Merge branch 'main' into main

superlinked · Feb 13, 2024 · 2f905fe · 2f905fe
2 parents 374972d + b908a17
commit 2f905fe
Show file tree

Hide file tree

Showing 11 changed files with 126 additions and 113 deletions.
diff --git a/.github/workflows/json-bundle.yml b/.github/workflows/json-bundle.yml
@@ -6,6 +6,7 @@ on:
 
 jobs:
   bundle:
+    if: ${{ github.repository == 'superlinked/VectorHub' }}
     runs-on: ubuntu-latest
     permissions:
       contents: 'read'

diff --git a/README.md b/README.md
@@ -2,7 +2,7 @@
 
 # VectorHub
 
-VectorHub is a free and open-sourced learning hub for people interested in adding vector retrieval to their ML stack. On VectorHub you will find practical resources to help you -
+[VectorHub](https://hub.superlinked.com) is a free and open-sourced learning hub for people interested in adding vector retrieval to their ML stack. On VectorHub you will find practical resources to help you -
 
 * Create MVPs with easy-to-follow learning materials
 * Solve use case specific challenges in vector retrieval
@@ -11,14 +11,18 @@ VectorHub is a free and open-sourced learning hub for people interested in addin
 
 Read more about our philosophy in our [Manifesto](manifesto.md).
 
-## Built With
+## Tools by VectorHub
+[Vector DB Comparison](https://vdbs.superlinked.com) is a free and open source tool from VectorHub to compare vector databases. It is created to outline the feature sets of different VDB solutions. Each of the features outlined has been verified to varying degrees.
 
-* [Archbee](https://www.archbee.com/) - Frontend for markdown files
 
 ## Contributing
 
 Please read [CONTRIBUTING.md](https://hub.superlinked.com/contributing) for details on our code of conduct, and the process for submitting pull requests to us.
 
+### Built With
+
+* [Archbee](https://www.archbee.com/) - Frontend for markdown files
+
 ## License
 This work is licensed under a
 [Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License][cc-by-nc-sa].

diff --git a/docs/home.md b/docs/home.md
@@ -43,6 +43,7 @@ Here are some examples from the community, more coming soon!
 
 Subscribe to be updated when new ones come out & check the blog section.
 
+- [02/01 - Scaling RAG for Production](https://hub.superlinked.com/scaling-rag-for-production): How to go from working model to a production system with step-by-step instructions.
 - [01/25 - Improving RAG performance with Knowledge Graphs](use_cases/knowledge_graphs.md): Adding knowledge graph embeddings as contextual data to improve the performance of RAG.
 - [01/18 Representation Learning on Graph Structured Data](https://hub.superlinked.com/representation-learning-on-graph-structured-data): Understanding how combining KGEs and semantic embeddings can improve understanding of your solution.
 - [01/11 - VDB Feature Matrix](https://vdbs.superlinked.com/): Find the right Vector Database (VDB) for your use case.

diff --git a/docs/summary.md b/docs/summary.md
@@ -21,6 +21,7 @@
   - [Personalized Search](use_cases/personalized_search.md)
   - [Recommender Systems](use_cases/recommender_systems.md)
   - [Retrieval Augmented Generation](use_cases/retrieval_augmented_generation.md)
+  - [Scaling RAG for Production](use_cases/scaling_rag_for_production.md)
   - [Enhancing RAG with multiple agents](use_cases/multi_agent_rag.md)
   - [Embeddings on browser](use_cases/embeddings_on_browser.md)
   - [Answering Questions with Knowledge Graph Embeddings](use_cases/knowledge_graph_embedding.md)

diff --git a/docs/tools/vdb_table/data/azureai.json b/docs/tools/vdb_table/data/azureai.json
@@ -20,9 +20,7 @@
   },
   "dev_languages": {
     "value": [
-      "C#",
-      "C++",
-      "Java"
+      "c++"
     ],
     "source_url": "",
     "comment": ""
@@ -151,4 +149,4 @@
     "source_url": "https://learn.microsoft.com/azure/search/vector-search-how-to-generate-embeddings",
     "comment": ""
   }
-}
+}
diff --git a/docs/tools/vdb_table/data/meilisearch.json b/docs/tools/vdb_table/data/meilisearch.json
@@ -51,7 +51,7 @@
     "comment": ""
   },
   "sparse_vectors": {
-    "support": "full",
+    "support": "none",
     "source_url": "",
     "comment": ""
   },

diff --git a/docs/tools/vdb_table/data/rockset.json b/docs/tools/vdb_table/data/rockset.json
@@ -14,139 +14,139 @@
     "comment": ""
   },
   "license": {
-    "value": "",
-    "source_url": "",
+    "value": "Proprietary",
+    "source_url": "https://rockset.com/legal/terms-of-service/",
     "comment": ""
   },
   "dev_languages": {
     "value": [
-      ""
+      "c++"
     ],
     "source_url": "",
     "comment": ""
   },
   "github_stars": 0,
-  "vector_launch_year": 0,
+  "vector_launch_year": 2023,
   "metadata_filter": {
-    "support": "",
+    "support": "full",
     "source_url": "",
     "comment": ""
   },
   "hybrid_search": {
-    "support": "",
-    "source_url": "",
+    "support": "full",
+    "source_url": "https://github.com/sofia099/search_autocomplete",
     "comment": ""
   },
   "facets": {
-    "support": "",
-    "source_url": "",
+    "support": "full",
+    "source_url": "https://docs.rockset.com/documentation/reference/aggregate-functions",
     "comment": ""
   },
   "geo_search": {
-    "support": "",
-    "source_url": "",
+    "support": "full",
+    "source_url": "https://docs.rockset.com/documentation/reference/geographic-functions",
     "comment": ""
   },
   "multi_vec": {
-    "support": "",
+    "support": "none",
     "source_url": "",
     "comment": ""
   },
   "sparse_vectors": {
-    "support": "",
+    "support": "none",
     "source_url": "",
     "comment": ""
   },
   "bm25": {
-    "support": "",
+    "support": "none",
     "source_url": "",
     "comment": ""
   },
   "full_text": {
-    "support": "",
-    "source_url": "",
+    "support": "full",
+    "source_url": "https://docs.rockset.com/documentation/reference/text-search-functions",
     "comment": ""
   },
   "embeddings_text": {
-    "support": "",
-    "source_url": "",
+    "support": "partial",
+    "source_url": "https://docs.rockset.com/documentation/reference/user-defined-functions",
     "comment": ""
   },
   "embeddings_image": {
-    "support": "",
-    "source_url": "",
+    "support": "partial",
+    "source_url": "https://docs.rockset.com/documentation/reference/user-defined-functions",
     "comment": ""
   },
   "embeddings_structured": {
-    "support": "",
+    "support": "none",
     "source_url": "",
     "comment": ""
   },
   "rag": {
-    "support": "",
+    "support": "none",
     "source_url": "",
     "comment": ""
   },
   "recsys": {
-    "support": "",
+    "support": "none",
     "source_url": "",
     "comment": ""
   },
   "langchain": {
-    "support": "",
-    "source_url": "",
+    "support": "full",
+    "source_url": "https://rockset.com/docs/langchain/",
     "comment": ""
   },
   "llamaindex": {
-    "support": "",
-    "source_url": "",
+    "support": "full",
+    "source_url": "https://rockset.com/docs/llama_index/",
     "comment": ""
   },
   "managed_cloud": {
     "support": "full",
-    "source_url": "",
+    "source_url": "https://docs.rockset.com/documentation/docs/what-is-rockset",
     "comment": ""
   },
   "pricing": {
     "value": "",
-    "source_url": "",
+    "source_url": "https://rockset.com/pricing/",
     "comment": ""
   },
   "in_process": {
-    "support": "",
+    "support": "none",
     "source_url": "",
     "comment": ""
   },
   "multi_tenancy": {
-    "support": "",
-    "source_url": "",
+    "support": "full",
+    "source_url": "https://docs.rockset.com/documentation/docs/multitenancy",
     "comment": ""
   },
   "disk_index": {
-    "support": "",
-    "source_url": "",
+    "support": "full",
+    "source_url": "https://rockset.com/blog/separate-compute-storage-rocksdb/",
     "comment": ""
   },
   "ephemeral": {
-    "support": "",
+    "support": "none",
     "source_url": "",
     "comment": ""
   },
   "sharding": {
-    "support": "",
-    "source_url": "",
-    "comment": ""
+    "support": "full",
+    "source_url": "https://rockset.com/whitepapers/rockset-concepts-designs-and-architecture",
+    "comment": "tech talk that includes sharding details: https://www.youtube.com/watch?v=trXiMHjP6a8"
   },
   "doc_size": {
-    "bytes": 0,
+    "bytes": 41943040,
     "unlimited": false,
-    "source_url": "",
+    "source_url": "https://docs.rockset.com/documentation/docs/debugging#document-size-is-too-large",
     "comment": ""
   },
   "vector_dims": {
     "value": 0,
-    "unlimited": false,
+    "unlimited": true,
     "source_url": "",
     "comment": ""
   }
-}
+}
diff --git a/docs/tools/vdb_table/data/usearch.json b/docs/tools/vdb_table/data/usearch.json
@@ -15,7 +15,7 @@
   },
   "license": {
     "value": "Apache-2.0",
-    "source_url": "",
+    "source_url": "https://github.com/unum-cloud/usearch/blob/main/LICENSE",
     "comment": ""
   },
   "dev_languages": {
@@ -25,26 +25,26 @@
     "source_url": "",
     "comment": ""
   },
-  "github_stars": 1061,
+  "github_stars": 1250,
   "vector_launch_year": 2023,
   "metadata_filter": {
-    "support": "",
+    "support": "partial",
     "source_url": "",
-    "comment": ""
+    "comment": "hybrid filtering techniques are available in some SDKs, like C++, but not in Python"
   },
   "hybrid_search": {
     "support": "",
     "source_url": "",
-    "comment": ""
+    "comment": "hybrid filtering techniques are available in some SDKs, like C++, but not in Python"
   },
   "facets": {
-    "support": "",
+    "support": "none",
     "source_url": "",
     "comment": ""
   },
   "geo_search": {
     "support": "full",
-    "source_url": "",
+    "source_url": "https://ashvardanian.com/posts/abusing-vector-search/",
     "comment": ""
   },
   "multi_vec": {
@@ -58,24 +58,24 @@
     "comment": ""
   },
   "bm25": {
-    "support": "",
+    "support": "none",
     "source_url": "",
     "comment": ""
   },
   "full_text": {
-    "support": "",
+    "support": "partial",
     "source_url": "",
-    "comment": ""
+    "comment": "with custom user-defined metrics on similar-length string until v3"
   },
   "embeddings_text": {
-    "support": "",
-    "source_url": "",
-    "comment": ""
+    "support": "partial",
+    "source_url": "https://github.com/unum-cloud/uform",
+    "comment": "UForm embeddings as well as third-party solutions can be used with USearch"
   },
   "embeddings_image": {
-    "support": "",
-    "source_url": "",
-    "comment": ""
+    "support": "partial",
+    "source_url": "https://github.com/unum-cloud/uform",
+    "comment": "UForm embeddings as well as third-party solutions can be used with USearch"
   },
   "embeddings_structured": {
     "support": "",
@@ -108,23 +108,23 @@
     "comment": ""
   },
   "pricing": {
-    "value": "",
+    "value": "none",
     "source_url": "",
     "comment": ""
   },
   "in_process": {
-    "support": "none",
-    "source_url": "",
-    "comment": ""
+    "support": "full",
+    "source_url": "https://ashvardanian.com/posts/porting-cpp-library-to-ten-languages/",
+    "comment": "The whole library is compiled for the target language runtime to be embedded natively into apps in different languages"
   },
   "multi_tenancy": {
-    "support": "",
+    "support": "none",
     "source_url": "",
     "comment": ""
   },
   "disk_index": {
-    "support": "",
-    "source_url": "",
+    "support": "partial",
+    "source_url": "https://github.com/unum-cloud/usearch/#serialization--serving-index-from-disk",
     "comment": ""
   },
   "ephemeral": {
@@ -133,7 +133,7 @@
     "comment": ""
   },
   "sharding": {
-    "support": "",
+    "support": "none",
     "source_url": "",
     "comment": ""
   },

diff --git a/docs/tools/vdb_table/data/vectara.json b/docs/tools/vdb_table/data/vectara.json
@@ -20,7 +20,7 @@
   },
   "dev_languages": {
     "value": [
-      "not known"
+      ""
     ],
     "source_url": "",
     "comment": ""