Commit graph

659 commits

Author SHA1 Message Date
Cyber MacGeddon
24d05cbcdf Remove cruft 2025-04-17 16:53:51 +01:00
Cyber MacGeddon
b110af41fb Prompt template working 2025-04-17 16:12:46 +01:00
Cyber MacGeddon
44b1d7e508 async & flow donw 2025-04-16 21:34:39 +01:00
Cyber MacGeddon
28377de390 Separate into separate Flow object 2025-04-16 20:58:48 +01:00
Cyber MacGeddon
51000e39ff More refactoring 2025-04-16 20:50:41 +01:00
Cyber MacGeddon
4c22f23f3a Comments, maybe broke something 2025-04-16 20:46:48 +01:00
Cyber MacGeddon
38cea4c26d VertexAI LLM working 2025-04-16 17:43:49 +01:00
Cyber MacGeddon
b94b4b7389 API finalised 2025-04-16 16:11:18 +01:00
Cyber MacGeddon
91d28e9d56 Change input_output to flow_processor 2025-04-16 13:47:23 +01:00
Cyber MacGeddon
8f89336db3 API tweak for input_output 2025-04-16 12:55:47 +01:00
Cyber MacGeddon
510cfb1103 Token chunker 2025-04-15 23:13:21 +01:00
Cyber MacGeddon
cfdeadfb34 Chunker ported 2025-04-15 23:09:32 +01:00
Cyber MacGeddon
b2b69ff935 Input/output made more flexible 2025-04-15 19:37:30 +01:00
Cyber MacGeddon
c3f1aacbfc Remove cruft 2025-04-15 16:18:03 +01:00
Cyber MacGeddon
60ca5aa3a6 input/output is working 2025-04-15 16:13:18 +01:00
Cyber MacGeddon
98faec7798 PDF done but not working 2025-04-15 00:12:50 +01:00
Cyber MacGeddon
9fdc408a95 Metrics working 2025-04-14 22:39:09 +01:00
Cyber MacGeddon
726baa9932 Tidying 2025-04-14 20:44:22 +01:00
Cyber MacGeddon
74fb52dd3b Separate config part of config-sc 2025-04-14 19:43:36 +01:00
Cyber MacGeddon
d924dad25f Roughly working on config svc 2025-04-14 19:23:43 +01:00
Cyber MacGeddon
1d150cdc21 Working on processor API 2025-04-14 17:51:23 +01:00
Cyber MacGeddon
e66c06f99a New API emerging 2025-04-14 09:05:42 +01:00
Cyber MacGeddon
df6a11bb86 - Changed module names to idents in all processors
- Add --id argument to base
- Tweaked config into handler
2025-04-10 19:14:31 +01:00
cybermaggedon
a06a814a41
Merge master into 0.22 (#341)
* Update README.md text
---------
Co-authored-by: Jack Colquitt <126733989+JackColquitt@users.noreply.github.com>
2025-04-08 17:51:33 +01:00
cybermaggedon
ad5a1bbff4
Remove release bundle step from release (#339) 2025-04-04 15:59:10 +01:00
cybermaggedon
a759a1771e
Added CLI tg-set-prompt command, can be used to update prompts dynamically. (#338)
Added CLI tg-set-prompt command, can be used to update prompts dynamically. (#338)
2025-04-04 15:43:40 +01:00
cybermaggedon
298d09f388
Prompt and agent manager, dynamically load configuration from config-svc
- prompt-template takes config from the config-svc, dynamically reloads
  as new config appears.
- agent-react takes config from config-svc, dynamically reloads
- Fixed lack of data in config queue, needed to take the Earliest, not the
  Latest values.
- Changed text-completion and knowledge-query tool to both use 'query'
  as the argument.
- Prompt and agent no longer have command line args to supply
  configuration.
2025-04-02 16:37:08 +01:00
cybermaggedon
b08c7f03a6
Remove template dir, see github.com/trustgraph-ai/trustgraph-templates (#336) 2025-04-02 14:21:22 +01:00
cybermaggedon
1d222235d3
Configuration initialisation (#335)
* - Fixed error reporting in config
- Updated tg-init-pulsar to be able to load initial config to config-svc
- Tweaked API naming and added more config calls

* Tools to dump out prompts and agent tools
2025-04-02 13:52:33 +01:00
cybermaggedon
a2c64cad4a
Added config reload handler mechanism, calls a Python method on config (#334) 2025-04-02 00:23:30 +01:00
cybermaggedon
88eae0a9f0
Fix no version/config at startup (#333) 2025-04-01 20:54:59 +01:00
cybermaggedon
fa09dc319e
Feature/config service (#332)
Configuration service provides an API to change configuration. Complete configuration is pushed down a config queue so that users have a complete copy of config object.
2025-04-01 19:47:05 +01:00
Cyber MacGeddon
21bda863a7 Merge config-portal templates to here 2025-03-31 22:15:55 +01:00
Cyber MacGeddon
b1cefbe1f7 Update setup.py files to prep 0.22 branch 2025-03-31 22:14:38 +01:00
cybermaggedon
57663742e6
Fix bedrock: (#331)
- Fix missing await
- Fix missing error response
2025-03-27 15:17:08 +00:00
cybermaggedon
8efc3b281d
Fix missing openai symbol / allow specifying base URL (#330) 2025-03-25 21:12:34 +00:00
cybermaggedon
b1ab2938b0
Fix/minor issues (#329)
* Fix MistralAI, symbol error caused it to fail to start

* Update templates
2025-03-25 19:14:56 +00:00
cybermaggedon
222de268c7
LMStudio template support (#328) 2025-03-22 00:56:40 +00:00
cybermaggedon
6ceb926b69
Merge pull request #327 from trustgraph-ai/release/v0.21
0.21 to master
2025-03-22 00:45:02 +00:00
cybermaggedon
482592b976
Added Mistral OCR client (#326)
- Added Mistral OCR client
- Template updates for pdf-ocr
- Template updates for pdf-ocr-mistral
2025-03-22 00:27:20 +00:00
Tyler Oliver
fe422b2b95
Add support for Cassandra auth with SSL check (#318)
Following recommended approach in Datastax documenation I've added the necessary TLS/SSL check

https://docs.datastax.com/en/developer/python-driver/3.17/security/index.html
2025-03-20 22:25:23 +00:00
cybermaggedon
322725be04
Fix container build (#325) 2025-03-20 09:38:54 +00:00
cybermaggedon
c759d55734
Added module which does OCR for PDF, pdf-ocr in a separate package (#324)
(has a lot of dependencies).  Uses Tesseract.
2025-03-20 09:29:40 +00:00
cybermaggedon
cbfe37fec7
Integration with LM Studio LLM hosting (#323) 2025-03-19 19:07:56 +00:00
cybermaggedon
64e42bed6f
Fix/async send typos (#322) 2025-03-19 00:03:58 +00:00
cybermaggedon
1495666e65
Fix typo (#321) 2025-03-18 23:40:31 +00:00
cybermaggedon
dd4a119f49
Fix broken setup.py (#320) 2025-03-18 21:09:18 +00:00
cybermaggedon
6565adb1ec
Enable AKS integration of text-completion-azure-openai (#319)
Reconfigure so that AZURE_TOKEN, AZURE_MODEL and AZURE_ENDPOINT
can be used to set the token/model/endpoint parameters.  This allows it to
be deployed in K8s and use secrets to set these environment variables
2025-03-18 20:27:45 +00:00
cybermaggedon
a22bf0f04e
Azure AKS, experimenting with config (#317) 2025-03-15 12:41:46 +00:00
cybermaggedon
1db6dd5dfd
Support bedrock inference profiles (#314)
* Break out enums for different model types

* Add model detection for inference profiles in US and EU

* Encapsulate model handling, make it easier to manage
2025-03-15 12:39:15 +00:00