FAQs on TigerGraph copilot

Puneet2 · July 15, 2024, 11:04am

How to use “Ollama” instead of OpenAI.
[CoPilot/docs/notebooks/SupportAIDemo.ipynb at main · tigergraph/CoPilot · GitHub] (CoPilot/docs/notebooks/SupportAIDemo.ipynb at main · tigergraph/CoPilot · GitHub) In this SupportAI notebook
What are the flexible options to configure document question answering (DQA) on:
PDF
CSV
JSON
And in this above “SupportAIDemo,” do we need to mention the Pytigergraph documentation URL to ingest the data for DQA?
like this : {“url”: “https://docs.tigergraph.com/pytigergraph/current/intro/”, “content”: “Text of the document”}

Parker_Erickson · July 15, 2024, 1:39pm

Hi Puneet,

For Ollama, simply use a llm_config.json file that looks something like this:

{
    "model_name": "llama3",
    "embedding_service": {
        "embedding_model_service": "openai",
        "authentication_configuration": {
            "OPENAI_API_KEY": "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"
        }
    },
    "completion_service": {
        "llm_service": "ollama",
        "llm_model": "llama3",
        "model_kwargs": {
            "temperature": 0.0000001
        },
        "prompt_path": "./app/prompts/openai_gpt4/"
    }
}

Note, there is not an Ollama embedding service, and you can change the “llm_model” field of the completion service to a different model name available on Ollama. Then export the path of this config json to a LLM_CONFIG environment variable (the CoPilot repo has more details for this part).

Unfortunately we only support JSON and CSV documents for SupportAI thus far, however a wider variety of document types we are considering. The initial JSON and CSV document types are due to TigerGraph natively supporting those file types in loading jobs. You do not need to mention the URL, however there needs to be some notion of “primary key” in your JSON documents. This would be the value of the doc_id_field found in the createDocumentIngest method of the notebook.

Puneet2 · July 15, 2024, 2:37pm

ok @Parker_Erickson thanks for your reply
so, in the given SupportAIDemo notebook
which CSV or JSON we are referring in the example?
can you please provide the **doc_id_field**
res = conn.ai.createDocumentIngest(data_source = “s3”,data_source_config = {“aws_access_key”: “YOUR_AWS_ACCESS_KEY”, “aws_secret_key”: “YOUR_AWS_SECRET_KEY”},loader_config = {“doc_id_field”: “url”, “content_field”: “content”},file_format = “json”)

so that we can run that notebook end to end,
or we need to use our own ?

Thanks

Puneet2 · July 15, 2024, 3:15pm

{
“model_name”: “GPT-4”,
“embedding_service”: {
“embedding_model_service”: “openai”,
“authentication_configuration”: {
“OPENAI_API_KEY”: “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”
}
},
“completion_service”: {
“llm_service”: “ollama”,
“llm_model”: “llama3”,
“model_kwargs”: {
“temperature”: 0.0000001
},
“model_kwargs”: {
“temperature”: 0
},
“prompt_path”: “./app/prompts/openai_gpt4/”
}
}

after setting this in llm_config.json
we are getting below error
Ollama is running on localhost:11434 with the model name “llama3”


File "/usr/local/lib/python3.11/site-packages/anyio/_backends/_asyncio.py", line 877, in run_sync_in_worker_thread
    return await future
           ^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/anyio/_backends/_asyncio.py", line 807, in run
    result = context.run(func, *args)
             ^^^^^^^^^^^^^^^^^^^^^^^^
  File "/code/app/routers/inquiryai.py", line 106, in retrieve_answer
    raise Exception("LLM Completion Service Not Supported")
Exception: LLM Completion Service Not Supported

Parker_Erickson · July 15, 2024, 3:16pm

You need to use your own unfortunately, as TigerGraph data streaming connectors don’t support non-authenticated AWS buckets. Here is an excerpt of our pyTG docs in JSON form though:

{"url": "https://docs.tigergraph.com/pytigergraph/current/gds/", "content": "GDS Functions\nGraph Data Science (GDS) functions perform machine learning tasks such as the following:\nLoading data from a TigerGraph database in batches\nData Loaders\nSplitting vertices into training, test, and validation sets\nData Splitting Functions\nGathering metrics for Graph Neural Network (GNN) predictions\npyTigerGraph GDS Metrics\nInstalling and running Graph Data Science algorithms\nFeaturizer", "links": ["https://docs.tigergraph.com/pytigergraph/current/contributing/", "https://docs.tigergraph.com/pytigergraph/current/getting-started/", "https://docs.tigergraph.com/pytigergraph/current/gds/splitters", "https://docs.tigergraph.com/pytigergraph/current/getting-started/connection", "https://docs.tigergraph.com/pytigergraph/current/core-functions/edge", "https://docs.tigergraph.com/tigergraph-server/current/gsql-shell/web", "https://docs.tigergraph.com/pytigergraph/1.3/gds/", "https://docs.tigergraph.com/pytigergraph/current/core-functions/gsql", "https://docs.tigergraph.com/pytigergraph/current/core-functions/schema", "https://docs.tigergraph.com/pytigergraph/current/core-functions/vertex", "https://docs.tigergraph.com/pytigergraph/current/core-functions/path", "https://docs.tigergraph.com/gui/current/intro/", "https://docs.tigergraph.com/pytigergraph/current/release-notes/legacy-tg-versions", "https://docs.tigergraph.com/tigergraph-server/current/intro/", "https://docs.tigergraph.com/pytigergraph/1.4/gds/", "https://docs.tigergraph.com/pytigergraph/current/getting-started/install", "https://docs.tigergraph.com/pytigergraph/current/datasets/datasets_object", "https://docs.tigergraph.com/insights/current/intro/", "https://docs.tigergraph.com/ml-workbench/current/intro/", "https://docs.tigergraph.com/pytigergraph/current/core-functions/udt", "https://docs.tigergraph.com/pytigergraph/current/gds/graphsage", "https://docs.tigergraph.com/pytigergraph/current/gds/pyg_transforms", "https://docs.tigergraph.com/pytigergraph/current/gds/nodepiece", "https://docs.tigergraph.com/pytigergraph/current/gds/transforms", "https://docs.tigergraph.com/pytigergraph/current/release-notes/", "https://docs.tigergraph.com/cloud/start/overview", "https://docs.tigergraph.com/pytigergraph/current/core-functions/base", "https://docs.tigergraph.com/pytigergraph/current/getting-started/101", "https://docs.tigergraph.com/home", "https://docs.tigergraph.com/pytigergraph/current/object_oriented_schema/schema-def", "https://docs.tigergraph.com/pytigergraph/current/core-functions/query", "https://docs.tigergraph.com/pytigergraph/1.2/gds/", "https://docs.tigergraph.com/graphql/current/", "https://docs.tigergraph.com/pytigergraph/current/core-functions/auth", "https://docs.tigergraph.com/pytigergraph/current/gds/models", "https://docs.tigergraph.com/sitemap.xml", "https://docs.tigergraph.com/pytigergraph/current/gds/gds", "https://docs.tigergraph.com/", "https://docs.tigergraph.com/pytigergraph/current/intro/", "https://docs.tigergraph.com/pytigergraph/current/visualization/visualization", "https://docs.tigergraph.com/pytigergraph/current/core-functions/", "https://docs.tigergraph.com/pytigergraph/current/gds/nodepiece_transforms", "https://docs.tigergraph.com/pytigergraph/1/gds/", "https://docs.tigergraph.com/pytigergraph/current/core-functions/loading", "https://docs.tigergraph.com/pytigergraph/current/gds/dataloaders", "https://docs.tigergraph.com/home/", "https://docs.tigergraph.com/pytigergraph/1.1/gds/", "https://docs.tigergraph.com/pytigergraph/current/gds/featurizer", "https://docs.tigergraph.com/pytigergraph/current/gds/trainer", "https://docs.tigergraph.com/pytigergraph/current/gds/metrics", "https://docs.tigergraph.com/pytigergraph/current/core-functions/utils", "https://docs.tigergraph.com/pytigergraph/current/datasets/datasets", "https://docs.tigergraph.com/gsql-ref/current/intro/", "https://docs.tigergraph.com/pytigergraph/current/gds/", "https://docs.tigergraph.com/graph-ml/current/intro/"]}
{"url": "https://docs.tigergraph.com/pytigergraph/current/getting-started/", "content": "Getting Started\nThe Getting Started sequence walks you through the following:\nInstalling pyTigerGraph\nConnecting to TigerGraph\npyTigerGraph 101\nAt the conclusion of the Getting Started sequence, you\u2019ll have reached an excellent starting point for further, more detail-driven activities.", "links": ["https://docs.tigergraph.com/pytigergraph/current/contributing/", "https://docs.tigergraph.com/pytigergraph/current/getting-started/", "https://docs.tigergraph.com/pytigergraph/current/gds/splitters", "https://docs.tigergraph.com/pytigergraph/1.4/getting-started/", "https://docs.tigergraph.com/pytigergraph/current/getting-started/connection", "https://docs.tigergraph.com/pytigergraph/current/core-functions/edge", "https://docs.tigergraph.com/tigergraph-server/current/gsql-shell/web", "https://docs.tigergraph.com/pytigergraph/current/core-functions/gsql", "https://docs.tigergraph.com/pytigergraph/current/core-functions/schema", "https://docs.tigergraph.com/pytigergraph/current/core-functions/vertex", "https://docs.tigergraph.com/pytigergraph/current/core-functions/path", "https://docs.tigergraph.com/gui/current/intro/", "https://docs.tigergraph.com/pytigergraph/current/release-notes/legacy-tg-versions", "https://docs.tigergraph.com/tigergraph-server/current/intro/", "https://docs.tigergraph.com/pytigergraph/current/getting-started/install", "https://docs.tigergraph.com/pytigergraph/current/datasets/datasets_object", "https://docs.tigergraph.com/insights/current/intro/", "https://docs.tigergraph.com/ml-workbench/current/intro/", "https://docs.tigergraph.com/pytigergraph/current/core-functions/udt", "https://docs.tigergraph.com/pytigergraph/current/gds/graphsage", "https://docs.tigergraph.com/pytigergraph/current/gds/pyg_transforms", "https://docs.tigergraph.com/pytigergraph/current/gds/nodepiece", "https://docs.tigergraph.com/pytigergraph/current/gds/transforms", "https://docs.tigergraph.com/pytigergraph/current/release-notes/", "https://docs.tigergraph.com/cloud/start/overview", "https://docs.tigergraph.com/pytigergraph/current/core-functions/base", "https://docs.tigergraph.com/pytigergraph/current/getting-started/101", "https://docs.tigergraph.com/home", "https://docs.tigergraph.com/pytigergraph/current/object_oriented_schema/schema-def", "https://docs.tigergraph.com/pytigergraph/current/core-functions/query", "https://docs.tigergraph.com/pytigergraph/1.1/getting-started/", "https://docs.tigergraph.com/graphql/current/", "https://docs.tigergraph.com/pytigergraph/current/core-functions/auth", "https://docs.tigergraph.com/pytigergraph/current/gds/models", "https://docs.tigergraph.com/sitemap.xml", "https://docs.tigergraph.com/pytigergraph/1.3/getting-started/", "https://docs.tigergraph.com/pytigergraph/current/gds/gds", "https://docs.tigergraph.com/", "https://docs.tigergraph.com/pytigergraph/current/intro/", "https://docs.tigergraph.com/pytigergraph/current/visualization/visualization", "https://docs.tigergraph.com/pytigergraph/current/core-functions/", "https://docs.tigergraph.com/pytigergraph/current/gds/nodepiece_transforms", "https://docs.tigergraph.com/pytigergraph/1.2/getting-started/", "https://docs.tigergraph.com/pytigergraph/1/getting-started/", "https://docs.tigergraph.com/pytigergraph/current/core-functions/loading", "https://docs.tigergraph.com/pytigergraph/current/gds/dataloaders", "https://docs.tigergraph.com/home/", "https://docs.tigergraph.com/pytigergraph/current/gds/featurizer", "https://docs.tigergraph.com/pytigergraph/current/gds/trainer", "https://docs.tigergraph.com/pytigergraph/current/gds/metrics", "https://docs.tigergraph.com/pytigergraph/current/core-functions/utils", "https://docs.tigergraph.com/pytigergraph/current/datasets/datasets", "https://docs.tigergraph.com/gsql-ref/current/intro/", "https://docs.tigergraph.com/pytigergraph/current/gds/", "https://docs.tigergraph.com/graph-ml/current/intro/"]}
{"url": "https://docs.tigergraph.com/pytigergraph/current/gds/pyg_transforms", "content": "PyTorch Geometric Transforms\nTemporalPyGTransform\nThe TemporalPyGTransform creates a sequence of subgraph batches out of a single batch of data produced by a NeighborLoader or HGTLoader. It assumes that there are datetime attributes on vertices and edges. If vertex attributes change over time, children vertex attributes are moved to the appropriate parent, and then the children are removed from the graph.\n_init_\n()\ninit\n(vertex_start_attrs: dict, vertex_end_attrs: dict, edge_start_attrs: dict, edge_end_attrs: dict, start_dt: int, end_dt: int, feature_transforms: dict, timestep: int = 86400)\nInstantiate a TemporalPyGTransform.\nParameters:\nvertex_start_attrs (str, dict)\n: If using on a homogeneous graph, string of the attribute storing the timestamp of when a vertex becomes valid to include.\nIf using on a heterogenous graph, dictionary that describes the attribute storing the timestamp of when a vertex becomes a valid vertex to include in the graph.\nIn the format of {\"VERTEX_TYPE\": \"attribute_name\"}.\nvertex_end_attrs (str, dict)\n: If using on a homogeneous graph, string of the attribute storing the timestamp of when a vertex stops being valid to include.\nIf using on a heterogenous graph, dictionary that describes the attribute storing the timestamp of when a vertex stops being a valid vertex to include in the graph.\nIn the format of {\"VERTEX_TYPE\": \"attribute_name\"}\nedge_start_attrs (str, dict)\n: If using on a homogeneous graph, string of the attribute storing the timestamp of when an edge becomes valid to include.\nIf using on a heterogenous graph, dictionary that describes the attribute storing the timestamp of when an edge becomes a valid edge to include in the graph.\nUses the PyG edge format of (\"SourceVertexType\", \"EdgeName\", \"DestinationVertexType\").\nIn the format of {(\"SourceVertexType\", \"EdgeName\", \"DestinationVertexType\"): \"attribute_name\"}.\nedge_end_attrs (str, dict)\n: If using on a homogeneous graph, string of the attribute storing the timestamp of when an edge stops being valid to include.\nIf using on a heterogenous graph, dictionary that describes the attribute storing the timestamp of when an edge stops being a valid edge to include in the graph.\nUses the PyG edge format of (\"SourceVertexType\", \"EdgeName\", \"DestinationVertexType\").\nIn the format of {(\"SourceVertexType\", \"EdgeName\", \"DestinationVertexType\"): \"attribute_name\"}\nstart_dt (int)\n: The UNIX epoch time to start generating the sequence of subgraphs.\nend_dt (int)\n: The UNIX epoch time to stop generating the sequence of subgraphs.\nfeature_transforms (dict, optional)\n: Only available on heterogeneous graphs. Moves temporally dynamic features from \"children\" vertices to \"parent\" vertices when\nmodelling temporal attributes in TigerGraph.\nThe key of the dictionary is the edge to move the attributes from the child type to the parent type, and the value is a list of attributes to move.\nIn the fromat of {(\"ItemInstance\", \"reverse_DESCRIBED_BY\", \"Item\"): [\"x\"]}\ntimestep (int, optional)\n: The number of seconds to use in between timesteps. Defaults to 86400 seconds (1 day).\ncall\n()\ncall\n(data) \u2192 list\nPerform the transform. Returns a list of PyTorch Geometric data objects, a sequence of snapshots in time of the graph.\nEdges are removed between vertices that do not have connections at the given time. All vertices are in each snapshot, but are marked\nas present with the \"vertex_present\" attribute in the produced data objects.\nParameter:\ndata (pyg.data.HeteroData or pyg.data.Data)\n: Takes in a PyTorch Geometric data object, such as ones produced by the dataloaders.", "links": ["https://docs.tigergraph.com/pytigergraph/current/contributing/", "https://docs.tigergraph.com/pytigergraph/current/getting-started/", "https://docs.tigergraph.com/pytigergraph/current/gds/splitters", "https://docs.tigergraph.com/pytigergraph/current/getting-started/connection", "https://docs.tigergraph.com/pytigergraph/current/core-functions/edge", "https://docs.tigergraph.com/tigergraph-server/current/gsql-shell/web", "https://docs.tigergraph.com/pytigergraph/current/core-functions/gsql", "https://docs.tigergraph.com/pytigergraph/current/core-functions/schema", "https://docs.tigergraph.com/pytigergraph/current/core-functions/vertex", "https://docs.tigergraph.com/pytigergraph/current/core-functions/path", "https://docs.tigergraph.com/gui/current/intro/", "https://docs.tigergraph.com/pytigergraph/current/release-notes/legacy-tg-versions", "https://docs.tigergraph.com/tigergraph-server/current/intro/", "https://docs.tigergraph.com/pytigergraph/current/getting-started/install", "https://docs.tigergraph.com/pytigergraph/current/datasets/datasets_object", "https://docs.tigergraph.com/insights/current/intro/", "https://docs.tigergraph.com/ml-workbench/current/intro/", "https://docs.tigergraph.com/pytigergraph/current/core-functions/udt", "https://docs.tigergraph.com/pytigergraph/current/gds/graphsage", "https://docs.tigergraph.com/pytigergraph/current/gds/pyg_transforms", "https://docs.tigergraph.com/pytigergraph/current/gds/nodepiece", "https://docs.tigergraph.com/pytigergraph/current/gds/transforms", "https://docs.tigergraph.com/pytigergraph/current/release-notes/", "https://docs.tigergraph.com/cloud/start/overview", "https://docs.tigergraph.com/pytigergraph/current/core-functions/base", "https://docs.tigergraph.com/pytigergraph/current/getting-started/101", "https://docs.tigergraph.com/pytigergraph/current/gds/pyg_transforms#_init", "https://docs.tigergraph.com/home", "https://docs.tigergraph.com/pytigergraph/current/object_oriented_schema/schema-def", "https://docs.tigergraph.com/pytigergraph/current/core-functions/query", "https://docs.tigergraph.com/graphql/current/", "https://docs.tigergraph.com/pytigergraph/current/core-functions/auth", "https://docs.tigergraph.com/pytigergraph/current/gds/models", "https://docs.tigergraph.com/sitemap.xml", "https://docs.tigergraph.com/pytigergraph/current/gds/gds", "https://docs.tigergraph.com/", "https://docs.tigergraph.com/pytigergraph/current/intro/", "https://docs.tigergraph.com/pytigergraph/current/visualization/visualization", "https://docs.tigergraph.com/pytigergraph/current/core-functions/", "https://docs.tigergraph.com/pytigergraph/current/gds/nodepiece_transforms", "https://docs.tigergraph.com/pytigergraph/1.4/gds/pyg_transforms", "https://docs.tigergraph.com/pytigergraph/current/gds/pyg_transforms#_temporalpygtransform", "https://docs.tigergraph.com/pytigergraph/current/core-functions/loading", "https://docs.tigergraph.com/pytigergraph/current/gds/dataloaders", "https://docs.tigergraph.com/home/", "https://docs.tigergraph.com/pytigergraph/current/gds/featurizer", "https://docs.tigergraph.com/pytigergraph/current/gds/trainer", "https://docs.tigergraph.com/pytigergraph/1/intro/", "https://docs.tigergraph.com/pytigergraph/current/core-functions/utils", "https://docs.tigergraph.com/pytigergraph/current/gds/metrics", "https://docs.tigergraph.com/pytigergraph/1.1/intro/", "https://docs.tigergraph.com/pytigergraph/1.3/intro/", "https://docs.tigergraph.com/pytigergraph/current/datasets/datasets", "https://docs.tigergraph.com/pytigergraph/current/gds/pyg_transforms#_call", "https://docs.tigergraph.com/pytigergraph/1.2/intro/", "https://docs.tigergraph.com/gsql-ref/current/intro/", "https://docs.tigergraph.com/pytigergraph/current/gds/", "https://docs.tigergraph.com/graph-ml/current/intro/"]}
{"url": "https://docs.tigergraph.com/pytigergraph/current/contributing/tests", "content": "", "links": ["https://docs.tigergraph.com/pytigergraph/current/contributing/", "https://docs.tigergraph.com/pytigergraph/current/getting-started/", "https://docs.tigergraph.com/pytigergraph/current/gds/splitters", "https://docs.tigergraph.com/pytigergraph/1.2/contributing/tests", "https://docs.tigergraph.com/pytigergraph/current/getting-started/connection", "https://docs.tigergraph.com/pytigergraph/current/core-functions/edge", "https://docs.tigergraph.com/tigergraph-server/current/gsql-shell/web", "https://docs.tigergraph.com/pytigergraph/current/core-functions/gsql", "https://docs.tigergraph.com/pytigergraph/current/core-functions/schema", "https://docs.tigergraph.com/pytigergraph/current/core-functions/vertex", "https://docs.tigergraph.com/pytigergraph/current/core-functions/path", "https://docs.tigergraph.com/gui/current/intro/", "https://docs.tigergraph.com/pytigergraph/current/release-notes/legacy-tg-versions", "https://docs.tigergraph.com/tigergraph-server/current/intro/", "https://docs.tigergraph.com/pytigergraph/current/getting-started/install", "https://docs.tigergraph.com/pytigergraph/current/datasets/datasets_object", "https://docs.tigergraph.com/insights/current/intro/", "https://docs.tigergraph.com/ml-workbench/current/intro/", "https://docs.tigergraph.com/pytigergraph/current/core-functions/udt", "https://docs.tigergraph.com/pytigergraph/current/gds/graphsage", "https://docs.tigergraph.com/pytigergraph/current/gds/pyg_transforms", "https://docs.tigergraph.com/pytigergraph/1.3/contributing/tests", "https://docs.tigergraph.com/pytigergraph/current/gds/transforms", "https://docs.tigergraph.com/pytigergraph/current/gds/nodepiece", "https://docs.tigergraph.com/cloud/start/overview", "https://docs.tigergraph.com/pytigergraph/current/release-notes/", "https://docs.tigergraph.com/pytigergraph/1.4/contributing/tests", "https://docs.tigergraph.com/pytigergraph/current/getting-started/101", "https://docs.tigergraph.com/pytigergraph/current/core-functions/base", "https://docs.tigergraph.com/home", "https://docs.tigergraph.com/pytigergraph/current/object_oriented_schema/schema-def", "https://docs.tigergraph.com/pytigergraph/current/core-functions/query", "https://docs.tigergraph.com/pytigergraph/1/contributing/tests", "https://docs.tigergraph.com/graphql/current/", "https://docs.tigergraph.com/pytigergraph/current/core-functions/auth", "https://docs.tigergraph.com/pytigergraph/current/gds/models", "https://docs.tigergraph.com/sitemap.xml", "https://docs.tigergraph.com/pytigergraph/1.1/contributing/tests", "https://docs.tigergraph.com/pytigergraph/current/gds/gds", "https://docs.tigergraph.com/", "https://docs.tigergraph.com/pytigergraph/current/intro/", "https://docs.tigergraph.com/pytigergraph/current/visualization/visualization", "https://docs.tigergraph.com/pytigergraph/current/core-functions/", "https://docs.tigergraph.com/pytigergraph/current/gds/nodepiece_transforms", "https://docs.tigergraph.com/pytigergraph/current/core-functions/loading", "https://docs.tigergraph.com/pytigergraph/current/gds/dataloaders", "https://docs.tigergraph.com/home/", "https://docs.tigergraph.com/pytigergraph/current/gds/featurizer", "https://docs.tigergraph.com/pytigergraph/current/gds/trainer", "https://docs.tigergraph.com/pytigergraph/current/gds/metrics", "https://docs.tigergraph.com/pytigergraph/current/core-functions/utils", "https://docs.tigergraph.com/pytigergraph/current/datasets/datasets", "https://docs.tigergraph.com/pytigergraph/current/contributing/tests", "https://docs.tigergraph.com/gsql-ref/current/intro/", "https://docs.tigergraph.com/pytigergraph/current/gds/", "https://docs.tigergraph.com/graph-ml/current/intro/"]}

Parker_Erickson · July 15, 2024, 3:17pm

Have you built the docker containers yourself or used Docker pull? I am not sure if the released dockers have Ollama support yet.

Puneet2 · July 16, 2024, 12:53pm

hi @Parker_Erickson
thanks for your reply
so as of now, we are using OpenAI only

what we observed that “SupportAI” notebook required “TG cloud 4.0.0 version”
and while hitting the “hnswoverlap” method

conn.ai.searchDocuments(query,
                        method="hnswoverlap",
                        method_parameters = {"indices": ["Document", "DocumentChunk", "Entity", "Relationship"],
                                             "top_k": 2,
                                             "num_hops": 2,
                                             "num_seen_min": 2})

We r getting below error “Request-URI too large for url”

requests.exceptions.HTTPError: 414 Client Error: Request-URI Too Large for url: https://tg-29ba8f89-6d9d-4cc9-8aec-ea9c9353c0f0.us-east-1.i.tgcloud.io:443/restpp/query/pyTigerGraphRAG/HNSW_Overlap_Search?query_vector_as_string=0.010086149635291985%2C-0.0005599928919482359%2C-0.0010078976122693017%2C-0.0011585441708155764%2C-0.00792688089914476%2C0.0010204514921481579%2C-0.025495145270541652%2C-0.01797716250578058%2C-0.0016535259697861853%2C-0415%2C-0.0009738227289322178%2C0.027661587984949165%2C-0.04264016355103428%2C0.023515218540320532%2C0.024548224843670183%2C-0.005929020154595558%2C0.014806410332387202%2C-0.023285662411862952%2C-0.019196682930671352%2C0.018393234618424553%2C-6.383425768846028e-05%2C-0.0003272977114442952%2C-0.0023942051154693623%2C-0.0346343726163169%2C-0.0021036722672752675%2C0.0014266592682689078%2C-0.024175194737942662%2C-0.00464493718499142%2C-0.017604132400053058%2C0.027388989849575128%2C0.009971370639740561%2C-0.002295567338172925%2C0.022654380264636703%2C0.02629859358278845%2C-0.0015145365438362307%2C0.009232485337868444%2C-0.03991417847200339%2C-0.031219717289268%2C-0.036528217195350376%2C-0.0061872717304329704%2C-0.0007868595352578488%2C0.022123531950409208%2C-0.04728868912213979&v_types=Document&v_types=DocumentChunk&v_types=Entity&v_types=Relationship&collection_prefix=pyTigerGraphRAG&top_k=2&num_hops=2&num_seen_min=2&milvus_host=milvus-standalone&milvus_port=19530&vector_field_name=document_vector&vertex_id_field_name=vertex_id

Parker_Erickson · July 16, 2024, 1:26pm

Strange. Can we schedule a debugging call?

Puneet2 · July 16, 2024, 1:30pm

yes, please provide the calendar link
and suitable timings (IST)

Thanks