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
# ---- llm ----
model: openai:gpt-4o # Specify the LLM to use
temperature: null # Set default temperature parameter (0, 1)
top_p: null # Set default top-p parameter, with a range of (0, 1) or (0, 2) depending on the model
# ---- behavior ----
stream: true # Controls whether to use the stream-style API.
save: true # Indicates whether to persist the message
keybindings: emacs # Choose keybinding style (emacs, vi)
editor: null # Specifies the command used to edit input buffer or session. (e.g. vim, emacs, nano).
wrap: no # Controls text wrapping (no, auto, <max-width>)
wrap_code: false # Enables or disables wrapping of code blocks
# ---- function-calling ----
# Visit https://github.com/sigoden/llm-functions for setup instructions
function_calling: true # Enables or disables function calling (Globally).
mapping_tools: # Alias for a tool or toolset
fs: 'fs_cat,fs_ls,fs_mkdir,fs_rm,fs_write'
use_tools: null # Which tools to use by default. (e.g. 'fs,web_search')
# ---- prelude ----
repl_prelude: null # Set a default role or session for REPL mode (e.g. role:<name>, session:<name>, <session>:<role>)
cmd_prelude: null # Set a default role or session for CMD mode (e.g. role:<name>, session:<name>, <session>:<role>)
agent_prelude: null # Set a session to use when starting a agent (e.g. temp, default)
# ---- session ----
# Controls the persistence of the session. if true, auto save; if false, not save; if null, asking the user
save_session: null
# Compress session when token count reaches or exceeds this threshold
compress_threshold: 4000
# Text prompt used for creating a concise summary of session message
summarize_prompt: 'Summarize the discussion briefly in 200 words or less to use as a prompt for future context.'
# Text prompt used for including the summary of the entire session
summary_prompt: 'This is a summary of the chat history as a recap: '
# ---- RAG ----
# See [RAG-Guide](https://github.com/sigoden/aichat/wiki/RAG-Guide) for more details.
rag_embedding_model: null # Specifies the embedding model used for context retrieval
rag_reranker_model: null # Specifies the reranker model used for sorting retrieved documents
rag_top_k: 5 # Specifies the number of documents to retrieve for answering queries
rag_chunk_size: null # Defines the size of chunks for document processing in characters
rag_chunk_overlap: null # Defines the overlap between chunks
# Defines the query structure using variables like __CONTEXT__ and __INPUT__ to tailor searches to specific needs
rag_template: |
Answer the query based on the context while respecting the rules. (user query, some textual context and rules, all inside xml tags)
<context>
__CONTEXT__
</context>
<rules>
- If you don't know, just say so.
- If you are not sure, ask for clarification.
- Answer in the same language as the user query.
- If the context appears unreadable or of poor quality, tell the user then answer as best as you can.
- If the answer is not in the context but you think you know the answer, explain that to the user then answer with your own knowledge.
- Answer directly and without using xml tags.
</rules>
<user_query>
__INPUT__
</user_query>
# Define document loaders to control how RAG and `.file`/`--file` load files of specific formats.
document_loaders:
# You can add custom loaders using the following syntax:
# <file-extension>: <command-to-load-the-file>
# Note: Use `$1` for input file and `$2` for output file. If `$2` is omitted, use stdout as output.
pdf: 'pdftotext $1 -' # Load .pdf file, see https://poppler.freedesktop.org to set up pdftotext
docx: 'pandoc --to plain $1' # Load .docx file, see https://pandoc.org to set up pandoc
# ---- apperence ----
highlight: true # Controls syntax highlighting
light_theme: false # Activates a light color theme when true. env: AICHAT_LIGHT_THEME
# Custom REPL left/right prompts, see https://github.com/sigoden/aichat/wiki/Custom-REPL-Prompt for more details
left_prompt:
'{color.green}{?session {?agent {agent}>}{session}{?role /}}{!session {?agent {agent}>}}{role}{?rag @{rag}}{color.cyan}{?session )}{!session >}{color.reset} '
right_prompt:
'{color.purple}{?session {?consume_tokens {consume_tokens}({consume_percent}%)}{!consume_tokens {consume_tokens}}}{color.reset}'
# ---- misc ----
serve_addr: 127.0.0.1:8000 # Server listening address
user_agent: null # Set User-Agent HTTP header, use `auto` for aichat/<current-version>
save_shell_history: true # Whether to save shell execution command to the history file
# URL to sync model changes from, e.g., https://cdn.jsdelivr.net/gh/sigoden/aichat@main/models.yaml
sync_models_url: https://raw.githubusercontent.com/sigoden/aichat/refs/heads/main/models.yaml
# ---- clients ----
clients:
# All clients have the following configuration:
# - type: xxxx
# name: xxxx # Only use it to distinguish clients with the same client type. Optional
# models:
# - name: xxxx # Chat model
# max_input_tokens: 100000
# supports_vision: true
# supports_function_calling: true
# - name: xxxx # Embedding model
# type: embedding
# default_chunk_size: 1500
# max_batch_size: 100
# - name: xxxx # Reranker model
# type: reranker
# patch: # Patch api
# chat_completions: # Api type, possible values: chat_completions, embeddings, and rerank
# <regex>: # The regex to match model names, e.g. '.*' 'gpt-4o' 'gpt-4o|gpt-4-.*'
# url: '' # Patch request url
# body: # Patch request body
# <json>
# headers: # Patch request headers
# <key>: <value>
# extra:
# proxy: socks5://127.0.0.1:1080 # Set proxy
# connect_timeout: 10 # Set timeout in seconds for connect to api
# See https://platform.openai.com/docs/quickstart
- type: openai
api_base: https://api.openai.com/v1 # Optional
api_key: xxx
organization_id: org-xxx # Optional
# For any platform compatible with OpenAI's API
- type: openai-compatible
name: ollama
api_base: http://localhost:11434/v1
api_key: xxx # Optional
models:
- name: deepseek-r1
max_input_tokens: 131072
- name: llama3.1
max_input_tokens: 128000
supports_function_calling: true
- name: llama3.2-vision
max_input_tokens: 131072
supports_vision: true
- name: nomic-embed-text
type: embedding
default_chunk_size: 1000
max_batch_size: 50
# See https://ai.google.dev/docs
- type: gemini
api_base: https://generativelanguage.googleapis.com/v1beta
api_key: xxx
patch:
chat_completions:
'.*':
body:
safetySettings:
- category: HARM_CATEGORY_HARASSMENT
threshold: BLOCK_NONE
- category: HARM_CATEGORY_HATE_SPEECH
threshold: BLOCK_NONE
- category: HARM_CATEGORY_SEXUALLY_EXPLICIT
threshold: BLOCK_NONE
- category: HARM_CATEGORY_DANGEROUS_CONTENT
threshold: BLOCK_NONE
# See https://docs.anthropic.com/claude/reference/getting-started-with-the-api
- type: claude
api_base: https://api.anthropic.com/v1 # Optional
api_key: xxx
# See https://docs.mistral.ai/
- type: openai-compatible
name: mistral
api_base: https://api.mistral.ai/v1
api_key: xxx
# See https://docs.x.ai/docs
- type: openai-compatible
name: xai
api_base: https://api.x.ai/v1
api_key: xxx
# See https://docs.ai21.com/docs/quickstart
- type: openai-compatible
name: ai12
api_base: https://api.ai21.com/studio/v1
api_key: xxx
# See https://docs.cohere.com/docs/the-cohere-platform
- type: cohere
api_base: https://api.cohere.ai/v2 # Optional
api_key: xxx
# See https://docs.perplexity.ai/docs/getting-started
- type: openai-compatible
name: perplexity
api_base: https://api.perplexity.ai
api_key: xxx
# See https://console.groq.com/docs/quickstart
- type: openai-compatible
name: groq
api_base: https://api.groq.com/openai/v1
api_key: xxx
# See https://learn.microsoft.com/en-us/azure/ai-services/openai/chatgpt-quickstart
- type: azure-openai
api_base: https://{RESOURCE}.openai.azure.com
api_key: xxx
models:
- name: gpt-4o # Model deployment name
max_input_tokens: 128000
supports_vision: true
supports_function_calling: true
# See https://cloud.google.com/vertex-ai
- type: vertexai
project_id: xxx
location: xxx
# Specifies a application-default-credentials (adc) file
# Run `gcloud auth application-default login` to init the adc file
# see https://cloud.google.com/docs/authentication/external/set-up-adc
adc_file: <gcloud-config-dir>/application_default_credentials.json> # Optional field
patch:
chat_completions:
'gemini-.*':
body:
safetySettings:
- category: HARM_CATEGORY_HARASSMENT
threshold: BLOCK_ONLY_HIGH
- category: HARM_CATEGORY_HATE_SPEECH
threshold: BLOCK_ONLY_HIGH
- category: HARM_CATEGORY_SEXUALLY_EXPLICIT
threshold: BLOCK_ONLY_HIGH
- category: HARM_CATEGORY_DANGEROUS_CONTENT
threshold: BLOCK_ONLY_HIGH
# See https://docs.aws.amazon.com/bedrock/latest/userguide/
- type: bedrock
access_key_id: xxx
secret_access_key: xxx
region: xxx
# See https://developers.cloudflare.com/workers-ai/
- type: openai-compatible
name: cloudflare
api_base: https://api.cloudflare.com/client/v4/accounts/{ACCOUNT_ID}/ai/v1
api_key: xxx
# See https://cloud.baidu.com/doc/WENXINWORKSHOP/index.html
- type: openai-compatible
name: ernie
api_base: https://qianfan.baidubce.com/v2
api_key: xxx
# See https://dashscope.aliyun.com/
- type: openai-compatible
name: qianwen
api_base: https://dashscope.aliyuncs.com/compatible-mode/v1
api_key: xxx
# See https://cloud.tencent.com/product/hunyuan
- type: openai-compatible
name: hunyuan
api_base: https://api.hunyuan.cloud.tencent.com/v1
api_key: xxx
# See https://platform.moonshot.cn/docs/intro
- type: openai-compatible
name: moonshot
api_base: https://api.moonshot.cn/v1
api_key: xxx
# See https://platform.deepseek.com/api-docs/
- type: openai-compatible
name: deepseek
api_base: https://api.deepseek.com
api_key: xxx
# See https://open.bigmodel.cn/dev/howuse/introduction
- type: openai-compatible
name: zhipuai
api_base: https://open.bigmodel.cn/api/paas/v4
api_key: xxx
# See https://platform.lingyiwanwu.com/docs
- type: openai-compatible
name: lingyiwanwu
api_base: https://api.lingyiwanwu.com/v1
api_key: xxx
# See https://platform.minimaxi.com/document/Fast%20access
- type: openai-compatible
name: minimax
api_base: https://api.minimax.chat/v1
api_key: xxx
# See https://openrouter.ai/docs#quick-start
- type: openai-compatible
name: openrouter
api_base: https://openrouter.ai/api/v1
api_key: xxx
# See https://github.com/marketplace/models
- type: openai-compatible
name: github
api_base: https://models.inference.ai.azure.com
api_key: xxx
# See https://deepinfra.com/docs
- type: openai-compatible
name: deepinfra
api_base: https://api.deepinfra.com/v1/openai
api_key: xxx
# ----- RAG dedicated -----
# See https://jina.ai
- type: openai-compatible
name: jina
api_base: https://api.jina.ai/v1
api_key: xxx
# See https://docs.voyageai.com/docs/introduction
- type: openai-compatible
name: voyageai
api_base: https://api.voyageai.com/v1
api_key: xxx