@@ -62,7 +62,7 @@ Build your AI business in three lines of code!
62
62
63
63
* [ gpt-4.1-mini] ( https://platform.openai.com/docs/models/gpt-4.1-mini ) (agent)
64
64
* [ gpt-4.1-nano] ( https://platform.openai.com/docs/models/gpt-4.1-nano ) (router)
65
- * [ text-embedding-3-large] ( https://platform.openai.com/docs/models/text-embedding-3-large ) (embedding)
65
+ * [ text-embedding-3-large] ( https://platform.openai.com/docs/models/text-embedding-3-large ) or [ text-embedding-3-small ] ( https://platform.openai.com/docs/models/text-embedding-3-small ) (embedding)
66
66
* [ tts-1] ( https://platform.openai.com/docs/models/tts-1 ) (audio TTS)
67
67
* [ gpt-4o-mini-transcribe] ( https://platform.openai.com/docs/models/gpt-4o-mini-transcribe ) (audio transcription)
68
68
* [ gemini-2.0-flash] ( https://ai.google.dev/gemini-api/docs/models#gemini-2.0-flash ) (optional)
@@ -308,6 +308,8 @@ config = {
308
308
309
309
### Knowledge Base
310
310
311
+ The Knowledge Base (KB) is meant to store text values and/or small PDFs.
312
+
311
313
``` python
312
314
config = {
313
315
" knowledge_base" : {
@@ -538,13 +540,9 @@ async for response in solana_agent.process("user123", "What are the latest AI de
538
540
print (response, end = " " )
539
541
```
540
542
541
- ## Runtime Prompt Injection
542
-
543
- Many use cases for Solana Agent require training your agents on your company data.
544
-
545
- This can be accomplished via runtime prompt injection. Integrations that work well with FAQs.
543
+ ## Advanced Customization
546
544
547
- This knowledge is accessible to all your AI agents.
545
+ ### Runtime Prompt Injection
548
546
549
547
``` python
550
548
from solana_agent import SolanaAgent
@@ -568,7 +566,7 @@ async for response in solana_agent.process("user123", "How do replace the latch
568
566
print (response, end = " " )
569
567
```
570
568
571
- ## Custom Routing
569
+ ### Custom Routing
572
570
573
571
In advanced cases like implementing a ticketing system on-top of Solana Agent - you can use your own router.
574
572
0 commit comments