Closed Gaute945 closed 5 months ago
prompt ai and recive data using an node.js server
this is needed code for implementing ai later
the bot runs a local api,
cli logs: llama_new_context_with_model: n_ctx = 2048 │ llama_new_context_with_model: freq_base = 1000000.0 │ llama_new_context_with_model: freq_scale = 1 │ llama_new_context_with_model: KV self size = 256.00 MiB, K (f16): 128.00 MiB, V (f16): 128.00 MiB │ llama_build_graph: non-view tensors processed: 1124/1124 │ llama_new_context_with_model: compute buffer total size = 187.22 MiB │ {"timestamp":1704353523,"level":"INFO","function":"main","line":3097,"message":"HTTP server listening","port":"62118","hostnam│ e":"127.0.0.1"} │ {"timestamp":1704353523,"level":"INFO","function":"log_server_request","line":2608,"message":"request","remote_addr":"127.0.0.│ 1","remote_port":43704,"status":200,"method":"HEAD","path":"/","params":{}} │ 2024/01/04 08:32:03 llama.go:508: llama runner started in 1.401130 seconds │ [GIN] 2024/01/04 - 08:32:03 | 200 | 1.675973836s | 127.0.0.1 | POST "/api/generate" │ {"timestamp":1704353528,"level":"INFO","function":"log_server_request","line":2608,"message":"request","remote_addr":"127.0.0.│ 1","remote_port":43704,"status":200,"method":"HEAD","path":"/","params":{}} │ 2024/01/04 08:32:08 llama.go:577: loaded 0 images │ {"timestamp":1704353537,"level":"INFO","function":"log_server_request","line":2608,"message":"request","remote_addr":"127.0.0.│ 1","remote_port":43704,"status":200,"method":"POST","path":"/completion","params":{}} │ {"timestamp":1704353537,"level":"INFO","function":"log_server_request","line":2608,"message":"request","remote_addr":"127.0.0.│ 1","remote_port":43704,"status":200,"method":"POST","path":"/tokenize","params":{}} │ [GIN] 2024/01/04 - 08:32:17 | 200 | 9.548824745s | 127.0.0.1 | POST "/api/generate"
Note:
https://github.com/jmorganca/ollama/tree/main/api
Gaute945
commented
9 months ago Gaute945
commented
9 months ago
prompt ai and recive data using an node.js server
Rationale
this is needed code for implementing ai later
Implementation Details
the bot runs a local api,
Additional Information
cli logs: llama_new_context_with_model: n_ctx = 2048 │ llama_new_context_with_model: freq_base = 1000000.0 │ llama_new_context_with_model: freq_scale = 1 │ llama_new_context_with_model: KV self size = 256.00 MiB, K (f16): 128.00 MiB, V (f16): 128.00 MiB │ llama_build_graph: non-view tensors processed: 1124/1124 │ llama_new_context_with_model: compute buffer total size = 187.22 MiB │ {"timestamp":1704353523,"level":"INFO","function":"main","line":3097,"message":"HTTP server listening","port":"62118","hostnam│ e":"127.0.0.1"} │ {"timestamp":1704353523,"level":"INFO","function":"log_server_request","line":2608,"message":"request","remote_addr":"127.0.0.│ 1","remote_port":43704,"status":200,"method":"HEAD","path":"/","params":{}} │ 2024/01/04 08:32:03 llama.go:508: llama runner started in 1.401130 seconds │ [GIN] 2024/01/04 - 08:32:03 | 200 | 1.675973836s | 127.0.0.1 | POST "/api/generate" │ {"timestamp":1704353528,"level":"INFO","function":"log_server_request","line":2608,"message":"request","remote_addr":"127.0.0.│ 1","remote_port":43704,"status":200,"method":"HEAD","path":"/","params":{}} │ 2024/01/04 08:32:08 llama.go:577: loaded 0 images │ {"timestamp":1704353537,"level":"INFO","function":"log_server_request","line":2608,"message":"request","remote_addr":"127.0.0.│ 1","remote_port":43704,"status":200,"method":"POST","path":"/completion","params":{}} │ {"timestamp":1704353537,"level":"INFO","function":"log_server_request","line":2608,"message":"request","remote_addr":"127.0.0.│ 1","remote_port":43704,"status":200,"method":"POST","path":"/tokenize","params":{}} │ [GIN] 2024/01/04 - 08:32:17 | 200 | 9.548824745s | 127.0.0.1 | POST "/api/generate"
Note: