From 483f12fab2349e0b8727a33bde51ba01c6c9d773 Mon Sep 17 00:00:00 2001 From: Puja Trivedi Date: Fri, 7 Nov 2025 11:14:27 -0800 Subject: [PATCH 1/5] updated structsense configuration to have external links and added new 'basic' .env file --- docs/structsense_configuration.md | 35 +++++++------------------------ 1 file changed, 7 insertions(+), 28 deletions(-) diff --git a/docs/structsense_configuration.md b/docs/structsense_configuration.md index 076068e..18938bc 100644 --- a/docs/structsense_configuration.md +++ b/docs/structsense_configuration.md @@ -16,7 +16,8 @@ Pass the YAML via CLI, e.g. `--config config/ner_agent.yaml`. - `{judged_structured_information_with_human_feedback}` — judge output - `{modification_context}`, `{user_feedback_text}` — inputs to feedback agent -A blank template is available in `config_template/`. See **Templates**. +**Config Template**\ +A blank template is available in [config_template](https://github.com/sensein/structsense/blob/main/config_template/config.yaml). ## Agent Configuration @@ -152,32 +153,10 @@ embedder_config: | `ENABLE_MLFLOW` | Enable MLflow | `false` | | `MLFLOW_TRACKING_URL` | MLflow tracking URL | `http://localhost:5000` | -### Minimal (no tracking, no knowledge source) + +## Example `.env` ```bash -ENABLE_WEIGHTSANDBIAS=false -ENABLE_MLFLOW=false ENABLE_KG_SOURCE=false -``` - -### Example `.env` -```bash -WEAVIATE_API_KEY=your_api_key -WEAVIATE_HTTP_HOST=localhost -WEAVIATE_HTTP_PORT=8080 -WEAVIATE_HTTP_SECURE=false - -WEAVIATE_GRPC_HOST=localhost -WEAVIATE_GRPC_PORT=50051 -WEAVIATE_GRPC_SECURE=false - -WEAVIATE_TIMEOUT_INIT=30 -WEAVIATE_TIMEOUT_QUERY=60 -WEAVIATE_TIMEOUT_INSERT=120 - -OLLAMA_API_ENDPOINT=http://host.docker.internal:11434 -OLLAMA_MODEL=nomic-embed-text - -ENABLE_WEAVE=true -ENABLE_MLFLOW=true -MLFLOW_TRACKING_URL=http://localhost:5000 -``` +OLLAMA_API_ENDPOINT=http://localhost:11434 +OLLAMA_MODEL=nomic-embed-text:v1.5 +``` \ No newline at end of file From c26f7abf62661c50f48e16c7c8a474bd8b9e0900 Mon Sep 17 00:00:00 2001 From: Puja Trivedi Date: Fri, 7 Nov 2025 11:24:27 -0800 Subject: [PATCH 2/5] removed redundant info and added external links --- docs/structsense_examples.md | 20 +++++--------------- 1 file changed, 5 insertions(+), 15 deletions(-) diff --git a/docs/structsense_examples.md b/docs/structsense_examples.md index fc56d68..4805e6d 100644 --- a/docs/structsense_examples.md +++ b/docs/structsense_examples.md @@ -1,19 +1,9 @@ # Examples -- See the `example/` directory for usage demonstrations and reference configs. -- A blank configuration is provided under `config_template/`. +- See the [example/](https://github.com/sensein/structsense/tree/main/example) directory for usage demonstrations and reference configs. ## Example Use Cases -- Entity and relation extraction from text -- Knowledge graph construction - -## Blank Configuration Template - -A starting template is provided in `config_template/`. - -Before modifying, read: -- **Configuration Overview & Template** -- **Agents** -- **Tasks** -- **Embeddings & Knowledge** -- **Environment Variables** +**For more information about StructSense use cases, see [here](https://arxiv.org/html/2507.03674v2#S5)** +- Neuroscience Named Entity Extraction from text +- Resource (i.e. models, datasets) Extraction +- ReproSchema Extraction From 71a0c4d715408a7f365bf1721b91950545b41151 Mon Sep 17 00:00:00 2001 From: puja-trivedi <44144244+puja-trivedi@users.noreply.github.com> Date: Fri, 7 Nov 2025 11:28:44 -0800 Subject: [PATCH 3/5] Update docs/structsense_examples.md For better accessibility and clarity, it's recommended to use descriptive link text instead of 'here'. This helps users understand the context of the link without having to read the surrounding text. Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> --- docs/structsense_examples.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/structsense_examples.md b/docs/structsense_examples.md index 4805e6d..db0c9e7 100644 --- a/docs/structsense_examples.md +++ b/docs/structsense_examples.md @@ -3,7 +3,7 @@ - See the [example/](https://github.com/sensein/structsense/tree/main/example) directory for usage demonstrations and reference configs. ## Example Use Cases -**For more information about StructSense use cases, see [here](https://arxiv.org/html/2507.03674v2#S5)** +**For more information about StructSense use cases, see the [StructSense paper on arXiv](https://arxiv.org/html/2507.03674v2#S5)** - Neuroscience Named Entity Extraction from text - Resource (i.e. models, datasets) Extraction - ReproSchema Extraction From 3ac7064009beeb8ab22adc9af3e501a6b6d0866d Mon Sep 17 00:00:00 2001 From: puja-trivedi <44144244+puja-trivedi@users.noreply.github.com> Date: Fri, 7 Nov 2025 11:29:03 -0800 Subject: [PATCH 4/5] Update docs/structsense_examples.md There are trailing spaces at the end of these lines. It's best practice to remove them for consistency and to prevent potential issues with certain text processing tools. Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> --- docs/structsense_examples.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/structsense_examples.md b/docs/structsense_examples.md index db0c9e7..6a28967 100644 --- a/docs/structsense_examples.md +++ b/docs/structsense_examples.md @@ -5,5 +5,5 @@ ## Example Use Cases **For more information about StructSense use cases, see the [StructSense paper on arXiv](https://arxiv.org/html/2507.03674v2#S5)** - Neuroscience Named Entity Extraction from text -- Resource (i.e. models, datasets) Extraction -- ReproSchema Extraction +- Resource (i.e. models, datasets) Extraction +- ReproSchema Extraction From 55ef0f7da6b74d7b3e39c34ac3a914974ae586d5 Mon Sep 17 00:00:00 2001 From: puja-trivedi <44144244+puja-trivedi@users.noreply.github.com> Date: Fri, 7 Nov 2025 11:29:42 -0800 Subject: [PATCH 5/5] Update structsense_configuration.md added new line to end of file --- docs/structsense_configuration.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/structsense_configuration.md b/docs/structsense_configuration.md index 18938bc..bed3f56 100644 --- a/docs/structsense_configuration.md +++ b/docs/structsense_configuration.md @@ -159,4 +159,4 @@ embedder_config: ENABLE_KG_SOURCE=false OLLAMA_API_ENDPOINT=http://localhost:11434 OLLAMA_MODEL=nomic-embed-text:v1.5 -``` \ No newline at end of file +```