ak-gemini 1.0.3 → 1.0.5
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +40 -20
- package/index.cjs +53 -41351
- package/index.js +45 -2
- package/package.json +3 -3
package/README.md
CHANGED
|
@@ -7,12 +7,13 @@ Use this to power LLM-driven data pipelines, JSON mapping, or any automated AI t
|
|
|
7
7
|
|
|
8
8
|
## Features
|
|
9
9
|
|
|
10
|
-
* **Model-Agnostic
|
|
11
|
-
* **Declarative Examples
|
|
12
|
-
* **Automatic Validation & Repair
|
|
13
|
-
* **
|
|
14
|
-
* **
|
|
15
|
-
* **
|
|
10
|
+
* **Model-Agnostic:** Use any Gemini model (`gemini-2.0-flash` by default)
|
|
11
|
+
* **Declarative Few-shot Examples:** Seed transformations using example mappings, with support for custom keys (`PROMPT`, `ANSWER`, `CONTEXT`, or your own)
|
|
12
|
+
* **Automatic Validation & Repair:** Validate outputs with your own async function; auto-repair failed payloads with LLM feedback loop (exponential backoff, fully configurable)
|
|
13
|
+
* **Token Counting & Safety:** Preview the *exact* Gemini token consumption for any operation—including all examples, instructions, and your input—before sending, so you can avoid window errors and manage costs.
|
|
14
|
+
* **Strong TypeScript/JSDoc Typings:** All public APIs fully typed (see `/types`)
|
|
15
|
+
* **Minimal API Surface:** Dead simple, no ceremony—init, seed, transform, validate.
|
|
16
|
+
* **Robust Logging:** Pluggable logger for all steps, easy debugging
|
|
16
17
|
|
|
17
18
|
---
|
|
18
19
|
|
|
@@ -43,7 +44,7 @@ or pass it directly in the constructor options.
|
|
|
43
44
|
### 2. **Basic Example**
|
|
44
45
|
|
|
45
46
|
```js
|
|
46
|
-
import AITransformer from '
|
|
47
|
+
import AITransformer from 'ak-gemini';
|
|
47
48
|
|
|
48
49
|
const transformer = new AITransformer({
|
|
49
50
|
modelName: 'gemini-2.0-flash', // or your preferred Gemini model
|
|
@@ -72,7 +73,22 @@ console.log(result);
|
|
|
72
73
|
|
|
73
74
|
---
|
|
74
75
|
|
|
75
|
-
### 3. **
|
|
76
|
+
### 3. **Token Window Safety/Preview**
|
|
77
|
+
|
|
78
|
+
Before calling `.message()` or `.seed()`, you can preview the exact token usage that will be sent to Gemini—*including* your system instructions, examples, and user input. This is vital for avoiding window errors and managing context size:
|
|
79
|
+
|
|
80
|
+
```js
|
|
81
|
+
const { totalTokens, breakdown } = await transformer.estimateTokenUsage({ name: "Bob" });
|
|
82
|
+
console.log(`Total tokens: ${totalTokens}`);
|
|
83
|
+
console.log(breakdown); // See per-section token counts
|
|
84
|
+
|
|
85
|
+
// Optional: abort or trim if over limit
|
|
86
|
+
if (totalTokens > 32000) throw new Error("Request too large for selected Gemini model");
|
|
87
|
+
```
|
|
88
|
+
|
|
89
|
+
---
|
|
90
|
+
|
|
91
|
+
### 4. **Automatic Validation & Self-Healing**
|
|
76
92
|
|
|
77
93
|
You can pass a custom async validator—if it fails, the transformer will attempt to self-correct using LLM feedback, retrying up to `maxRetries` times:
|
|
78
94
|
|
|
@@ -127,7 +143,12 @@ You can omit `examples` to use the `examplesFile` (if provided).
|
|
|
127
143
|
|
|
128
144
|
#### `await transformer.message(sourcePayload)`
|
|
129
145
|
|
|
130
|
-
Transforms input JSON to output JSON using the seeded examples and system instructions.
|
|
146
|
+
Transforms input JSON to output JSON using the seeded examples and system instructions. Throws if estimated token window would be exceeded.
|
|
147
|
+
|
|
148
|
+
#### `await transformer.estimateTokenUsage(sourcePayload)`
|
|
149
|
+
|
|
150
|
+
Returns `{ totalTokens, breakdown }` for the *full request* that would be sent to Gemini (system instructions + all examples + your sourcePayload as the new prompt).
|
|
151
|
+
Lets you preview token window safety and abort/trim as needed.
|
|
131
152
|
|
|
132
153
|
#### `await transformer.transformWithValidation(sourcePayload, validatorFn, options?)`
|
|
133
154
|
|
|
@@ -187,10 +208,19 @@ const result = await transformer.transformWithValidation(
|
|
|
187
208
|
|
|
188
209
|
---
|
|
189
210
|
|
|
211
|
+
## Token Window Management & Error Handling
|
|
212
|
+
|
|
213
|
+
* Throws on missing `GEMINI_API_KEY`
|
|
214
|
+
* `.message()` and `.seed()` will *estimate* and prevent calls that would exceed Gemini's model window
|
|
215
|
+
* All API and parsing errors surfaced as `Error` with context
|
|
216
|
+
* Validator and retry failures include the number of attempts and last error
|
|
217
|
+
|
|
218
|
+
---
|
|
219
|
+
|
|
190
220
|
## Testing
|
|
191
221
|
|
|
192
222
|
* **Jest test suite included**
|
|
193
|
-
*
|
|
223
|
+
* Real API integration tests as well as local unit tests
|
|
194
224
|
* 100% coverage for all error cases, configuration options, edge cases
|
|
195
225
|
|
|
196
226
|
Run tests with:
|
|
@@ -200,13 +230,3 @@ npm test
|
|
|
200
230
|
```
|
|
201
231
|
|
|
202
232
|
---
|
|
203
|
-
|
|
204
|
-
## Error Handling
|
|
205
|
-
|
|
206
|
-
* Throws on missing `GEMINI_API_KEY`
|
|
207
|
-
* All API and parsing errors surfaced as `Error` with context
|
|
208
|
-
* Validator and retry failures include the number of attempts and last error
|
|
209
|
-
|
|
210
|
-
---
|
|
211
|
-
|
|
212
|
-
|