Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
chenych
chat_demo
Commits
652c33e5
Commit
652c33e5
authored
Sep 14, 2024
by
chenych
Browse files
Fix bugs
parent
cf14b883
Changes
4
Show whitespace changes
Inline
Side-by-side
Showing
4 changed files
with
15 additions
and
17 deletions
+15
-17
client.py
client.py
+1
-1
llm_service/http_client.py
llm_service/http_client.py
+11
-11
llm_service/worker.py
llm_service/worker.py
+2
-4
rag/retriever.py
rag/retriever.py
+1
-1
No files found.
client.py
View file @
652c33e5
...
...
@@ -65,7 +65,7 @@ def stream_query(query, user_id=None):
'query'
:
query
,
'history'
:
[]
}
resp
=
requests
.
ge
t
(
url
,
resp
=
requests
.
pos
t
(
url
,
headers
=
headers
,
data
=
json
.
dumps
(
data
),
timeout
=
300
,
...
...
llm_service/http_client.py
View file @
652c33e5
...
...
@@ -4,7 +4,7 @@ import json
import
httpx
import
configparser
import
torch
import
requests
import
numpy
as
np
from
loguru
import
logger
from
BCEmbedding.tools.langchain
import
BCERerank
...
...
@@ -48,9 +48,9 @@ class OpenAPIClient:
continue
yield
output
async
def
get_response
(
self
,
headers
,
data
):
async
with
httpx
.
AsyncClient
()
as
client
:
resp
=
await
client
.
post
(
self
.
url
,
json
=
data
,
headers
=
headers
,
timeout
=
300
)
def
get_response
(
self
,
headers
,
data
):
resp
=
requests
.
post
(
self
.
url
,
json
=
data
,
headers
=
headers
,
timeout
=
300
)
try
:
result
=
json
.
loads
(
resp
.
content
.
decode
(
"utf-8"
))
output
=
result
[
'choices'
][
0
][
'message'
][
'content'
]
...
...
llm_service/worker.py
View file @
652c33e5
...
...
@@ -137,10 +137,8 @@ class Worker:
if
len
(
chunks
)
==
0
:
logger
.
debug
(
'Response by finetune model'
)
response
=
self
.
response_by_finetune
(
query
,
history
=
history
)
data
=
json
.
loads
(
response
.
content
.
decode
(
"utf-8"
))
chunks
=
[
output
]
response
=
await
self
.
response_by_finetune
(
query
,
history
=
history
)
chunks
=
[
response
]
elif
use_template
:
logger
.
debug
(
'Response by template'
)
response
=
self
.
format_rag_result
(
chunks
,
references
,
stream
=
stream
)
...
...
rag/retriever.py
View file @
652c33e5
...
...
@@ -14,7 +14,7 @@ from BCEmbedding.tools.langchain import BCERerank
from
langchain.retrievers
import
ContextualCompressionRetriever
from
langchain_community.vectorstores.utils
import
DistanceStrategy
from
requests.exceptions
import
RequestException
from
elastic_keywords_search
import
ElasticKeywordsSearch
from
.
elastic_keywords_search
import
ElasticKeywordsSearch
app
=
FastAPI
()
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment