Spaces:

Rutvij1504
/

RRTest_Rag

Paused

App Files Files Community

RRTest_Rag

Commit History

Jul 17

10:50
Implement platform pricing override rule and expand brand misspelling correction filter

Rutvij1504

0bb414f
10:39
Expand identity query matching to handle variations like who am i talking to

Rutvij1504

4ec2da8

Jun 29

15:35
Add vector DB abstraction supporting pgvector and ChromaDB, plus migration testing tool and documentation

Rutvij1504

8bbe1de
09:47
Implement category-based pre-filtering, token-based history pruning, and output token cap adjustments

Rutvij1504

4dde94b

Jun 24

11:16
Enhance security, input sanitization, and request validation in app.py

Rutvij1504

f319e20
07:38
Add README files for Mac and Linux

Rutvij1504

4f24dbd

Jun 22

07:57
Update assistant persona to Mintoak Website Assistant, add evaluation scripts and update data

Rutvij07

5fc8a03

Jun 17

09:57
Add Mintoak overall culture query enhancement rule

Rutvij07

d987eb7
09:10
Limit sources returned to top 1-2 and add scraping scripts

Rutvij07

dfa7a8f
06:39
Implement systematic semantic relevance and domain-context filtering

Rutvij07

e3f6623

Jun 16

17:43
Sort sources by priority (products > blogs > other)

Rutvij07

8392d38
17:33
Fix employee count hallucinations and expand fallback triggers

Rutvij07

dc0330f
17:11
Fix technology head routing and add corporate M&A out-of-scope guardrails

Rutvij07

d22e574
16:46
Update leadership information, separate CTO query rules, and rebuild DB

Rutvij07

c041586
15:29
Update KB addresses, dynamic aggregation, and increase chunk size

Rutvij07

0f0370c
15:06
Update Knowledge Base with scraped non-blog/non-product pages and add scraper agent skill

Rutvij07

947c1f3
12:02
Enhance retrieval filters, add career/address rules, increase max chunk size, and rebuild data

Rutvij07

1270a97
11:12
Update RAG instructions for B2B merchant engagement and add evaluation report

Rutvij07

778d3ac
08:21
fix: allow address, contact, and office location keywords in out-of-scope check

Rutvij07

6a86939
06:32
Upload adapters/mintoak/adapters.safetensors with huggingface_hub

Rutvij1504

Verified signature
e1730af
06:32
Upload adapters/mintoak/adapter_config.json with huggingface_hub

Rutvij1504

Verified signature
d982a24
06:31
feat: integrate fine-tuned Qwen 2.5 1.5B persona and evaluator parity

Rutvij07

b9cbd80

Jun 15

12:27
Update app.py and chat_server.py

Rutvij07

fd12374
11:15
formated the output

Rutvij07

ea874af
10:36
improved chat

Rutvij07

f8ff263
09:11
bug solved

Rutvij07

25e2a5d
08:27
Your commit message here

Rutvij07

1d19943
08:13
Update codebase and configure automatic environment switcher (excluding MLX adapters)

Rutvij07

7a6b0da

Jun 13

13:12
Update application files and add launch script

Rutvij07

1192c0a

Jun 11

11:35
feat: implement config-driven query enhancement registry and sync all workspaces

Rutvij07

7612219
07:48
Update app.py with query optimizer and add ask.py CLI helper

Rutvij07

2401d2a

May 30

05:57
Sync frontend lead capture form and endpoints to Space

Rutvij07

3248ec7
05:40
Deploy UI update like GPT and chat histroy

Rutvij07

4480ae0
05:06
Optimize frontend HTML rendering by throttling markdown parse

Rutvij07

c0021c5
04:58
Revert "Optimize PyTorch CPU thread count to prevent core thrashing"⁠

Rutvij07

c5d47d0
04:51
Optimize PyTorch CPU thread count to prevent core thrashing

Rutvij07

363218e
04:35
Align max_new_tokens to 256

Rutvij07

4f3ce07
04:34
Upgrade to Qwen 2.5 1.5B Instruct GPU model with PyTorch

Rutvij07

352ce38

May 29

19:32
Configure explicit thread count for CPU to prevent thrashing

Rutvij07

f567443
19:20
Fix python f-string syntax error

Rutvij07

9add6b4
19:11
Use pre-compiled CPU wheels for llama-cpp-python

Rutvij07

77bb44b
18:51
Fix exit code 143 by removing GGUF pre-download from build stage

Rutvij07

790a687
18:41
Optimize with GGUF CPU engine and fix catalog injection

Rutvij07

4162ff6
18:21
Deploy RAG chatbot with auto-population

Rutvij07

6e7d23c
17:58
initial commit

Rutvij1504

Verified signature
0ed4bc4

Commit History

Jul 17

Implement platform pricing override rule and expand brand misspelling correction filter

Expand identity query matching to handle variations like who am i talking to

Jun 29

Add vector DB abstraction supporting pgvector and ChromaDB, plus migration testing tool and documentation

Implement category-based pre-filtering, token-based history pruning, and output token cap adjustments

Jun 24

Enhance security, input sanitization, and request validation in app.py

Add README files for Mac and Linux

Jun 22

Update assistant persona to Mintoak Website Assistant, add evaluation scripts and update data

Jun 17

Add Mintoak overall culture query enhancement rule

Limit sources returned to top 1-2 and add scraping scripts

Implement systematic semantic relevance and domain-context filtering

Jun 16

Sort sources by priority (products > blogs > other)

Fix employee count hallucinations and expand fallback triggers

Fix technology head routing and add corporate M&A out-of-scope guardrails

Update leadership information, separate CTO query rules, and rebuild DB

Update KB addresses, dynamic aggregation, and increase chunk size

Update Knowledge Base with scraped non-blog/non-product pages and add scraper agent skill

Enhance retrieval filters, add career/address rules, increase max chunk size, and rebuild data

Update RAG instructions for B2B merchant engagement and add evaluation report

fix: allow address, contact, and office location keywords in out-of-scope check

Upload adapters/mintoak/adapters.safetensors with huggingface_hub

Upload adapters/mintoak/adapter_config.json with huggingface_hub

feat: integrate fine-tuned Qwen 2.5 1.5B persona and evaluator parity

Jun 15

Update app.py and chat_server.py

formated the output

improved chat

bug solved

Your commit message here

Update codebase and configure automatic environment switcher (excluding MLX adapters)

Jun 13

Update application files and add launch script

Jun 11

feat: implement config-driven query enhancement registry and sync all workspaces

Update app.py with query optimizer and add ask.py CLI helper

May 30

Sync frontend lead capture form and endpoints to Space

Deploy UI update like GPT and chat histroy

Optimize frontend HTML rendering by throttling markdown parse

Revert "Optimize PyTorch CPU thread count to prevent core thrashing"⁠

Optimize PyTorch CPU thread count to prevent core thrashing

Align max_new_tokens to 256

Upgrade to Qwen 2.5 1.5B Instruct GPU model with PyTorch

May 29

Configure explicit thread count for CPU to prevent thrashing

Fix python f-string syntax error

Use pre-compiled CPU wheels for llama-cpp-python

Fix exit code 143 by removing GGUF pre-download from build stage

Optimize with GGUF CPU engine and fix catalog injection

Deploy RAG chatbot with auto-population

initial commit