### What problem does this PR solve?
1. Use input length to prepare res
2. Adjust torch_empty_cache code location
### Type of change
- [x] Refactoring
- [x] Performance Improvement
fix: preserve correct MIME & unify data URL handling for vision inputs
(relates #9248)
- Updated image2base64() to return a full data URL
(data:image/<fmt>;base64,...) with accurate MIME
- Removed hardcoded image/jpeg in Base._image_prompt(); pass through
data URLs and default raw base64 to image/png
- Set AnthropicCV._image_prompt() raw base64 media_type default to
image/png
- Ensures MIME type matches actual image content, fixing “cannot process
base64 image” errors on vLLM/OpenAI-compatible backends
### What problem does this PR solve?
This PR fixes a compatibility issue where base64-encoded images sent to
vision models (e.g., vLLM/OpenAI-compatible backends) were rejected due
to mismatched MIME type or incorrect decoding.
Previously, the backend:
- Always converted raw base64 into data:image/jpeg;base64,... even if
the actual content was PNG.
- In some cases, base64 decoding was attempted on the full data URL
string instead of the pure base64 part.
This caused errors like:
```
cannot process base64 image
failed to decode base64 string: illegal base64 data at input byte 0
```
by strict validators such as vLLM.
With this fix, the MIME type in the request now matches the actual image
content, and data URLs are correctly handled or passed through, ensuring
vision models can decode and process images reliably.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
All models pass the mock response tests, which means that if a model can
return the correct response, everything should work as expected.
However, not all models have been fully tested in a real environment,
the real API_KEY. I suggest actively monitoring the refactored models
over the coming period to ensure they work correctly and fixing them
step by step, or waiting to merge until most have been tested in
practical environment.
### Type of change
- [x] Refactoring
Updated constructors for base and derived classes in chat, embedding,
rerank, sequence2txt, and tts models to accept **kwargs. This change
improves extensibility and allows passing additional parameters without
breaking existing interfaces.
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: IT: Sop.Son <sop.son@feavn.local>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
### What problem does this PR solve?
https://github.com/infiniflow/ragflow/issues/9177
The reason should be due to the gemin internal use a different parameter
name
`
max_output_tokens (int):
Optional. The maximum number of tokens to include in a
response candidate.
Note: The default value varies by model, see the
``Model.output_token_limit`` attribute of the ``Model``
returned from the ``getModel`` function.
This field is a member of `oneof`_ ``_max_output_tokens``.
`
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
#9082#6365
<u> **WARNING: it's not compatible with the older version of `Agent`
module, which means that `Agent` from older versions can not work
anymore.**</u>
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
fix error 429 api rate limit when building knowledge graph for all chat
model and Mistral embedding model.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
fix issue with `keep_alive=-1` for ollama chat model by allowing a user
to set an additional configuration option. It is no-breaking change
because it still uses a previous default value such as: `keep_alive=-1`
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [X] Performance Improvement
- [X] Other (please describe):
- Additional configuration option has been added to control behavior of
RAGFlow while working with ollama LLM
### What problem does this PR solve?
Add model provider DeepInfra. This model list comes from our community.
NOTE: most endpoints haven't been tested, but they should work as OpenAI
does.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Correct the logging message from "OpenAI cat_with_tools" to "OpenAI
chat_with_tools" in the `_exceptions` method of the `Base` class to
accurately reflect the method name and improve error traceability.
### Type of change
- [x] Typo
### What problem does this PR solve?
Add xAI provider (experimental feature, requires user feedback).
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Based on https://github.com/infiniflow/ragflow/issues/8740
1. A better handle for 'NoneType' object is not subscriptable
2. Add some logs to get the internal message
### Type of change
- [x] Refactoring
fix: retry embedding with Qwen family models when limits temporarily
reached.
APIs of Qwen family models are limited by calling rates. When reached,
the "output" attribute of the "resp" will be None, and in turn cause
TypeError when trying to retrieve "embeddings". Since these limits are
almost temporary, I have added a simple retry mechanism to avoid it.
Besides, if retry_max reached, the error can be early raised, instead of
hidden behind "TypeError".
### What problem does this PR solve?
Sometimes Qwen blocks calling due to rate limits, but it will cause the
whole parsing procedure stops when creating knowledge base. In this
situation, resp["output"] will be None, and resp["output"]["embeddings"]
will cause TypeError. Since the limits are temporary, I apply a simple
retry mechanism to solve it.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
The following error occurred during local testing, which should be fixed
by configuring 'exist_ok=True'.
```log
set_progress(7461edc2535c11f0a2aa0242c0a82009), progress: -1, progress_msg: 21:41:41 Page(1~100000001): [ERROR][Errno 17] File exists: '/ragflow/tmp'
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
This PR introduces Google Cloud Vision API integration to enhance image
understanding capabilities in the application. It addresses the need for
advanced image description and chat functionalities by implementing a
new `GoogleCV` class to handle API interactions and updating relevant
configurations. This enables users to leverage Google Cloud Vision for
image-to-text tasks, improving the application's ability to process and
interpret visual data.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
This PR addresses an incompatibility issue with the Google Chat API by
correcting the message content format in the `GoogleChat` class.
Previously, the content was directly assigned to the "parts" field,
which did not align with the API's expected format. This change ensures
that messages are properly formatted with a "text" key within a
dictionary, as required by the API.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
[https://github.com/infiniflow/ragflow/issues/8324](url)
docker image version: v0.19.1
The `_clean_conf` function was not implemented in the `_chat` and
`chat_streamly` methods of the `GeminiChat` class, causing the error
"Unknown field for GenerationConfig: max_tokens" when the default LLM
config includes the "max_tokens" parameter.
**Buggy Code(ragflow/rag/llm/chat_model.py)**
```python
class GeminiChat(Base):
def __init__(self, key, model_name, base_url=None, **kwargs):
super().__init__(key, model_name, base_url=base_url, **kwargs)
from google.generativeai import GenerativeModel, client
client.configure(api_key=key)
_client = client.get_default_generative_client()
self.model_name = "models/" + model_name
self.model = GenerativeModel(model_name=self.model_name)
self.model._client = _client
def _clean_conf(self, gen_conf):
for k in list(gen_conf.keys()):
if k not in ["temperature", "top_p"]:
del gen_conf[k]
return gen_conf
def _chat(self, history, gen_conf):
from google.generativeai.types import content_types
system = history[0]["content"] if history and history[0]["role"] == "system" else ""
hist = []
for item in history:
if item["role"] == "system":
continue
hist.append(deepcopy(item))
item = hist[-1]
if "role" in item and item["role"] == "assistant":
item["role"] = "model"
if "role" in item and item["role"] == "system":
item["role"] = "user"
if "content" in item:
item["parts"] = item.pop("content")
if system:
self.model._system_instruction = content_types.to_content(system)
response = self.model.generate_content(hist, generation_config=gen_conf)
ans = response.text
return ans, response.usage_metadata.total_token_count
def chat_streamly(self, system, history, gen_conf):
from google.generativeai.types import content_types
if system:
self.model._system_instruction = content_types.to_content(system)
#❌_clean_conf was not implemented
for k in list(gen_conf.keys()):
if k not in ["temperature", "top_p", "max_tokens"]:
del gen_conf[k]
for item in history:
if "role" in item and item["role"] == "assistant":
item["role"] = "model"
if "content" in item:
item["parts"] = item.pop("content")
ans = ""
try:
response = self.model.generate_content(history, generation_config=gen_conf, stream=True)
for resp in response:
ans = resp.text
yield ans
yield response._chunks[-1].usage_metadata.total_token_count
except Exception as e:
yield ans + "\n**ERROR**: " + str(e)
yield 0
```
**Implement the _clean_conf function**
```python
class GeminiChat(Base):
def __init__(self, key, model_name, base_url=None, **kwargs):
super().__init__(key, model_name, base_url=base_url, **kwargs)
from google.generativeai import GenerativeModel, client
client.configure(api_key=key)
_client = client.get_default_generative_client()
self.model_name = "models/" + model_name
self.model = GenerativeModel(model_name=self.model_name)
self.model._client = _client
def _clean_conf(self, gen_conf):
for k in list(gen_conf.keys()):
if k not in ["temperature", "top_p"]:
del gen_conf[k]
return gen_conf
def _chat(self, history, gen_conf):
from google.generativeai.types import content_types
#✅ implement _clean_conf to remove the wrong parameters
gen_conf = self._clean_conf(gen_conf)
system = history[0]["content"] if history and history[0]["role"] == "system" else ""
hist = []
for item in history:
if item["role"] == "system":
continue
hist.append(deepcopy(item))
item = hist[-1]
if "role" in item and item["role"] == "assistant":
item["role"] = "model"
if "role" in item and item["role"] == "system":
item["role"] = "user"
if "content" in item:
item["parts"] = item.pop("content")
if system:
self.model._system_instruction = content_types.to_content(system)
response = self.model.generate_content(hist, generation_config=gen_conf)
ans = response.text
return ans, response.usage_metadata.total_token_count
def chat_streamly(self, system, history, gen_conf):
from google.generativeai.types import content_types
#✅ implement _clean_conf to remove the wrong parameters
gen_conf = self._clean_conf(gen_conf)
if system:
self.model._system_instruction = content_types.to_content(system)
#✅Removed duplicate parameter filtering logic "for k in list(gen_conf.keys()):"
for item in history:
if "role" in item and item["role"] == "assistant":
item["role"] = "model"
if "content" in item:
item["parts"] = item.pop("content")
ans = ""
try:
response = self.model.generate_content(history, generation_config=gen_conf, stream=True)
for resp in response:
ans = resp.text
yield ans
yield response._chunks[-1].usage_metadata.total_token_count
except Exception as e:
yield ans + "\n**ERROR**: " + str(e)
yield 0
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
image_version: v0.19.1
This PR fixes a bug in the HuggingFaceEmBedding API method that was
causing AssertionError: assert len(vects) == len(docs) during the
document embedding process.
#### Problem
The HuggingFaceEmbed.encode() method had an early return statement
inside the for loop, causing it to return after processing only the
first text input instead of processing all texts in the input list.
**Error Messenge**
```python
AssertionError: assert len(vects) == len(docs) # input chunks != embedded vectors from embedding api
File "/ragflow/rag/svr/task_executor.py", line 442, in embedding
```
**Buggy code(/ragflow/rag/llm/embedding_model.py)**
```python
class HuggingFaceEmbed(Base):
def __init__(self, key, model_name, base_url=None):
if not model_name:
raise ValueError("Model name cannot be None")
self.key = key
self.model_name = model_name.split("___")[0]
self.base_url = base_url or "http://127.0.0.1:8080"
def encode(self, texts: list):
embeddings = []
for text in texts:
response = requests.post(...)
if response.status_code == 200:
try:
embedding = response.json()
embeddings.append(embedding[0])
# ❌ Early return
return np.array(embeddings), sum([num_tokens_from_string(text) for text in texts])
except Exception as _e:
log_exception(_e, response)
else:
raise Exception(...)
```
**Fixed Code(I just Rollback this function to the v0.19.0 version)**
```python
Class HuggingFaceEmbed(Base):
def __init__(self, key, model_name, base_url=None):
if not model_name:
raise ValueError("Model name cannot be None")
self.key = key
self.model_name = model_name.split("___")[0]
self.base_url = base_url or "http://127.0.0.1:8080"
def encode(self, texts: list):
embeddings = []
for text in texts:
response = requests.post(...)
if response.status_code == 200:
embedding = response.json()
embeddings.append(embedding[0]) # ✅ Only append, no return
else:
raise Exception(...)
return np.array(embeddings), sum([num_tokens_from_string(text) for text in texts]) # ✅ Return after processing all
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
