fix(chat_model): handle plain Azure-OpenAI keys without JSONDecodeError (#17204) - #17215
Open
Harsh23Kashyap wants to merge 1223 commits into
Open
fix(chat_model): handle plain Azure-OpenAI keys without JSONDecodeError (#17204)#17215Harsh23Kashyap wants to merge 1223 commits into
Harsh23Kashyap wants to merge 1223 commits into
Conversation
### Summary Refine ingestion task state transitions
…#16794) ## What An **Await Response** (`UserFillUp`) node placed inside a **Loop** now pauses and waits for a fresh user response on **every** iteration, instead of only on the first one. ## Problem When a `UserFillUp` node lives inside a `Loop`, it only paused for input on the first iteration. On subsequent iterations the loop ran straight through, silently reusing the answer the user gave the first time. Root cause is in `UserFillUp._invoke` / the canvas wait-check (`agent/canvas.py`). The wait-check decides whether to pause by calling `Canvas._is_input_field_satisfied` on the node's form fields — a field counts as satisfied as soon as its `value` is not `None`: ```python @staticmethod def _is_input_field_satisfied(field): ... if value is None: return False return True ``` The same component object is reused across loop iterations, and `UserFillUp._invoke` writes the answer into `self._param.inputs[...]["value"]` via `set_input_value`. Nothing cleared those values when the node was re-entered for the next iteration, so: | Iteration | Entry (no answer yet) | Field value | Satisfied? | Result | |---|---|---|---|---| | 1 | fresh | `None` | no | pauses ✅ | | 1 | resume w/ answer | `answer` | yes | continues ✅ | | 2 | fresh | `answer` (**stale**) | yes | continues ❌ (should pause) | ## Fix When a `UserFillUp` is entered without a fresh user answer (`merged_inputs` is empty), clear the retained form values so the wait-check treats the form as unsatisfied and pauses again: ```python merged_inputs = self._merge_runtime_inputs(kwargs.get("inputs", {})) if not merged_inputs: self._clear_form_values() ``` - Fresh entry / new loop iteration → no answer supplied → values cleared → node pauses and waits. - Resume with an answer → `merged_inputs` is non-empty → values applied normally, nothing cleared. - Non-loop behavior is unchanged: the first entry already had `None` values, so clearing is a no-op there. `Begin` overrides `_invoke` and is unaffected. ## Tests Added to `test/testcases/test_web_api/test_canvas_app/test_fillup_unit.py`: - `test_user_fillup_clears_stale_values_on_reentry_without_answer` — a retained value is cleared on a fresh entry with no answer (loop re-entry). - `test_user_fillup_keeps_values_when_answer_supplied` — a supplied answer is applied and not cleared. All unit tests pass and `ruff check` is clean. ## Scope This targets the Python agent runtime (`agent/`). It is independent of any other in-flight Await Response change.
### Summary Sync code from EE Signed-off-by: Jin Hai <haijin.chn@gmail.com>
…reprocessing (infiniflow#7316) (infiniflow#16785) Fixes infiniflow#7316. ## Problem `deepdoc/vision/operators.py` defines the image-standardize preprocessing op as `class StandardizeImag` (missing the final `e`), but every caller — including `deepdoc/vision/recognizer.py::Recognizer.preprocess` — looks the class up by the canonical string `"StandardizeImage"` via: ```python op_type = new_op_info.pop("type") # "StandardizeImage" preprocess_ops.append(getattr(operators, op_type)(**new_op_info)) ``` So `getattr(operators, "StandardizeImage")` raised `AttributeError`, and the "StandardizeImage" preprocessing step silently never ran for any image pipeline that used the dynamic dispatch (LayoutLMv3 and friends). The user-visible symptom is that the standardize step is missing entirely from the preprocessing chain, so the model gets un-normalized images. ## Production fix ```diff -class StandardizeImag: +class StandardizeImage: """normalize image Args: mean (list): im - mean std (list): im / std is_scale (bool): whether need im / 255 norm_type (str): type in ['mean_std', 'none'] """ ``` That's the entire production change — a one-character class rename. The misnamed `StandardizeImag` had no other references in the codebase (verified via `git grep`), so removing it is safe; every caller uses the canonical `"StandardizeImage"` string and will now resolve correctly. ## Tests New `test/unit_test/deepdoc/vision/test_operators_standardize_image.py` with six regression tests, all green locally: ``` test_standardize_image_class_resolves_by_canonical_name PASSED test_standardize_image_callable_matches_legacy_alias_name PASSED test_standardize_image_normalizes_input_with_mean_std_and_is_scale PASSED test_standardize_image_skips_scaling_when_is_scale_false PASSED test_standardize_image_norm_type_none_passes_image_through PASSED test_standardize_image_via_module_getattr_dispatch_path PASSED 6 passed in 0.18s ``` The tests: 1. **Pin the dispatch contract** (`hasattr(operators, "StandardizeImage")`) — this is the exact check the recognizer's `getattr` would do, so any future regression fails the same way the runtime would. 2. **Pin that the misspelled name is gone** — if a downstream caller ever relied on it, this fails loudly. 3–5. **Behavioural coverage** of the three documented code paths: `is_scale=True, norm_type="mean_std"`, `is_scale=False, norm_type="mean_std"`, and `norm_type="none"`. 6. **End-to-end via the same `getattr(operators, "StandardizeImage")` call** the recognizer uses, with a real numpy image, so any rename or removal surfaces as `AttributeError` instead of silently skipping the step. Verified both ways: - Without the fix → **all 6 tests fail** (Python even suggests `'StandardizeImag' → 'StandardizeImage'`) - With the fix → all 6 pass in 0.15s The test file follows the project's existing pattern (`test/unit_test/deepdoc/parser/test_html_parser.py`): load the target module via `importlib.util.spec_from_file_location`, stub the only project-internal import (`rag.utils.lazy_image`), and assert against the loaded module — no full RAGFlow runtime required. ## Risk Very low. The class is renamed; no public Python API was using the misnamed class. The only reference path is the `"StandardizeImage"` string in `recognizer.py:270`, which now resolves correctly. ## Out of scope - No other ops in `operators.py` are affected; checked all the others (DecodeImage, NormalizeImage, Permute, etc.) and they all use correct names. - The dynamic-dispatch lookups in `recognizer.py` for `LinearResize`, `StandardizeImage`, `Permute`, `PadStride` all use the same dispatch path; only the `StandardizeImage` key was broken. No other keys need fixing. Made with [Cursor](https://cursor.com) --------- Co-authored-by: Taranum01 <Taranum01@users.noreply.github.com> Co-authored-by: Cursor <cursoragent@cursor.com> Co-authored-by: Zhichang Yu <yuzhichang@gmail.com>
### What problem does this PR solve? Issue [infiniflow#16758](infiniflow#16758) — clicking a chunk whose data references a single-line variable from an Await-Response (UserFillUp) component, the Agent's `user_prompt` is being resolved against the **previous** canvas run's captured value instead of the current run's value. The system-prompt path works only because the system prompt is computed upstream and re-reads the value on the new run. ### Root cause `Canvas._run_impl` reset every path component with `only_output=True`, so `_param.inputs` was never cleared between runs. `ComponentBase.get_input()` calls `set_input_value(var, resolved)` at line 482, which writes the resolved variable into `self._param.inputs[var]["value"]`. On the next canvas run, that input was never cleared, so the previous run's resolved value stuck around. The Agent's `kwargs.get("user_prompt")` then read the stale string and forwarded it to the LLM, which produced the "Understood. Please provide the text..." fallback because the prompt looked empty. ### What changed? - `agent/canvas.py` — differentiate `begin` (still `only_output=True`, since it has no inputs and the webhook payload branch below populates `request` explicitly) from non-begin path components (reset with `only_output=False`, which clears both `inputs` and `outputs`). - `test/unit_test/agent/test_canvas_input_reset.py` — new pytest module. Pinned the contract: non-begin path components receive `only_output=False`. The fix is small enough to verify with a stub canvas rather than a full canvas-runtime test (the existing agent conftest hits an unrelated `scholarly` import on Python 3.13, so a real canvas import would require fixing that first). ### Backward compatibility - `Begin` behaviour unchanged. - All non-begin path components: previously persisted inputs across runs (the bug); now reset between runs. Components that were relying on stale inputs (none found in the existing test suite) would lose that as a side effect, but that is the entire point of the fix. - No API surface change. No backend change. ### Testing ``` $ uv run pytest test/unit_test/agent/test_canvas_input_reset.py -v collected 4 items test/unit_test/agent/test_canvas_input_reset.py::test_begin_is_reset_with_only_output_true PASSED test/unit_test/agent/test_canvas_input_reset.py::test_non_begin_path_components_are_reset_with_only_output_false PASSED test/unit_test/agent/test_canvas_input_reset.py::test_only_path_components_are_reset PASSED test/unit_test/agent/test_canvas_input_reset.py::test_inputs_reset_flag_is_passed_to_non_begin_components PASSED 4 passed in 0.14s ``` `python3 -m py_compile agent/canvas.py` clean. Existing agent test files (`test_switch.py`, `test_llm_prompt.py`) hit a pre-existing `scholarly` import error on Python 3.13 (unrelated to this PR), so I couldn't run the full agent suite. Recommend fixing the `scholarly` import separately. ### Files changed - `agent/canvas.py` (+9 / −1) - `test/unit_test/agent/test_canvas_input_reset.py` (new, +104) Fixes infiniflow#16758 --------- Co-authored-by: Harsh Kashyap <harshkashyap@Harshs-MacBook-Pro.local> Co-authored-by: Zhichang Yu <yuzhichang@gmail.com> Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
## Summary - Merge upstream main and retain PubMed component support. - Preserve newly registered tool components and update registry verification. ## Tests - `bash build.sh --test ./internal/agent/component/...` - `bash build.sh --test ./internal/agent/tool/...` <img width="1817" height="972" alt="image" src="https://github.com/user-attachments/assets/9fcb9448-9e26-41b9-940c-a9bfde9835e9" /> --------- Co-authored-by: Jin Hai <haijin.chn@gmail.com>
### Summary 1. update docker compose file to start NATS healthy 2. Add two commands ``` RAGFlow(admin)> live; SUCCESS RAGFlow(admin)> health; +---------------+-------+ | field | value | +---------------+-------+ | storage | ok | | message_queue | ok | | status | ok | | db | ok | | redis | ok | | doc_engine | ok | +---------------+-------+ ``` --------- Signed-off-by: Jin Hai <haijin.chn@gmail.com>
As title. Signed-off-by: Jin Hai <haijin.chn@gmail.com>
…iflow#16808) ## Summary - register the Go `ArXiv` canvas component and add its input form - align the Go ArXiv request/schema with Python by keeping only `query` in runtime args and moving `top_n`/`sort_by` to node params - keep ArXiv results consistent for canvas output and tool response handling ## Test - `bash build.sh --test ./internal/agent/tool ./internal/agent/component` <img width="1817" height="972" alt="image" src="https://github.com/user-attachments/assets/7f726dfa-a996-4561-b481-cb0b44bec81c" />
…very (infiniflow#16826) ### Summary 1. refactor dataflow_service.go 2. guard nats message re-delivery 3. support document parse cancelling & re-run
…w#16822) ### Summary Implement builtin chunk mehtod as ingestion pipeline in GO
…nfiniflow#16851) ### Summary Feat: Added support for session graph and session essence templates.
### Summary as title. --------- Signed-off-by: Jin Hai <haijin.chn@gmail.com>
…16849) ## Summary - Add the GitHub Canvas component with tool registration and reference propagation. - Align the Invoke component with the Python contract for node config, input form, response output, and timing fields. - GitHub search and HTTP Invoke now work correctly in the Go Canvas runtime. ## Tests - `bash build.sh --test ./internal/agent/tool/...` - `bash build.sh --test ./internal/agent/component/...` Note: the untracked go_ragflow_cli file is not part of the PR changes. <img width="1813" height="1102" alt="image" src="https://github.com/user-attachments/assets/f69cef32-59a0-4287-a06b-6843d85198cf" /> <img width="1813" height="1102" alt="image" src="https://github.com/user-attachments/assets/b37dfc31-bc9b-4937-a38e-d2184bb157fe" />
…nfiniflow#16692) ### Summary Port the **QWeather** agent tool to the modern `ToolBase` / `_invoke` interface. It was still written against the removed legacy `ComponentBase` / `_run` / `be_output` API, so it was non-functional as an Agent tool — adding it to an Agent raised `AttributeError` because it had no `get_meta()`. This is the same defect that was fixed for the AkShare tool in infiniflow#16417. **Changes** - `QWeatherParam` now extends `ToolParamBase` with a `meta` exposing a `query` (location) parameter, and adds `get_input_form()`. Existing config (`web_apikey`, `lang`, `type`, `user_type`, `time_period`) is preserved. - `QWeather` now extends `ToolBase` and implements `_invoke(**kwargs)` with the standard retry loop, cancellation checks, `set_output("formalized_content", ...)`, and `thoughts()`. The weather / indices / air-quality branches and the API error-code messages are kept. - Added `test/unit_test/agent/component/test_qweather.py` covering the restored `meta`, param validation, the weather-now and multi-day and indices branches, the empty-query short-circuit, and the location-lookup error message. **Testing** - `ruff check agent/tools/qweather.py test/unit_test/agent/component/test_qweather.py` — clean - `ruff format --check` — clean - `pytest test/unit_test/agent/component/test_qweather.py`
### Summary 1. refactor message processing 2. delete un-used componentIndexMap 3. unfold (delete) internal/ingestion/task/task_handler.go
### Summary certain tests fail because of test drift and were fixed, other because of go issues --------- Co-authored-by: Wang Qi <wangq8@outlook.com>
…on (infiniflow#16854) ## Summary - Align Go WenCai and SearXNG behavior, schemas, and node parameters with Python. - Add the `WenCai` and `SearXNG` Canvas components and register their tool factories. - Match Python's current WenCai behavior by returning an empty report while its upstream request is disabled. - Add SearXNG request validation, SSRF-safe DNS pinning, raw result preservation, and reference rendering. - Support context cancellation, error envelopes, and lock-safe retrieval references. ## Tests Passed: - `bash build.sh --test ./internal/agent/tool/...` - `bash build.sh --test ./internal/agent/component/...` - `bash build.sh --test ./internal/agent/runtime/...` - `bash build.sh --test ./internal/agent/...` - `cd web && npm run type-check` <img width="1900" height="1102" alt="image" src="https://github.com/user-attachments/assets/ec77d217-d9fd-455a-96ec-9aabf6841109" /> <img width="1900" height="1102" alt="image" src="https://github.com/user-attachments/assets/52ac129f-cb65-453d-ae48-cc518803ac23" />
### Summary As title Unable to test it since I don't have apiKey for `openai` , `Anthropic` and `Gemini` --- <img width="1130" height="557" alt="image" src="https://github.com/user-attachments/assets/11570c75-68f3-490d-8186-4ecbcd8b8f40" />
### Summary ``` RAGFlow(admin)> show version; +--------------+-----------------------+ | field | value | +--------------+-----------------------+ | version | v0.26.4-84-g547bc8614 | | version_type | open source | +--------------+-----------------------+ ``` --------- Signed-off-by: Jin Hai <haijin.chn@gmail.com>
…ate is displayed at the end. (infiniflow#16861) ### Summary Feat: If the interval between two outputs exceeds 600ms, a loading state is displayed at the end.
### Summary In Go and python implementation, the dataset / KB id isn't validated if it is accessible by this user. --------- Signed-off-by: Jin Hai <haijin.chn@gmail.com>
…niflow#16758) (infiniflow#16792) ## Summary `ComponentBase.variable_ref_patt` (and its duplicate in `agent.canvas.Graph.get_value_with_variable`) is the regex the canvas runtime uses to find `cpn_id@var_nm` template refs in component prompts. The `cpn_id` half was constrained to `[a-zA-Z:0-9]+`, which silently dropped underscores. Component ids emitted by the frontend all contain underscores (`userfillup_abc`, `retrieval_xyz`, `llm_0`, `message_0`, …), so any template ref like `{userfillup_abc@line}` failed to match. The placeholder then leaked through to the LLM verbatim, and the Agent answered only its system-prompt directive. This is exactly the "unconsidered await response" symptom in infiniflow#16758: ``` Begin(Task) -> Await response -> Agent -> Message ``` Widen `cpn_id` from `[a-zA-Z:0-9]+` to `[a-zA-Z0-9_]+`. Bare `{line}` (no cpn_id) remains unrecognised so it stays literal until the user wires it up — matching the existing `VARIABLE_REF_PATTERN` shape used by `agent.dsl_migration` for the same purpose. ## Changes - `agent/component/base.py` — fix `variable_ref_patt` class attribute. - `agent/canvas.py` — same fix applied to the inline regex inside `Graph.get_value_with_variable` (kept as the literal regex to avoid coupling the two unrelated sites). - `test/testcases/test_web_api/test_canvas_app/test_variable_ref_pattern_unit.py` — new regression test pinning both the regex shape and end-to-end resolution. ## Regression coverage ``` test_variable_ref_patt_matches_underscored_component_ids PASSED test_variable_ref_patt_still_matches_legacy_ids PASSED test_get_input_elements_from_text_resolves_underscored_id PASSED test_string_format_substitutes_underscored_ref PASSED test_variable_ref_patt_does_not_match_bare_var_name PASSED ``` All five regression tests fail against the pre-fix regex (verified via `git stash` round trip — drop fix, tests fail, restore fix, tests pass). The two targeted existing tests in the same directory (`test_fillup_unit.py`, `test_iterationitem_unit.py`) continue to pass. ## Repro before the fix ```python import re patt = r"\{* *\{([a-zA-Z:0-9]+@[A-Za-z0-9_.-]+|sys\.[A-Za-z0-9_.]+|env\.[A-Za-z0-9_.]+)\} *\}*" list(re.finditer(patt, "{userfillup_abc@line}")) # => [] # <-- bug ``` ## Repro after the fix ```python import re patt = r"\{* *\{([a-zA-Z0-9_]+@[A-Za-z0-9_.-]+|sys\.[A-Za-z0-9_.]+|env\.[A-Za-z0-9_.]+)\} *\}*" list(re.finditer(patt, "{userfillup_abc@line}")) # => [<re.Match object; span=(0, 24), match='{userfillup_abc@line}'>] ``` Fixes infiniflow#16758 ## Test plan - [x] New unit tests pass - [x] Reverse-apply the fix and confirm the regression tests fail (they do) - [x] `test_fillup_unit.py` (existing sibling suite) still passes - [x] `test_iterationitem_unit.py` (existing sibling suite) still passes - [ ] Project CI green --------- Co-authored-by: Taranum01 <taranum01@users.noreply.github.com> Co-authored-by: Cursor <cursoragent@cursor.com>
dosubot
Bot
added
🐞 bug
Contributor
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (1)
🚧 Files skipped from review as they are similar to previous changes (1)
📝 WalkthroughWalkthroughAzure credential parsing is centralized in ChangesAzure credential resolution
Estimated code review effort: 3 (Moderate) | ~20 minutes Poem
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (1)
rag/llm/key_utils.py (1)
55-55: 📐 Maintainability & Code Quality | 🔵 Trivial | ⚡ Quick winKeep the resolver internal.
All current consumers explicitly import
_resolve_azure_credentials, so adding this underscore-prefixed helper to__all__unnecessarily creates a public compatibility surface.Proposed fix
-__all__ = ["_normalize_replicate_key", "_resolve_azure_credentials"] +__all__ = ["_normalize_replicate_key"]As per coding guidelines, “Reduce public surface area by making helpers private or internal when possible.”
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@rag/llm/key_utils.py` at line 55, Remove _resolve_azure_credentials from __all__ in key_utils.py, leaving only the intended public export while keeping the helper itself and its existing internal consumers unchanged.Source: Coding guidelines
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@test/unit_test/rag/llm/test_chat_model_azure_key_fallback.py`:
- Around line 123-125: In the test setup around SupportedLiteLLMProvider, stop
assigning the unnecessary MiniMax enum member and scope the OpenRouter
assignment to the existing context manager so it is automatically restored after
the test. Ensure the shim cannot leak state into subsequent tests, preferably by
deleting or otherwise resetting the patched attribute during teardown.
---
Nitpick comments:
In `@rag/llm/key_utils.py`:
- Line 55: Remove _resolve_azure_credentials from __all__ in key_utils.py,
leaving only the intended public export while keeping the helper itself and its
existing internal consumers unchanged.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 6652bbd4-847a-4166-81f6-71f740f4c8bf
📒 Files selected for processing (5)
rag/llm/chat_model.pyrag/llm/cv_model.pyrag/llm/embedding_model.pyrag/llm/key_utils.pytest/unit_test/rag/llm/test_chat_model_azure_key_fallback.py
4 tasks
This was referenced Jul 24, 2026
Open
Move the SupportedLiteLLMProvider.OpenRouter assignment inside the with block using patch.object(..., create=True) so the patched member is automatically restored after the test and cannot leak into subsequent tests. Drop the unused MiniMax assignment — the Azure branch in LiteLLMBase.__init__ never reaches the MiniMax lookup.
This was referenced Jul 28, 2026
Harsh23Kashyap
added a commit
to Harsh23Kashyap/ragflow
that referenced
this pull request
Aug 20, 2026
Pre-fix, the Azure-OpenAI provider in rag/llm had 4 unfixed call sites
with 3 different patterns for parsing the key:
- chat (chat_model.py:1649-1651): bare json.loads(key).get(...) with
no try/except; crashes with JSONDecodeError on a plain Portal API
key (the most common user mistake) and AttributeError on any JSON
non-object input.
- vision / CV (cv_model.py:380): local helper with silent fallback
for non-object JSON, silently using the raw key string.
- embed (embedding_model.py:325): identical local helper, a duplicate
copy of the CV one.
- seq2txt (sequence2txt_model.py:386): raw key passed straight to
AzureOpenAI; a JSON string was used as the api_key and the call
silently failed at the API with a 401.
Unify all 4 through a single _resolve_azure_credentials helper in
rag/llm/key_utils.py that follows the same pattern as the other 5
helpers in the JSON-decode family (Bedrock, BaiduYiyan, VolcEngine,
OpenRouter, GoogleCV):
1. Accepts a dict (returned verbatim) or a JSON-string-encoded dict.
2. On non-JSON input, raises a clear ModelException (retryable=False)
naming the required fields and pointing at conf/models/azure.json,
instead of letting json.loads bubble up as JSONDecodeError.
3. On a JSON top-level type that is not a dict (list, string,
number, bool, null), raises the same clear ModelException instead
of calling .get('api_key') on the value and getting AttributeError.
Returns (api_key, api_version) where api_version defaults to
'2024-02-01' and api_key defaults to '' if missing.
The two duplicate _resolve_azure_credentials definitions in
cv_model.py and embedding_model.py are removed in favor of the
shared helper.
Fixes infiniflow#17675. Supersedes the partial infiniflow#17215 (which only touched the
chat branch and used a silent-fallback helper).
Harsh23Kashyap
added a commit
to Harsh23Kashyap/ragflow
that referenced
this pull request
Aug 20, 2026
…t a JSON object (infiniflow#17389) The BaiduYiyan / Qianfan provider in rag/llm/chat_model.py:1189 does an unguarded `json.loads(key)` followed by `.get("yiyan_ak")` and `.get("yiyan_sk")`. The provider REQUIRES a JSON key (per conf/models/baidu.json) but a user pasting a plain Baidu API key like "bce-v3/ALTAK-.../..." (the most common mistake: copying from the Qianfan console into a BaiduYiyan field) would crash with `json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)` from inside rag/llm internals, with no indication of what the user did wrong. This is the BaiduYiyan equivalent of: - infiniflow#17204 / PR infiniflow#17215 (Azure-OpenAI) - infiniflow#17373 / PR infiniflow#17377 (AWS Bedrock) Add a parallel helper to rag.llm.key_utils that mirrors the Bedrock fix shape: ``` def _resolve_qianfan_credentials(key): # Accepts dict or JSON-string-encoded dict. Returns the dict. # On non-JSON input (e.g. plain "bce-v3/..."): # raises ModelException with the required schema in the message # (yiyan_ak + yiyan_sk, conf/models/baidu.json reference). # On JSON top-level non-dict (list, string, number): # raises ModelException rather than letting the caller hit # AttributeError on .get("yiyan_ak"). ``` Wire BaiduYiyanChat.__init__ (chat_model.py:1189) through the helper instead of the bare `json.loads(key)`. The downstream `key.get("yiyan_ak", "")` / `.get("yiyan_sk", "")` calls are unchanged. No public API change. No data-model change. No migration. Fixes infiniflow#17389.
Harsh23Kashyap
added a commit
to Harsh23Kashyap/ragflow
that referenced
this pull request
Aug 20, 2026
The Bedrock provider requires a JSON key (auth_mode + bedrock_region plus
mode-specific fields per conf/models/bedrock.json), but every call site
in rag/llm/ was doing an unguarded json.loads(key) followed by
.get("auth_mode"). A user pasting a plain AWS access key (the most
common mistake: copying from the AWS console into a Bedrock field) would
crash with json.decoder.JSONDecodeError: Expecting value: line 1 column
1 (char 0) from inside rag/llm internals -- no indication of what the
user did wrong.
This is the Bedrock equivalent of infiniflow#17204 (Azure-OpenAI), which was fixed
in PR infiniflow#17215. Add a parallel helper to rag.llm.key_utils that:
- Accepts a pre-parsed dict (returns verbatim) or a JSON-string-encoded
dict (parses and returns the dict).
- On non-JSON input, raises a clear ModelException (retryable=False)
that names the required fields and points at
conf/models/bedrock.json for the full schema. Operators can
self-diagnose the mistake without opening a GitHub issue.
- On a JSON top-level type that is not a dict (list, string, number),
raises the same ModelException family rather than letting the model
class call .get("auth_mode") on a non-dict and hit
AttributeError downstream.
This commit adds the helper only. The wire-up into chat_model.py,
cv_model.py, embedding_model.py and rerank_model.py lands in the next
commit; the model classes' existing key.get("auth_mode") /
bedrock_key.get("auth_mode") calls are unchanged.
Fixes infiniflow#17373.
Harsh23Kashyap
added a commit
to Harsh23Kashyap/ragflow
that referenced
this pull request
Aug 20, 2026
The Bedrock provider requires a JSON key (auth_mode + bedrock_region plus
mode-specific fields per conf/models/bedrock.json), but every call site
in rag/llm/ was doing an unguarded json.loads(key) followed by
.get("auth_mode"). A user pasting a plain AWS access key (the most
common mistake: copying from the AWS console into a Bedrock field) would
crash with json.decoder.JSONDecodeError: Expecting value: line 1 column
1 (char 0) from inside rag/llm internals -- no indication of what the
user did wrong.
This is the Bedrock equivalent of infiniflow#17204 (Azure-OpenAI), which was fixed
in PR infiniflow#17215. Add a parallel helper to rag.llm.key_utils that:
- Accepts a pre-parsed dict (returns verbatim) or a JSON-string-encoded
dict (parses and returns the dict).
- On non-JSON input, raises a clear ModelException (retryable=False)
that names the required fields and points at
conf/models/bedrock.json for the full schema. Operators can
self-diagnose the mistake without opening a GitHub issue.
- On a JSON top-level type that is not a dict (list, string, number),
raises the same ModelException family rather than letting the model
class call .get("auth_mode") on a non-dict and hit
AttributeError downstream.
This commit adds the helper only. The wire-up into chat_model.py,
cv_model.py, embedding_model.py and rerank_model.py lands in the next
commit; the model classes' existing key.get("auth_mode") /
bedrock_key.get("auth_mode") calls are unchanged.
Fixes infiniflow#17373.
Contributor
|
would you please resolve the conflicts? |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
20 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.