-0.5257110595703125,-0.2566070556640625,0.230804443359375,-0.51434326171875,1.450927734375,-0.13272857666015625,0.38324737548828125,-0.6046142578125,0.47967529296875,0.0544891357421875,-0.19964599609375,0.7012939453125,1.388916015625,-1.66015625,-0.407958984375,-1.40576171875,0.1427450180053711,-1.119873046875,0.919525146484375,0.8438720703125,2.2939453125,0.01105499267578125,-0.0741424560546875,0.39068603515625,2.30322265625,0.45452880859375,-0.5588779449462891,1.159912109375,0.37579345703125,-0.43837738037109375,0.300567626953125,1.1546630859375,-0.21026611328125,1.07537841796875,1.288818359375,-0.04261016845703125,-0.405517578125,0.039306640625,0.047607421875,0.24953460693359375,0.0952911376953125,-0.57061767578125,-0.583740234375,-0.73150634765625,0.85992431640625,-0.638427734375,1.0047607421875,-0.3076629638671875,0.88616943359375,-0.3418426513671875,0.357086181640625,-0.35013866424560547,-0.408721923828125,-0.09002685546875,1.9013671875,-0.043849945068359375,0.14818572998046875,0.440948486328125,-0.85498046875,-0.02426910400390625,0.22553253173828125,1.5166015625,-0.9599609375,-1.1292724609375,1.220458984375,-0.5972900390625,-0.664215087890625,0.23602294921875,1.3953857421875,0.85760498046875,-1.29296875,-0.50775146484375,-1.97509765625,-0.72607421875,-1.34619140625,-0.31353759765625,-0.15783309936523438,-1.147705078125,0.07466888427734375,-0.51458740234375,2.057861328125,-1.994384765625,1.1192626953125,0.42047119140625,-0.9381103515625,-0.417510986328125,0.282257080078125,-0.1992340087890625,0.64166259765625,0.65594482421875,-1.835693359375,-1.1243896484375,-0.118255615234375,0.526153564453125,1.30615234375,-1.1182861328125,-0.32598876953125,0.3839569091796875,-0.7340087890625,1.238525390625,0.78912353515625,-0.3046722412109375,1.561279296875,0.4564208984375,0.79547119140625,0.978515625,-0.19110107421875,-1.196533203125,-0.0543060302734375,-0.211273193359375,0.9215087890625,-1.163330078125,-0.22772216796875,0.54144287109375,-0.539581298828125,0.367156982421875,-0.2320098876953125,0.84912109375,0.48486328125,-1.0509033203125,-0.4037933349609375,-0.13262939453125,1.3302001953125,0.40692138671875,1.545654296875,-0.30770111083984375,-1.563232421875,0.3138427734375,0.066162109375,-1.21490478515625,-1.26806640625,0.32611083984375,0.06850433349609375,1.70068359375,-0.43174171447753906,-0.07520866394042969,-1.11328125,-1.3681640625,0.8704833984375,-0.48931884765625,-0.57098388671875,-0.7716064453125,0.7298583984375,-0.59808349609375,-0.33929443359375,-0.414581298828125,0.1025390625,1.2266845703125,0.42816162109375,-0.807861328125,0.361602783203125,-0.8507080078125,-2.0341796875,-0.703857421875,0.12890625,0.47442626953125,-1.19384765625,-0.588134765625,0.01586151123046875,0.256378173828125,0.36114501953125,0.2126922607421875,2.204833984375,0.22434234619140625,0.09332275390625,-0.6929931640625,0.1107177734375,0.598876953125,0.54254150390625,2.134521484375,0.1041412353515625,1.48681640625,-0.1275634765625,0.292236328125,0.7822265625,0.2671966552734375,0.09737205505371094,-0.46954345703125,0.1925201416015625,0.02885150909423828,0.045196533203125,0.33062744140625,-1.032958984375,0.9552001953125,0.102752685546875,0.927734375,0.0724029541015625,-0.7486572265625,1.1007080078125,-0.3365478515625,-0.419708251953125,-1.0091552734375,-1.1881103515625,0.3725128173828125,-0.55859375,-0.7355880737304688,0.3479156494140625,0.101043701171875,0.66864013671875,0.633544921875,1.222900390625,1.385986328125,0.6439208984375,-0.8426513671875,-0.30462646484375,0.97802734375,0.3501625061035156,-0.454193115234375,-1.751708984375,0.363800048828125,0.08476495742797852,-0.432220458984375,-0.9049072265625,0.341552734375,0.42474365234375,-0.383758544921875,0.1580333709716797,-0.30384063720703125,0.488037109375,-1.6123046875,-0.09548091888427734,1.3516845703125,0.05536651611328125,-0.27874755859375,0.1202392578125,-2.123779296875,-0.3704833984375,-0.88446044921875,1.1922607421875,0.38851165771484375,0.23211669921875,0.4566650390625,-0.078399658203125,-1.5205078125,0.53070068359375,0.0497589111328125,1.372802734375,0.9677734375,-1.189208984375,-0.6856689453125,-1.2099609375,0.261993408203125,-1.925537109375,0.79150390625,-0.405059814453125,0.17988014221191406,-0.8179931640625,-0.14848709106445312,-0.506866455078125,0.9002685546875,0.9677734375,0.05352783203125,0.07342720031738281,0.22979736328125,1.627685546875,1.1768798828125,0.544219970703125,0.9749755859375,-0.406402587890625,-0.03668212890625,1.7470703125,0.003173828125,0.46917724609375,-0.552886962890625,-0.2722930908203125,0.82598876953125,1.02117919921875,-0.50787353515625,-0.3562650680541992,0.5240449905395508,0.4923095703125,0.383941650390625,-0.025167465209960938,-0.5028076171875,-0.6953353881835938,0.5027313232421875,-0.8018798828125,0.2240619659423828,-0.63861083984375,1.348876953125,0.35028076171875,0.68743896484375,1.239501953125,0.794921875,-0.1614227294921875,-0.371307373046875,-0.1471710205078125,-1.0521240234375,-0.31060791015625,0.06662368774414062,0.1534900665283203,1.951416015625,1.0489501953125,-0.404144287109375,0.0746612548828125,0.50347900390625,-0.639251708984375,-0.03094482421875,-0.86328125,0.802001953125,0.32769203186035156,-0.71337890625,-1.05181884765625,0.988037109375,-0.546051025390625,-0.65692138671875,0.4254798889160156,-1.20751953125,-1.111083984375,-0.21834754943847656,-0.4756431579589844,-0.6209716796875,0.2401123046875,-0.285430908203125,-1.0523681640625,0.9193115234375,-0.221282958984375,-0.11413383483886719,-0.08739852905273438,-0.175201416015625,0.113983154296875,1.1822509765625,0.9268798828125,-0.55474853515625,-0.49102783203125,-0.6048583984375,0.051971435546875,0.09192276000976562,-0.8843994140625,0.2191162109375,0.170654296875,0.38893890380859375,0.11091995239257812,0.0906524658203125,0.92236328125,0.246551513671875,0.26116943359375,0.570587158203125,1.381103515625,0.936767578125,-0.8555908203125,0.032196044921875,-0.4095458984375,0.2176055908203125,-0.8021240234375,-0.62060546875,0.268707275390625,-0.21563720703125,-1.05340576171875,1.1646728515625,0.433837890625,0.1472930908203125,-1.6845703125,-0.3991875648498535,0.517425537109375,-1.2269287109375,-1.0855712890625,0.659423828125,0.21179580688476562,-0.2398681640625,0.934661865234375,-0.3683624267578125,-0.755615234375,0.355560302734375,-0.3685150146484375,-0.38604736328125,0.04891301691532135,-0.72802734375,-0.62030029296875,0.1968536376953125,-1.19775390625,0.34820556640625,1.59375,-0.7813720703125,0.647125244140625,-0.22021484375,0.388458251953125,-0.9110107421875,-0.4603118896484375,0.7662353515625,0.360321044921875,-0.2811431884765625,-0.084381103515625,0.74566650390625,0.126922607421875,1.301513671875,-0.0454864501953125,0.13364797830581665,0.17798423767089844,1.440673828125,1.289306640625,-0.52252197265625,-1.49658203125,-2.004638671875,0.10943603515625,0.543701171875,0.40240478515625,-0.04791259765625,-0.556060791015625,0.06923675537109375,-0.083465576171875,0.8189697265625,-0.2060699462890625,0.57965087890625,1.29345703125,-0.1748046875,-0.69873046875,0.208160400390625,0.99072265625,3.18505859375,1.74853515625,-0.8223876953125,-1.000244140625,0.8284912109375,-0.053436279296875,0.81634521484375,0.4374542236328125,-0.059441566467285156,1.89599609375,-0.2098541259765625,0.48358154296875,0.91162109375,1.1109619140625,0.687744140625,1.1767578125,0.31285858154296875,-0.511505126953125,0.126983642578125,-0.818603515625,-1.1549072265625,-1.33642578125,0.8125,0.8345947265625,1.671142578125,-1.0694580078125,0.422515869140625,-0.61669921875,-0.854736328125,-0.392303466796875,-0.21673583984375,-0.490386962890625,-0.2745819091796875,0.338348388671875,1.769775390625,0.7159423828125,0.1293487548828125,-0.32505035400390625,-0.96978759765625,0.48663330078125,1.55810546875,1.42333984375,1.26806640625,-0.10715484619140625,-1.707275390625,0.732666015625,0.4626274108886719,0.8072509765625,-0.18320846557617188,0.900634765625,0.205902099609375,-1.2447509765625,0.5501375198364258,-0.067626953125,-0.30220794677734375,-1.546630859375,-0.3255805969238281,-0.28021240234375,-0.236236572265625,0.10071563720703125,-0.062450408935546875,-1.40185546875,-0.48760986328125,-0.7615966796875,0.1539459228515625,-0.463836669921875,-0.39532470703125,0.3518218994140625,1.224609375,0.9971923828125,-0.95458984375,0.25048828125,0.412689208984375,-0.8297214508056641,0.9842529296875,0.6094970703125,0.315765380859375,-0.3290557861328125,0.22796630859375,-0.34637451171875,0.7667236328125,-1.164306640625,-1.226318359375,0.36822509765625,-1.044677734375,0.197113037109375,0.621978759765625,0.59222412109375,0.2056427001953125,0.86346435546875,-0.60626220703125,-0.4264373779296875,0.67510986328125,0.09618759155273438,0.20380306243896484,-0.39398193359375,0.339813232421875,0.20688247680664062,0.17503929138183594,-0.3899383544921875,0.5027618408203125,-2.31494140625,0.0726776123046875,0.025909423828125,-0.476226806640625,0.15985107421875,-2.36962890625,0.056758880615234375,0.23986053466796875,-0.0033742189407348633,-0.983154296875,-0.5360374450683594,-0.4186553955078125,0.16510009765625,-0.3431129455566406,0.37799072265625,-0.05168914794921875,0.1660003662109375,0.1323089599609375,0.98681640625,0.21869373321533203,0.14003372192382812,-0.153839111328125,-0.7457275390625,-0.603759765625,-1.2054443359375,-0.0327606201171875,0.57861328125,0.71240234375,-0.8106689453125,-0.43511199951171875,-0.5113525390625,0.47777557373046875,-1.657470703125,-0.55712890625,0.9425048828125,-0.756103515625,0.9146728515625,0.98291015625,-0.29189300537109375,-0.7532958984375,-0.99072265625,-0.638763427734375,1.184814453125,0.184173583984375,0.39361572265625,1.0731201171875,0.047576904296875,-0.9503173828125,0.0052642822265625,0.224365234375,-0.20470428466796875,-1.67767333984375,-1.4921875,-1.287109375,-0.3265228271484375,-0.6295166015625,1.491455078125,-0.75732421875,-0.559326171875,1.3270263671875,0.350982666015625,0.53851318359375,-0.054534912109375,0.172088623046875,-0.40252685546875,1.511474609375,0.226959228515625,0.3145751953125,0.9840087890625,-0.9000244140625,0.71026611328125,0.0608062744140625,0.3066864013671875,-0.8043212890625,-0.41606903076171875,-0.3103790283203125,1.13836669921875,0.1932373046875,0.55682373046875,0.7596435546875,-0.6771240234375,-0.8277587890625,-0.77105712890625,0.957275390625,0.1772594451904297,-1.32958984375,-1.6732177734375,-0.9344482421875,0.1116943359375,-0.0357666015625,0.9981689453125,0.000148773193359375,-1.005615234375,0.66485595703125,0.49478912353515625,-0.3583221435546875,-0.16078567504882812,0.420166015625,0.277557373046875,-0.373138427734375,1.063720703125,0.20745849609375,1.492919921875,-0.130462646484375,1.55908203125,-0.173583984375,0.849365234375,0.0257568359375,-0.13447237014770508,-1.0125732421875,0.685302734375,-0.65789794921875,-0.1214752197265625,-2.06298828125,0.13034439086914062,-1.44873046875,-0.92822265625,0.026153564453125,0.3846435546875,-0.3443145751953125,-0.7200927734375,1.0894775390625,-1.86572265625,-0.173095703125,0.3957347869873047,0.778076171875,-0.5191192626953125,0.237274169921875,-0.492462158203125,0.44078826904296875,-0.162872314453125,-0.2239990234375,0.394622802734375,-0.7061767578125,-0.04705810546875,0.297607421875,-0.5181884765625,0.57061767578125,0.11334228515625,-0.00984954833984375,0.06342697143554688,0.1662750244140625,-0.292388916015625,-1.330078125,0.43804931640625,-0.547882080078125,-0.3859710693359375,-0.46136474609375,-0.742431640625,0.304351806640625,0.222320556640625,-0.219635009765625,-0.57855224609375,0.197998046875,-0.807861328125,0.1013031005859375,-0.43292236328125,0.8463134765625,-1.099365234375,-0.3472747802734375,0.1977081298828125,-0.5777587890625,-0.1681976318359375,-0.2085113525390625,-0.59197998046875,-0.3203125,0.70428466796875,0.474609375,1.1611328125,-0.890380859375,-0.55572509765625,0.3564605712890625,-0.12945556640625,1.803466796875,2.36376953125,0.398681640625,-1.327392578125,0.1839599609375,-0.612030029296875,-0.6049652099609375,-0.17806053161621094,-1.82421875,0.56988525390625,-1.214111328125,0.77215576171875,-1.1741943359375,0.057903289794921875,2.065185546875,0.21588134765625,0.31290435791015625,-1.765625,0.16321945190429688,-0.61279296875,0.15477752685546875,-0.53448486328125,-1.2510986328125,0.0748138427734375,0.1174468994140625,0.4141845703125,-0.22984695434570312,0.7135009765625,1.0921630859375,-0.14450454711914062,-1.000732421875,-0.235260009765625,0.74200439453125,-1.0675048828125,-0.763214111328125,-0.713134765625,0.8084716796875,0.72296142578125,0.315704345703125,1.3758544921875,-0.157318115234375,1.0859375,-0.30115509033203125,0.72015380859375,0.2470703125,-0.65179443359375,-0.1112213134765625,-1.846923828125,0.64300537109375]}

balezeauquentin commented 1 day ago

Hello,

Can you provide us your logs ?

Anyway, you can check those threads it helped me a lot when I had problems with Ollama #619, #650.

619 is for query embedding and #650 is for embedding when you are creating the graph.

horaceho commented 22 hours ago

Logs

indexing-engine.log logs.json

balezeauquentin commented 21 hours ago

Verify the name of your models, seems like llama3.1 isn't pulled on your Ollama instance.

user@VRH035941:~/.venv/graphrag$ ollama list 
NAME                            ID              SIZE    MODIFIED    
mxbai-embed-large:latest        468836162de7    669 MB  6 days ago 
nomic-embed-text:latest         0a109f422b47    274 MB  10 days ago
mistral:latest                  f974a74358d6    4.1 GB  10 days ago
llama3.1:latest                 42182419e950    4.7 GB  10 days ago
horaceho commented 21 hours ago

@balezeauquentin sorry for the outdated info (I switched to a different model):

$ ollama list 
NAME                         ID              SIZE      MODIFIED      
llama3.1:latest              42182419e950    4.7 GB    3 minutes ago    
llama3.1-32k-q8:latest       ec0697ee6936    8.5 GB    6 hours ago      
mistral:latest               f974a74358d6    4.1 GB    9 hours ago      
llama2:latest                78e26419b446    3.8 GB    10 hours ago     
nomic-embed-text:latest      0a109f422b47    274 MB    4 days ago       
llama3.1:8b-instruct-q8_0    b158ded76fa0    8.5 GB    4 days ago 
$ python -m graphrag.index --root t2
Logging enabled at /home/ohho/codes/python/try/graphrag/t2/output/indexing-engine.log
/home/ohho/conda/envs/graphrag/lib/python3.10/site-packages/numpy/core/fromnumeric.py:59: FutureWarning: 
'DataFrame.swapaxes' is deprecated and will be removed in a future version. Please use 'DataFrame.transpose' instead.
  return bound(*args, **kwds)
๐Ÿš€ create_base_text_units
                                 id  ... n_tokens
0  6d2823d11f18b1dbb3e9c4d3a1a7b3bf  ...      401

[1 rows x 5 columns]
๐Ÿš€ create_base_extracted_entities
                                        entity_graph
0  <graphml xmlns="http://graphml.graphdrawing.or...
๐Ÿš€ create_summarized_entities
                                        entity_graph
0  <graphml xmlns="http://graphml.graphdrawing.or...
โŒ create_base_entity_graph
None
โ ‡ GraphRAG Indexer 
โ”œโ”€โ”€ Loading Input (text) - 1 files loaded (0 filtered) โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ” 100% 0:00:00 0:00:00
โ”œโ”€โ”€ create_base_text_units
โ”œโ”€โ”€ create_base_extracted_entities
โ”œโ”€โ”€ create_summarized_entities
โ””โ”€โ”€ create_base_entity_graph
โŒ Errors occurred during the pipeline run, see logs for more details.

Updated logs

indexing-engine.log stats.json logs.json (zero byte empty file, please ignore)

balezeauquentin commented 21 hours ago

I can't open your logs file, I don't get why can you send it again please.

<Error>
  <Code>InvalidRange</Code>
  <Message>The requested range is not satisfiable</Message>
  <RangeRequested>bytes=0-10485759</RangeRequested>
  <ActualObjectSize>0</ActualObjectSize>
  <RequestId>5Q4X6TPBJE7NYK7R</RequestId>
  <HostId>
    PUR02jTh8ibmw+Bg/Nj45Z/OERZyIHP9UzEBR9IcF2N4GYXqv/SEc41zKz1lZuU9gM6T4dbmuL4=
  </HostId>
</Error>
horaceho commented 21 hours ago

The logs.json is an empty file:

$ ls -al t2/output/
total 52
drwxrwxr-x 2 ohho ohho  4096 Sep 23 20:40 .
drwxrwxr-x 6 ohho ohho  4096 Sep 23 20:40 ..
-rw-rw-r-- 1 ohho ohho  3433 Sep 23 20:40 create_base_extracted_entities.parquet
-rw-rw-r-- 1 ohho ohho 14725 Sep 23 20:40 create_base_text_units.parquet
-rw-rw-r-- 1 ohho ohho  3433 Sep 23 20:40 create_summarized_entities.parquet
-rw-rw-r-- 1 ohho ohho 16347 Sep 23 20:40 indexing-engine.log
-rw-rw-r-- 1 ohho ohho     0 Sep 23 20:40 logs.json
-rw-rw-r-- 1 ohho ohho  1076 Sep 23 20:40 stats.json
balezeauquentin commented 21 hours ago

And your RAG pipeline isn't working ?

wy371900521 commented 20 hours ago

่ฟ™ไธช้—ฎ้ข˜็‰นๅˆซๆถๅฟƒ,ๅ›ฐๆ‰ฐๆˆ‘ๅฅฝๅ‡ ๅคฉไบ†

9prodhi commented 13 hours ago

This should resolve the embedding issue you encountered. I faced a similar problem due to the different embedding format used by OpenAI. After installing the required dependencies, you can run the file as follows:

# repo: https://github.com/9prodhi/EmbedAdapter/blob/main/ollama_serv.py
python ollama_serv.py

Also do not forget to change embedding llm api_base setting.

horaceho commented 3 hours ago

After reducing the chunks size:

chunks:
  size: 300

it pass create_base_entity_graph and stopped at create_final_entities:

$ python -m graphrag.index --root t4
Logging enabled at /home/ohho/codes/python/try/graphrag/t4/output/indexing-engine.log
/home/ohho/conda/envs/graphrag/lib/python3.10/site-packages/numpy/core/fromnumeric.py:59: FutureWarning: 
'DataFrame.swapaxes' is deprecated and will be removed in a future version. Please use 'DataFrame.transpose' instead.
  return bound(*args, **kwds)
๐Ÿš€ create_base_text_units
                                 id  ... n_tokens
0  ac67bbf50ea59187cea5947b4e482e79  ...      300
1  0650fd69f66ac0d668f05d218942ac62  ...      201
2  7d902ccc1d6328cdf06ab78c6a43b5f8  ...        1

[3 rows x 5 columns]
๐Ÿš€ create_base_extracted_entities
                                        entity_graph
0  <graphml xmlns="http://graphml.graphdrawing.or...
๐Ÿš€ create_summarized_entities
                                        entity_graph
0  <graphml xmlns="http://graphml.graphdrawing.or...
๐Ÿš€ create_base_entity_graph
   level                                    clustered_graph
0      0  <graphml xmlns="http://graphml.graphdrawing.or...
/home/ohho/conda/envs/graphrag/lib/python3.10/site-packages/numpy/core/fromnumeric.py:59: FutureWarning: 
'DataFrame.swapaxes' is deprecated and will be removed in a future version. Please use 'DataFrame.transpose' instead.
  return bound(*args, **kwds)
โŒ create_final_entities
None
โ ™ GraphRAG Indexer 
โ”œโ”€โ”€ Loading Input (text) - 1 files loaded (0 filtered) โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ” 100% 0:00:00 0:00:00
โ”œโ”€โ”€ create_base_text_units
โ”œโ”€โ”€ create_base_extracted_entities
โ”œโ”€โ”€ create_summarized_entities
โ”œโ”€โ”€ create_base_entity_graph
โ””โ”€โ”€ create_final_entities
โŒ Errors occurred during the pipeline run, see logs for more details.

settings.yaml.txt indexing-engine.log logs.json stats.json

jackiezhangcn commented 1 hour ago

File "/home/zhangyj/anaconda3/envs/graphrag/lib/python3.12/site-packages/graphrag/llm/openai/openai_chat_llm.py", line 56, in _execute_llm return completion.choices[0].message.content


TypeError: 'NoneType' object is not subscriptable

seems no response generated from LLM (Ollama model), but don't know how to debug