forked from airbytehq/terraform-provider-airbyte
/
destination_langchain_data_source.go
executable file
·383 lines (362 loc) · 15.1 KB
/
destination_langchain_data_source.go
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
// Code generated by Speakeasy (https://speakeasyapi.dev). DO NOT EDIT.
package provider
import (
"github.com/ryan-pip/terraform-provider-airbyte/internal/sdk"
"github.com/ryan-pip/terraform-provider-airbyte/internal/sdk/pkg/models/operations"
"context"
"fmt"
"github.com/ryan-pip/terraform-provider-airbyte/internal/validators"
"github.com/hashicorp/terraform-plugin-framework-validators/stringvalidator"
"github.com/hashicorp/terraform-plugin-framework/datasource"
"github.com/hashicorp/terraform-plugin-framework/datasource/schema"
"github.com/hashicorp/terraform-plugin-framework/schema/validator"
"github.com/hashicorp/terraform-plugin-framework/types"
"github.com/hashicorp/terraform-plugin-framework/types/basetypes"
)
// Ensure provider defined types fully satisfy framework interfaces.
var _ datasource.DataSource = &DestinationLangchainDataSource{}
var _ datasource.DataSourceWithConfigure = &DestinationLangchainDataSource{}
func NewDestinationLangchainDataSource() datasource.DataSource {
return &DestinationLangchainDataSource{}
}
// DestinationLangchainDataSource is the data source implementation.
type DestinationLangchainDataSource struct {
client *sdk.SDK
}
// DestinationLangchainDataSourceModel describes the data model.
type DestinationLangchainDataSourceModel struct {
Configuration DestinationLangchain `tfsdk:"configuration"`
DestinationID types.String `tfsdk:"destination_id"`
Name types.String `tfsdk:"name"`
WorkspaceID types.String `tfsdk:"workspace_id"`
}
// Metadata returns the data source type name.
func (r *DestinationLangchainDataSource) Metadata(ctx context.Context, req datasource.MetadataRequest, resp *datasource.MetadataResponse) {
resp.TypeName = req.ProviderTypeName + "_destination_langchain"
}
// Schema defines the schema for the data source.
func (r *DestinationLangchainDataSource) Schema(ctx context.Context, req datasource.SchemaRequest, resp *datasource.SchemaResponse) {
resp.Schema = schema.Schema{
MarkdownDescription: "DestinationLangchain DataSource",
Attributes: map[string]schema.Attribute{
"configuration": schema.SingleNestedAttribute{
Computed: true,
Attributes: map[string]schema.Attribute{
"destination_type": schema.StringAttribute{
Computed: true,
Validators: []validator.String{
stringvalidator.OneOf(
"langchain",
),
},
Description: `must be one of ["langchain"]`,
},
"embedding": schema.SingleNestedAttribute{
Computed: true,
Attributes: map[string]schema.Attribute{
"destination_langchain_embedding_fake": schema.SingleNestedAttribute{
Computed: true,
Attributes: map[string]schema.Attribute{
"mode": schema.StringAttribute{
Computed: true,
Validators: []validator.String{
stringvalidator.OneOf(
"fake",
),
},
Description: `must be one of ["fake"]`,
},
},
Description: `Use a fake embedding made out of random vectors with 1536 embedding dimensions. This is useful for testing the data pipeline without incurring any costs.`,
},
"destination_langchain_embedding_open_ai": schema.SingleNestedAttribute{
Computed: true,
Attributes: map[string]schema.Attribute{
"mode": schema.StringAttribute{
Computed: true,
Validators: []validator.String{
stringvalidator.OneOf(
"openai",
),
},
Description: `must be one of ["openai"]`,
},
"openai_key": schema.StringAttribute{
Computed: true,
},
},
Description: `Use the OpenAI API to embed text. This option is using the text-embedding-ada-002 model with 1536 embedding dimensions.`,
},
"destination_langchain_update_embedding_fake": schema.SingleNestedAttribute{
Computed: true,
Attributes: map[string]schema.Attribute{
"mode": schema.StringAttribute{
Computed: true,
Validators: []validator.String{
stringvalidator.OneOf(
"fake",
),
},
Description: `must be one of ["fake"]`,
},
},
Description: `Use a fake embedding made out of random vectors with 1536 embedding dimensions. This is useful for testing the data pipeline without incurring any costs.`,
},
"destination_langchain_update_embedding_open_ai": schema.SingleNestedAttribute{
Computed: true,
Attributes: map[string]schema.Attribute{
"mode": schema.StringAttribute{
Computed: true,
Validators: []validator.String{
stringvalidator.OneOf(
"openai",
),
},
Description: `must be one of ["openai"]`,
},
"openai_key": schema.StringAttribute{
Computed: true,
},
},
Description: `Use the OpenAI API to embed text. This option is using the text-embedding-ada-002 model with 1536 embedding dimensions.`,
},
},
Validators: []validator.Object{
validators.ExactlyOneChild(),
},
Description: `Embedding configuration`,
},
"indexing": schema.SingleNestedAttribute{
Computed: true,
Attributes: map[string]schema.Attribute{
"destination_langchain_indexing_chroma_local_persistance": schema.SingleNestedAttribute{
Computed: true,
Attributes: map[string]schema.Attribute{
"collection_name": schema.StringAttribute{
Computed: true,
Description: `Name of the collection to use.`,
},
"destination_path": schema.StringAttribute{
Computed: true,
Description: `Path to the directory where chroma files will be written. The files will be placed inside that local mount.`,
},
"mode": schema.StringAttribute{
Computed: true,
Validators: []validator.String{
stringvalidator.OneOf(
"chroma_local",
),
},
Description: `must be one of ["chroma_local"]`,
},
},
Description: `Chroma is a popular vector store that can be used to store and retrieve embeddings. It will build its index in memory and persist it to disk by the end of the sync.`,
},
"destination_langchain_indexing_doc_array_hnsw_search": schema.SingleNestedAttribute{
Computed: true,
Attributes: map[string]schema.Attribute{
"destination_path": schema.StringAttribute{
Computed: true,
Description: `Path to the directory where hnswlib and meta data files will be written. The files will be placed inside that local mount. All files in the specified destination directory will be deleted on each run.`,
},
"mode": schema.StringAttribute{
Computed: true,
Validators: []validator.String{
stringvalidator.OneOf(
"DocArrayHnswSearch",
),
},
Description: `must be one of ["DocArrayHnswSearch"]`,
},
},
Description: `DocArrayHnswSearch is a lightweight Document Index implementation provided by Docarray that runs fully locally and is best suited for small- to medium-sized datasets. It stores vectors on disk in hnswlib, and stores all other data in SQLite.`,
},
"destination_langchain_indexing_pinecone": schema.SingleNestedAttribute{
Computed: true,
Attributes: map[string]schema.Attribute{
"index": schema.StringAttribute{
Computed: true,
Description: `Pinecone index to use`,
},
"mode": schema.StringAttribute{
Computed: true,
Validators: []validator.String{
stringvalidator.OneOf(
"pinecone",
),
},
Description: `must be one of ["pinecone"]`,
},
"pinecone_environment": schema.StringAttribute{
Computed: true,
Description: `Pinecone environment to use`,
},
"pinecone_key": schema.StringAttribute{
Computed: true,
},
},
Description: `Pinecone is a popular vector store that can be used to store and retrieve embeddings. It is a managed service and can also be queried from outside of langchain.`,
},
"destination_langchain_update_indexing_chroma_local_persistance": schema.SingleNestedAttribute{
Computed: true,
Attributes: map[string]schema.Attribute{
"collection_name": schema.StringAttribute{
Computed: true,
Description: `Name of the collection to use.`,
},
"destination_path": schema.StringAttribute{
Computed: true,
Description: `Path to the directory where chroma files will be written. The files will be placed inside that local mount.`,
},
"mode": schema.StringAttribute{
Computed: true,
Validators: []validator.String{
stringvalidator.OneOf(
"chroma_local",
),
},
Description: `must be one of ["chroma_local"]`,
},
},
Description: `Chroma is a popular vector store that can be used to store and retrieve embeddings. It will build its index in memory and persist it to disk by the end of the sync.`,
},
"destination_langchain_update_indexing_doc_array_hnsw_search": schema.SingleNestedAttribute{
Computed: true,
Attributes: map[string]schema.Attribute{
"destination_path": schema.StringAttribute{
Computed: true,
Description: `Path to the directory where hnswlib and meta data files will be written. The files will be placed inside that local mount. All files in the specified destination directory will be deleted on each run.`,
},
"mode": schema.StringAttribute{
Computed: true,
Validators: []validator.String{
stringvalidator.OneOf(
"DocArrayHnswSearch",
),
},
Description: `must be one of ["DocArrayHnswSearch"]`,
},
},
Description: `DocArrayHnswSearch is a lightweight Document Index implementation provided by Docarray that runs fully locally and is best suited for small- to medium-sized datasets. It stores vectors on disk in hnswlib, and stores all other data in SQLite.`,
},
"destination_langchain_update_indexing_pinecone": schema.SingleNestedAttribute{
Computed: true,
Attributes: map[string]schema.Attribute{
"index": schema.StringAttribute{
Computed: true,
Description: `Pinecone index to use`,
},
"mode": schema.StringAttribute{
Computed: true,
Validators: []validator.String{
stringvalidator.OneOf(
"pinecone",
),
},
Description: `must be one of ["pinecone"]`,
},
"pinecone_environment": schema.StringAttribute{
Computed: true,
Description: `Pinecone environment to use`,
},
"pinecone_key": schema.StringAttribute{
Computed: true,
},
},
Description: `Pinecone is a popular vector store that can be used to store and retrieve embeddings. It is a managed service and can also be queried from outside of langchain.`,
},
},
Validators: []validator.Object{
validators.ExactlyOneChild(),
},
Description: `Indexing configuration`,
},
"processing": schema.SingleNestedAttribute{
Computed: true,
Attributes: map[string]schema.Attribute{
"chunk_overlap": schema.Int64Attribute{
Computed: true,
Description: `Size of overlap between chunks in tokens to store in vector store to better capture relevant context`,
},
"chunk_size": schema.Int64Attribute{
Computed: true,
Description: `Size of chunks in tokens to store in vector store (make sure it is not too big for the context if your LLM)`,
},
"text_fields": schema.ListAttribute{
Computed: true,
ElementType: types.StringType,
Description: `List of fields in the record that should be used to calculate the embedding. All other fields are passed along as meta fields. The field list is applied to all streams in the same way and non-existing fields are ignored. If none are defined, all fields are considered text fields. When specifying text fields, you can access nested fields in the record by using dot notation, e.g. ` + "`" + `user.name` + "`" + ` will access the ` + "`" + `name` + "`" + ` field in the ` + "`" + `user` + "`" + ` object. It's also possible to use wildcards to access all fields in an object, e.g. ` + "`" + `users.*.name` + "`" + ` will access all ` + "`" + `names` + "`" + ` fields in all entries of the ` + "`" + `users` + "`" + ` array.`,
},
},
},
},
},
"destination_id": schema.StringAttribute{
Required: true,
},
"name": schema.StringAttribute{
Computed: true,
},
"workspace_id": schema.StringAttribute{
Computed: true,
},
},
}
}
func (r *DestinationLangchainDataSource) Configure(ctx context.Context, req datasource.ConfigureRequest, resp *datasource.ConfigureResponse) {
// Prevent panic if the provider has not been configured.
if req.ProviderData == nil {
return
}
client, ok := req.ProviderData.(*sdk.SDK)
if !ok {
resp.Diagnostics.AddError(
"Unexpected DataSource Configure Type",
fmt.Sprintf("Expected *sdk.SDK, got: %T. Please report this issue to the provider developers.", req.ProviderData),
)
return
}
r.client = client
}
func (r *DestinationLangchainDataSource) Read(ctx context.Context, req datasource.ReadRequest, resp *datasource.ReadResponse) {
var data *DestinationLangchainDataSourceModel
var item types.Object
resp.Diagnostics.Append(req.Config.Get(ctx, &item)...)
if resp.Diagnostics.HasError() {
return
}
resp.Diagnostics.Append(item.As(ctx, &data, basetypes.ObjectAsOptions{
UnhandledNullAsEmpty: true,
UnhandledUnknownAsEmpty: true,
})...)
if resp.Diagnostics.HasError() {
return
}
destinationID := data.DestinationID.ValueString()
request := operations.GetDestinationLangchainRequest{
DestinationID: destinationID,
}
res, err := r.client.Destinations.GetDestinationLangchain(ctx, request)
if err != nil {
resp.Diagnostics.AddError("failure to invoke API", err.Error())
if res != nil && res.RawResponse != nil {
resp.Diagnostics.AddError("unexpected http request/response", debugResponse(res.RawResponse))
}
return
}
if res == nil {
resp.Diagnostics.AddError("unexpected response from API", fmt.Sprintf("%v", res))
return
}
if res.StatusCode != 200 {
resp.Diagnostics.AddError(fmt.Sprintf("unexpected response from API. Got an unexpected response code %v", res.StatusCode), debugResponse(res.RawResponse))
return
}
if res.DestinationResponse == nil {
resp.Diagnostics.AddError("unexpected response from API. No response body", debugResponse(res.RawResponse))
return
}
data.RefreshFromGetResponse(res.DestinationResponse)
// Save updated data into Terraform state
resp.Diagnostics.Append(resp.State.Set(ctx, &data)...)
}