Accepting request 1194354 from science:machinelearning

- Update to version 0.3.6:
  * Fixed issue where /api/embed would return an error instead of
    loading the model when the input field was not provided.
  * ollama create can now import Phi-3 models from Safetensors
  * Added progress information to ollama create when importing GGUF
    files
  * Ollama will now import GGUF files faster by minimizing file
    copies
- Update to version 0.3.6:
  * Fixed issue where temporary files would not be cleaned up
  * Fix rare error when Ollama would start up due to invalid model
    data
- Update to version 0.3.4:
 * New embedding models
  - BGE-M3: a large embedding model from BAAI distinguished for 
    its versatility in Multi-Functionality, Multi-Linguality, and 
    Multi-Granularity.
  - BGE-Large: a large embedding model trained in english.
  - Paraphrase-Multilingual: A multilingual embedding model 
    trained on parallel data for 50+ languages.
 * New embedding API with batch support
   - Ollama now supports a new API endpoint /api/embed for 
     embedding generation:
 * This API endpoint supports new features:
   - Batches: generate embeddings for several documents in 
     one request
   - Normalized embeddings: embeddings are now normalized, 
     improving similarity results
   - Truncation: a new truncate parameter that will error if 
     set to false
   - Metrics: responses include load_duration, total_duration and 
     prompt_eval_count metrics

OBS-URL: https://build.opensuse.org/request/show/1194354
OBS-URL: https://build.opensuse.org/package/show/openSUSE:Factory/ollama?expand=0&rev=18

_service

@@ -3,7 +3,7 @@
   <service name="obs_scm" mode="manual">
     <param name="url">https://github.com/ollama/ollama.git</param>
     <param name="scm">git</param>
-    <param name="revision">v0.3.3</param>
+    <param name="revision">v0.3.6</param>
     <param name="versionformat">@PARENT_TAG@</param>
     <param name="versionrewrite-pattern">v(.*)</param>
     <param name="changesgenerate">enable</param>

_servicedata

@@ -1,4 +1,4 @@
 <servicedata>
 <service name="tar_scm">
                 <param name="url">https://github.com/ollama/ollama.git</param>
-              <param name="changesrevision">ce1fb4447efc9958dcf279f7eb2ae6941bec1220</param></service></servicedata>
+              <param name="changesrevision">4c4fe3f87fe1858b35bd0d41e093a0039ec4cee4</param></service></servicedata>

ollama-0.3.3.obscpio

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:80ced6af29997569d44f79381c5cd1d4e51edd3f97d9f5aae0207162b6de26ba
-size 153645582

ollama-0.3.6.obscpio

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96235e8d8cfdc20c732a699cc2036c907027c67482aa75fb0a7f3b6aa5089077
+size 184983566

ollama.changes

@@ -1,3 +1,44 @@
+-------------------------------------------------------------------
+Thu Aug 15 18:59:48 UTC 2024 - Eyad Issa <eyadlorenzo@gmail.com>
+
+- Update to version 0.3.6:
+  * Fixed issue where /api/embed would return an error instead of
+    loading the model when the input field was not provided.
+  * ollama create can now import Phi-3 models from Safetensors
+  * Added progress information to ollama create when importing GGUF
+    files
+  * Ollama will now import GGUF files faster by minimizing file
+    copies
+
+- Update to version 0.3.6:
+  * Fixed issue where temporary files would not be cleaned up
+  * Fix rare error when Ollama would start up due to invalid model
+    data
+
+-------------------------------------------------------------------
+Sun Aug 11 02:40:06 UTC 2024 - Alessandro de Oliveira Faria <cabelo@opensuse.org>
+
+- Update to version 0.3.4:
+ * New embedding models
+  - BGE-M3: a large embedding model from BAAI distinguished for 
+    its versatility in Multi-Functionality, Multi-Linguality, and 
+    Multi-Granularity.
+  - BGE-Large: a large embedding model trained in english.
+  - Paraphrase-Multilingual: A multilingual embedding model 
+    trained on parallel data for 50+ languages.
+ * New embedding API with batch support
+   - Ollama now supports a new API endpoint /api/embed for 
+     embedding generation:
+ * This API endpoint supports new features:
+   - Batches: generate embeddings for several documents in 
+     one request
+   - Normalized embeddings: embeddings are now normalized, 
+     improving similarity results
+   - Truncation: a new truncate parameter that will error if 
+     set to false
+   - Metrics: responses include load_duration, total_duration and 
+     prompt_eval_count metrics
+
 -------------------------------------------------------------------
 Sat Aug 03 09:41:56 UTC 2024 - eyadlorenzo@gmail.com
 

ollama.obsinfo

@@ -1,4 +1,4 @@
 name: ollama
-version: 0.3.3
-mtime: 1722555107
-commit: ce1fb4447efc9958dcf279f7eb2ae6941bec1220
+version: 0.3.6
+mtime: 1723575229
+commit: 4c4fe3f87fe1858b35bd0d41e093a0039ec4cee4

ollama.spec

@@ -17,7 +17,7 @@
 
 
 Name:           ollama
-Version:        0.3.3
+Version:        0.3.6
 Release:        0
 Summary:        Tool for running AI models on-premise
 License:        MIT

vendor.tar.zstd

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85f112c543064fe9979a85aac33cd4f8fd3ab9297bd058aeea044c7e20ad5929
-size 5354897
+oid sha256:55ce911e80d49668a716385a09682e6a6ad44d711486ee38b32e8269a0a6a3df
+size 5354975